Skip to content

Text-to-Video Generation with AnimateDiff

Overview

AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning by Yuwei Guo, Ceyuan Yang, Anyi Rao, Yaohui Wang, Yu Qiao, Dahua Lin, Bo Dai.

The abstract of the paper is the following:

With the advance of text-to-image models (e.g., Stable Diffusion) and corresponding personalization techniques such as DreamBooth and LoRA, everyone can manifest their imagination into high-quality images at an affordable cost. Subsequently, there is a great demand for image animation techniques to further combine generated static images with motion dynamics. In this report, we propose a practical framework to animate most of the existing personalized text-to-image models once and for all, saving efforts in model-specific tuning. At the core of the proposed framework is to insert a newly initialized motion modeling module into the frozen text-to-image model and train it on video clips to distill reasonable motion priors. Once trained, by simply injecting this motion modeling module, all personalized versions derived from the same base T2I readily become text-driven models that produce diverse and personalized animated images. We conduct our evaluation on several public representative personalized text-to-image models across anime pictures and realistic photographs, and demonstrate that our proposed framework helps these models generate temporally smooth animation clips while preserving the domain and diversity of their outputs. Code and pre-trained weights will be publicly available at this https URL.

Available Pipelines

Pipeline Tasks
AnimateDiffPipeline Text-to-Video Generation with AnimateDiff
AnimateDiffControlNetPipeline Controlled Video-to-Video Generation with AnimateDiff using ControlNet
AnimateDiffSparseControlNetPipeline Controlled Video-to-Video Generation with AnimateDiff using SparseCtrl
AnimateDiffSDXLPipeline Video-to-Video Generation with AnimateDiff
AnimateDiffVideoToVideoPipeline Video-to-Video Generation with AnimateDiff

Available checkpoints

Motion Adapter checkpoints can be found under guoyww. These checkpoints are meant to work with any model based on Stable Diffusion 1.4/1.5.

Usage example

AnimateDiffPipeline

AnimateDiff works with a MotionAdapter checkpoint and a Stable Diffusion model checkpoint. The MotionAdapter is a collection of Motion Modules that are responsible for adding coherent motion across image frames. These modules are applied after the Resnet and Attention blocks in Stable Diffusion UNet.

The following example demonstrates how to use a MotionAdapter checkpoint with Diffusers for inference based on StableDiffusion-1.4/1.5.

import mindspore as ms
from mindone.diffusers import AnimateDiffPipeline, DDIMScheduler, MotionAdapter
from mindone.diffusers.utils import export_to_gif

# Load the motion adapter
adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5-2", mindspore_dtype=ms.float16)
# load SD 1.5 based finetuned model
model_id = "SG161222/Realistic_Vision_V5.1_noVAE"
pipe = AnimateDiffPipeline.from_pretrained(model_id, motion_adapter=adapter, mindspore_dtype=ms.float16)
scheduler = DDIMScheduler.from_pretrained(
    model_id,
    subfolder="scheduler",
    clip_sample=False,
    timestep_spacing="linspace",
    beta_schedule="linear",
    steps_offset=1,
)
pipe.scheduler = scheduler

output = pipe(
    prompt=(
        "masterpiece, bestquality, highlydetailed, ultradetailed, sunset, "
        "orange sky, warm lighting, fishing boats, ocean waves seagulls, "
        "rippling water, wharf, silhouette, serene atmosphere, dusk, evening glow, "
        "golden hour, coastal landscape, seaside scenery"
    ),
    negative_prompt="bad quality, worse quality",
    num_frames=16,
    guidance_scale=7.5,
    num_inference_steps=25,
)
frames = output[0][0]
export_to_gif(frames, "animation.gif")

Here are some sample outputs:

masterpiece, bestquality, sunset.
masterpiece, bestquality, sunset

Tip

AnimateDiff tends to work better with finetuned Stable Diffusion models. If you plan on using a scheduler that can clip samples, make sure to disable it by setting clip_sample=False in the scheduler as this can also have an adverse effect on generated samples. Additionally, the AnimateDiff checkpoints can be sensitive to the beta schedule of the scheduler. We recommend setting this to linear.

AnimateDiffControlNetPipeline

Warning

⚠️ MindONE currently does not support the full process for condition frames generating, as MindONE does not yet support ZoeDetector from controlnet_aux. Therefore, you need to prepare the conditioning_video in advance to continue the process.

AnimateDiff can also be used with ControlNets ControlNet was introduced in Adding Conditional Control to Text-to-Image Diffusion Models by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala. With a ControlNet model, you can provide an additional control image to condition and control Stable Diffusion generation. For example, if you provide depth maps, the ControlNet model generates a video that'll preserve the spatial information from the depth maps. It is a more flexible and accurate way to control the video generation process.

import mindspore as ms
import numpy as np
from mindone.diffusers import AnimateDiffControlNetPipeline, AutoencoderKL, ControlNetModel, MotionAdapter, LCMScheduler
from mindone.diffusers.utils import export_to_gif, load_video

# Download controlnets from https://huggingface.co/lllyasviel/ControlNet-v1-1 to use .from_single_file
# Download Diffusers-format controlnets, such as https://huggingface.co/lllyasviel/sd-controlnet-depth, to use .from_pretrained()
controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-depth", mindspore_dtype=ms.float16)

# We use AnimateLCM for this example but one can use the original motion adapters as well (for example, https://huggingface.co/guoyww/animatediff-motion-adapter-v1-5-3)
motion_adapter = MotionAdapter.from_pretrained("wangfuyun/AnimateLCM")

vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse", mindspore_dtype=ms.float16)
pipe: AnimateDiffControlNetPipeline = AnimateDiffControlNetPipeline.from_pretrained(
    "SG161222/Realistic_Vision_V5.1_noVAE",
    motion_adapter=motion_adapter,
    controlnet=controlnet,
    vae=vae,
).to(dtype=ms.float16)
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config, beta_schedule="linear")
pipe.load_lora_weights("wangfuyun/AnimateLCM", weight_name="AnimateLCM_sd15_t2v_lora.safetensors", adapter_name="lcm-lora")
pipe.set_adapters(["lcm-lora"], [0.8])

video = load_video("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-vid2vid-input-1.gif")
conditioning_video = load_video("path/to/conditioning_video")
conditioning_frames = []

with pipe.progress_bar(total=len(conditioning_video)) as progress_bar:
    for frame in conditioning_video:
        conditioning_frames.append(frame)
        progress_bar.update()

prompt = "a panda, playing a guitar, sitting in a pink boat, in the ocean, mountains in background, realistic, high quality"
negative_prompt = "bad quality, worst quality"

video = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    num_frames=len(video),
    num_inference_steps=10,
    guidance_scale=2.0,
    conditioning_frames=conditioning_frames,
    generator=np.random.Generator(np.random.PCG64(seed=42)),
)[0][0]

export_to_gif(video, "animatediff_controlnet.gif", fps=8)

Here are some sample outputs:

Source Video Output Video
raccoon playing a guitar
racoon playing a guitar 		a panda, playing a guitar, sitting in a pink boat, in the ocean, mountains in background, realistic, high quality
a panda, playing a guitar, sitting in a pink boat, in the ocean, mountains in background, realistic, high quality

AnimateDiffSparseControlNetPipeline

SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models for achieving controlled generation in text-to-video diffusion models by Yuwei Guo, Ceyuan Yang, Anyi Rao, Maneesh Agrawala, Dahua Lin, and Bo Dai.

The abstract from the paper is:

The development of text-to-video (T2V), i.e., generating videos with a given text prompt, has been significantly advanced in recent years. However, relying solely on text prompts often results in ambiguous frame composition due to spatial uncertainty. The research community thus leverages the dense structure signals, e.g., per-frame depth/edge sequences, to enhance controllability, whose collection accordingly increases the burden of inference. In this work, we present SparseCtrl to enable flexible structure control with temporally sparse signals, requiring only one or a few inputs, as shown in Figure 1. It incorporates an additional condition encoder to process these sparse signals while leaving the pre-trained T2V model untouched. The proposed approach is compatible with various modalities, including sketches, depth maps, and RGB images, providing more practical control for video generation and promoting applications such as storyboarding, depth rendering, keyframe animation, and interpolation. Extensive experiments demonstrate the generalization of SparseCtrl on both original and personalized T2V generators. Codes and models will be publicly available at this https URL.

SparseCtrl introduces the following checkpoints for controlled text-to-video generation:

Using SparseCtrl Scribble

import mindspore as ms
import numpy as np

from mindone.diffusers import AnimateDiffSparseControlNetPipeline
from mindone.diffusers.models import AutoencoderKL, MotionAdapter, SparseControlNetModel
from mindone.diffusers.schedulers import DPMSolverMultistepScheduler
from mindone.diffusers.utils import export_to_gif, load_image


model_id = "SG161222/Realistic_Vision_V5.1_noVAE"
motion_adapter_id = "guoyww/animatediff-motion-adapter-v1-5-3"
controlnet_id = "guoyww/animatediff-sparsectrl-scribble"
lora_adapter_id = "guoyww/animatediff-motion-lora-v1-5-3"
vae_id = "stabilityai/sd-vae-ft-mse"

motion_adapter = MotionAdapter.from_pretrained(motion_adapter_id, mindspore_dtype=ms.float16)
controlnet = SparseControlNetModel.from_pretrained(controlnet_id, mindspore_dtype=ms.float16)
vae = AutoencoderKL.from_pretrained(vae_id, mindspore_dtype=ms.float16)
scheduler = DPMSolverMultistepScheduler.from_pretrained(
    model_id,
    subfolder="scheduler",
    beta_schedule="linear",
    algorithm_type="dpmsolver++",
    use_karras_sigmas=True,
)
pipe = AnimateDiffSparseControlNetPipeline.from_pretrained(
    model_id,
    motion_adapter=motion_adapter,
    controlnet=controlnet,
    vae=vae,
    scheduler=scheduler,
    mindspore_dtype=ms.float16,
)
pipe.load_lora_weights(lora_adapter_id, adapter_name="motion_lora")
pipe.fuse_lora(lora_scale=1.0)

prompt = "an aerial view of a cyberpunk city, night time, neon lights, masterpiece, high quality"
negative_prompt = "low quality, worst quality, letterboxed"

image_files = [
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-scribble-1.png",
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-scribble-2.png",
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-scribble-3.png"
]
condition_frame_indices = [0, 8, 15]
conditioning_frames = [load_image(img_file) for img_file in image_files]

video = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    num_inference_steps=25,
    conditioning_frames=conditioning_frames,
    controlnet_conditioning_scale=1.0,
    controlnet_frame_indices=condition_frame_indices,
    generator=np.random.Generator(np.random.PCG64(seed=1337)),
)[0][0]
export_to_gif(video, "output.gif")

Here are some sample outputs:

an aerial view of a cyberpunk city, night time, neon lights, masterpiece, high quality
scribble-1
scribble-2
scribble-3
an aerial view of a cyberpunk city, night time, neon lights, masterpiece, high quality

Using SparseCtrl RGB

import mindspore as ms
import numpy as np

from mindone.diffusers import AnimateDiffSparseControlNetPipeline
from mindone.diffusers.models import AutoencoderKL, MotionAdapter, SparseControlNetModel
from mindone.diffusers.schedulers import DPMSolverMultistepScheduler
from mindone.diffusers.utils import export_to_gif, load_image


model_id = "SG161222/Realistic_Vision_V5.1_noVAE"
motion_adapter_id = "guoyww/animatediff-motion-adapter-v1-5-3"
controlnet_id = "guoyww/animatediff-sparsectrl-rgb"
lora_adapter_id = "guoyww/animatediff-motion-lora-v1-5-3"
vae_id = "stabilityai/sd-vae-ft-mse"

motion_adapter = MotionAdapter.from_pretrained(motion_adapter_id, mindspore_dtype=ms.float16)
controlnet = SparseControlNetModel.from_pretrained(controlnet_id, mindspore_dtype=ms.float16)
vae = AutoencoderKL.from_pretrained(vae_id, mindspore_dtype=ms.float16)
scheduler = DPMSolverMultistepScheduler.from_pretrained(
    model_id,
    subfolder="scheduler",
    beta_schedule="linear",
    algorithm_type="dpmsolver++",
    use_karras_sigmas=True,
)
pipe = AnimateDiffSparseControlNetPipeline.from_pretrained(
    model_id,
    motion_adapter=motion_adapter,
    controlnet=controlnet,
    vae=vae,
    scheduler=scheduler,
    mindspore_dtype=ms.float16,
)
pipe.load_lora_weights(lora_adapter_id, adapter_name="motion_lora")

image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-firework.png")

video = pipe(
    prompt="closeup face photo of man in black clothes, night city street, bokeh, fireworks in background",
    negative_prompt="low quality, worst quality",
    num_inference_steps=25,
    conditioning_frames=image,
    controlnet_frame_indices=[0],
    controlnet_conditioning_scale=1.0,
    generator=np.random.Generator(np.random.PCG64(seed=42)),
)[0][0]
export_to_gif(video, "output.gif")

Here are some sample outputs:

closeup face photo of man in black clothes, night city street, bokeh, fireworks in background
closeup face photo of man in black clothes, night city street, bokeh, fireworks in background
closeup face photo of man in black clothes, night city street, bokeh, fireworks in background

AnimateDiffSDXLPipeline

AnimateDiff can also be used with SDXL models. This is currently an experimental feature as only a beta release of the motion adapter checkpoint is available.

import mindspore as ms
from mindone.diffusers.models import MotionAdapter
from mindone.diffusers import AnimateDiffSDXLPipeline, DDIMScheduler
from mindone.diffusers.utils import export_to_gif

adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-sdxl-beta", mindspore_dtype=ms.float16)
model_id = "stabilityai/stable-diffusion-xl-base-1.0"

scheduler = DDIMScheduler.from_pretrained(
    model_id,
    subfolder="scheduler",
    clip_sample=False,
    timestep_spacing="linspace",
    beta_schedule="linear",
    steps_offset=1,
)

pipe = AnimateDiffSDXLPipeline.from_pretrained(
    model_id,
    motion_adapter=adapter,
    scheduler=scheduler,
    mindspore_dtype=ms.float16,
    variant="fp16",
)


output = pipe(
    prompt="a panda surfing in the ocean, realistic, high quality",
    negative_prompt="low quality, worst quality",
    num_inference_steps=20,
    guidance_scale=8,
    width=1024,
    height=1024,
    num_frames=16,
)

frames = output.frames[0]
export_to_gif(frames, "animation.gif")

AnimateDiffVideoToVideoPipeline

AnimateDiff can also be used to generate visually similar videos or enable style/character/background or other edits starting from an initial video, allowing you to seamlessly explore creative possibilities.

import imageio
import requests
import numpy as np
import mindspore as ms
from mindone.diffusers import AnimateDiffVideoToVideoPipeline, DDIMScheduler, MotionAdapter
from mindone.diffusers.utils import export_to_gif
from io import BytesIO
from PIL import Image

# Load the motion adapter
adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5-2", mindspore_dtype=ms.float16)
# load SD 1.5 based finetuned model
model_id = "SG161222/Realistic_Vision_V5.1_noVAE"
pipe = AnimateDiffVideoToVideoPipeline.from_pretrained(model_id, motion_adapter=adapter, mindspore_dtype=ms.float16)
scheduler = DDIMScheduler.from_pretrained(
    model_id,
    subfolder="scheduler",
    clip_sample=False,
    timestep_spacing="linspace",
    beta_schedule="linear",
    steps_offset=1,
)
pipe.scheduler = scheduler

# helper function to load videos
def load_video(file_path: str):
    images = []

    if file_path.startswith(('http://', 'https://')):
        # If the file_path is a URL
        response = requests.get(file_path)
        response.raise_for_status()
        content = BytesIO(response.content)
        vid = imageio.get_reader(content)
    else:
        # Assuming it's a local file path
        vid = imageio.get_reader(file_path)

    for frame in vid:
        pil_image = Image.fromarray(frame)
        images.append(pil_image)

    return images

video = load_video("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-vid2vid-input-1.gif")

output = pipe(
    video = video,
    prompt="panda playing a guitar, on a boat, in the ocean, high quality",
    negative_prompt="bad quality, worse quality",
    guidance_scale=7.5,
    num_inference_steps=25,
    strength=0.5,
    generator=np.random.Generator(np.random.PCG64(42)),
)
frames = output[0][0]
export_to_gif(frames, "animation.gif")

Here are some sample outputs:

Source Video Output Video
raccoon playing a guitar
racoon playing a guitar 		panda playing a guitar
panda playing a guitar
closeup of margot robbie, fireworks in the background, high quality
closeup of margot robbie, fireworks in the background, high quality 		closeup of tony stark, robert downey jr, fireworks
closeup of tony stark, robert downey jr, fireworks

Using Motion LoRAs

Motion LoRAs are a collection of LoRAs that work with the guoyww/animatediff-motion-adapter-v1-5-2 checkpoint. These LoRAs are responsible for adding specific types of motion to the animations.

import numpy as np
import mindspore as ms
from mindone.diffusers import AnimateDiffPipeline, DDIMScheduler, MotionAdapter
from mindone.diffusers.utils import export_to_gif

# Load the motion adapter
adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5-2", mindspore_dtype=ms.float16)
# load SD 1.5 based finetuned model
model_id = "SG161222/Realistic_Vision_V5.1_noVAE"
pipe = AnimateDiffPipeline.from_pretrained(model_id, motion_adapter=adapter, mindspore_dtype=ms.float16)
pipe.load_lora_weights(
    "guoyww/animatediff-motion-lora-zoom-out", adapter_name="zoom-out"
)

scheduler = DDIMScheduler.from_pretrained(
    model_id,
    subfolder="scheduler",
    clip_sample=False,
    beta_schedule="linear",
    timestep_spacing="linspace",
    steps_offset=1,
)
pipe.scheduler = scheduler

output = pipe(
    prompt=(
        "masterpiece, bestquality, highlydetailed, ultradetailed, sunset, "
        "orange sky, warm lighting, fishing boats, ocean waves seagulls, "
        "rippling water, wharf, silhouette, serene atmosphere, dusk, evening glow, "
        "golden hour, coastal landscape, seaside scenery"
    ),
    negative_prompt="bad quality, worse quality",
    num_frames=16,
    guidance_scale=7.5,
    num_inference_steps=25,
    generator=np.random.Generator(np.random.PCG64(42)),
)
frames = output[0][0]
export_to_gif(frames, "animation.gif")
masterpiece, bestquality, sunset.
masterpiece, bestquality, sunset 
import numpy as np
import mindspore as ms
from mindone.diffusers import AnimateDiffPipeline, DDIMScheduler, MotionAdapter
from mindone.diffusers.utils import export_to_gif

# Load the motion adapter
adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5-2", mindspore_dtype=ms.float16)

# load SD 1.5 based finetuned model
model_id = "SG161222/Realistic_Vision_V5.1_noVAE"

pipe = AnimateDiffPipeline.from_pretrained(model_id, motion_adapter=adapter, mindspore_dtype=ms.float16)

pipe.load_lora_weights(
    "guoyww/animatediff-motion-lora-zoom-out", adapter_name="zoom-out",
)

pipe.load_lora_weights(
    "guoyww/animatediff-motion-lora-pan-left", adapter_name="pan-left",
)
pipe.set_adapters(["zoom-out", "pan-left"], adapter_weights=[1.0, 1.0])

scheduler = DDIMScheduler.from_pretrained(
    model_id,
    subfolder="scheduler",
    clip_sample=False,
    timestep_spacing="linspace",
    beta_schedule="linear",
    steps_offset=1,
)

pipe.scheduler = scheduler

output = pipe(
    prompt=(
        "masterpiece, bestquality, highlydetailed, ultradetailed, sunset, "
        "orange sky, warm lighting, fishing boats, ocean waves seagulls, "
        "rippling water, wharf, silhouette, serene atmosphere, dusk, evening glow, "
        "golden hour, coastal landscape, seaside scenery"
    ),
    negative_prompt="bad quality, worse quality",
    num_frames=16,
    guidance_scale=7.5,
    num_inference_steps=25,
    generator=np.random.Generator(np.random.PCG64(42)),
)

frames = output[0][0]

export_to_gif(frames, "animation.gif")
masterpiece, bestquality, sunset.
masterpiece, bestquality, sunset

Using AnimateLCM

AnimateLCM is a motion module checkpoint and an LCM LoRA that have been created using a consistency learning strategy that decouples the distillation of the image generation priors and the motion generation priors.

import numpy as np
from mindone.diffusers import AnimateDiffPipeline, LCMScheduler, MotionAdapter
from mindone.diffusers.utils import export_to_gif

adapter = MotionAdapter.from_pretrained("wangfuyun/AnimateLCM")
pipe = AnimateDiffPipeline.from_pretrained("emilianJR/epiCRealism", motion_adapter=adapter)
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config, beta_schedule="linear")

pipe.load_lora_weights("wangfuyun/AnimateLCM", weight_name="AnimateLCM_sd15_t2v_lora.safetensors", adapter_name="lcm-lora")

output = pipe(
    prompt="A space rocket with trails of smoke behind it launching into space from the desert, 4k, high resolution",
    negative_prompt="bad quality, worse quality, low resolution",
    num_frames=16,
    guidance_scale=1.5,
    num_inference_steps=6,
    generator=np.random.Generator(np.random.PCG64(0)),
)
frames = output[0][0]
export_to_gif(frames, "animatelcm.gif")
A space rocket, 4K.
A space rocket, 4K

AnimateLCM is also compatible with existing Motion LoRAs.

import numpy as np
import mindspore as ms
from mindone.diffusers import AnimateDiffPipeline, LCMScheduler, MotionAdapter
from mindone.diffusers.utils import export_to_gif

adapter = MotionAdapter.from_pretrained("wangfuyun/AnimateLCM")
pipe = AnimateDiffPipeline.from_pretrained("emilianJR/epiCRealism", motion_adapter=adapter)
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config, beta_schedule="linear")

pipe.load_lora_weights("wangfuyun/AnimateLCM", weight_name="AnimateLCM_sd15_t2v_lora.safetensors", adapter_name="lcm-lora")
pipe.load_lora_weights("guoyww/animatediff-motion-lora-tilt-up", adapter_name="tilt-up")

pipe.set_adapters(["lcm-lora", "tilt-up"], [1.0, 0.8])

output = pipe(
    prompt="A space rocket with trails of smoke behind it launching into space from the desert, 4k, high resolution",
    negative_prompt="bad quality, worse quality, low resolution",
    num_frames=16,
    guidance_scale=1.5,
    num_inference_steps=6,
    generator=np.random.Generator(np.random.PCG64(0)),
)
frames = output[0][0]
export_to_gif(frames, "animatelcm-motion-lora.gif")
A space rocket, 4K.
A space rocket, 4K

mindone.diffusers.pipelines.AnimateDiffPipeline

Bases: DiffusionPipeline, StableDiffusionMixin, TextualInversionLoaderMixin, IPAdapterMixin, LoraLoaderMixin

Pipeline for text-to-video generation.

This model inherits from [DiffusionPipeline]. Check the superclass documentation for the generic methods implemented for all pipelines (downloading, saving, running on a particular device, etc.).

The pipeline also inherits the following loading methods
  • [~loaders.TextualInversionLoaderMixin.load_textual_inversion] for loading textual inversion embeddings
  • [~loaders.LoraLoaderMixin.load_lora_weights] for loading LoRA weights
  • [~loaders.LoraLoaderMixin.save_lora_weights] for saving LoRA weights
  • [~loaders.IPAdapterMixin.load_ip_adapter] for loading IP Adapters
PARAMETER DESCRIPTION
vae

Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.

TYPE: [`AutoencoderKL`]

text_encoder

Frozen text-encoder (clip-vit-large-patch14).

TYPE: [`CLIPTextModel`]

tokenizer

A [~transformers.CLIPTokenizer] to tokenize text.

TYPE: `CLIPTokenizer`

unet

A [UNet2DConditionModel] used to create a UNetMotionModel to denoise the encoded video latents.

TYPE: [`UNet2DConditionModel`]

motion_adapter

A [MotionAdapter] to be used in combination with unet to denoise the encoded video latents.

TYPE: [`MotionAdapter`]

scheduler

A scheduler to be used in combination with unet to denoise the encoded image latents. Can be one of [DDIMScheduler], [LMSDiscreteScheduler], or [PNDMScheduler].

TYPE: [`SchedulerMixin`]

Source code in mindone/diffusers/pipelines/animatediff/pipeline_animatediff.py 
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
class AnimateDiffPipeline(
    DiffusionPipeline,
    StableDiffusionMixin,
    TextualInversionLoaderMixin,
    IPAdapterMixin,
    LoraLoaderMixin,
):
    r"""
    Pipeline for text-to-video generation.

    This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods
    implemented for all pipelines (downloading, saving, running on a particular device, etc.).

    The pipeline also inherits the following loading methods:
        - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
        - [`~loaders.LoraLoaderMixin.load_lora_weights`] for loading LoRA weights
        - [`~loaders.LoraLoaderMixin.save_lora_weights`] for saving LoRA weights
        - [`~loaders.IPAdapterMixin.load_ip_adapter`] for loading IP Adapters

    Args:
        vae ([`AutoencoderKL`]):
            Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
        text_encoder ([`CLIPTextModel`]):
            Frozen text-encoder ([clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14)).
        tokenizer (`CLIPTokenizer`):
            A [`~transformers.CLIPTokenizer`] to tokenize text.
        unet ([`UNet2DConditionModel`]):
            A [`UNet2DConditionModel`] used to create a UNetMotionModel to denoise the encoded video latents.
        motion_adapter ([`MotionAdapter`]):
            A [`MotionAdapter`] to be used in combination with `unet` to denoise the encoded video latents.
        scheduler ([`SchedulerMixin`]):
            A scheduler to be used in combination with `unet` to denoise the encoded image latents. Can be one of
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
    """

    model_cpu_offload_seq = "text_encoder->image_encoder->unet->vae"
    _optional_components = ["feature_extractor", "image_encoder", "motion_adapter"]
    _callback_tensor_inputs = ["latents", "prompt_embeds", "negative_prompt_embeds"]

    def __init__(
        self,
        vae: AutoencoderKL,
        text_encoder: CLIPTextModel,
        tokenizer: CLIPTokenizer,
        unet: Union[UNet2DConditionModel, UNetMotionModel],
        motion_adapter: MotionAdapter,
        scheduler: Union[
            DDIMScheduler,
            PNDMScheduler,
            LMSDiscreteScheduler,
            EulerDiscreteScheduler,
            EulerAncestralDiscreteScheduler,
            DPMSolverMultistepScheduler,
        ],
        feature_extractor: CLIPImageProcessor = None,
        image_encoder: CLIPVisionModelWithProjection = None,
    ):
        super().__init__()
        if isinstance(unet, UNet2DConditionModel):
            unet = UNetMotionModel.from_unet2d(unet, motion_adapter)

        self.register_modules(
            vae=vae,
            text_encoder=text_encoder,
            tokenizer=tokenizer,
            unet=unet,
            motion_adapter=motion_adapter,
            scheduler=scheduler,
            feature_extractor=feature_extractor,
            image_encoder=image_encoder,
        )
        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
        self.video_processor = VideoProcessor(do_resize=False, vae_scale_factor=self.vae_scale_factor)

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_prompt with num_images_per_prompt -> num_videos_per_prompt  # noqa: E501
    def encode_prompt(
        self,
        prompt,
        num_images_per_prompt,
        do_classifier_free_guidance,
        negative_prompt=None,
        prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        lora_scale: Optional[float] = None,
        clip_skip: Optional[int] = None,
    ):
        r"""
        Encodes the prompt into text encoder hidden states.

        Args:
            prompt (`str` or `List[str]`, *optional*):
                prompt to be encoded
            num_images_per_prompt (`int`):
                number of images that should be generated per prompt
            do_classifier_free_guidance (`bool`):
                whether to use classifier free guidance or not
            negative_prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts not to guide the image generation. If not defined, one has to pass
                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
                less than `1`).
            prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                provided, text embeddings will be generated from `prompt` input argument.
            negative_prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                argument.
            lora_scale (`float`, *optional*):
                A LoRA scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
            clip_skip (`int`, *optional*):
                Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
                the output of the pre-final layer will be used for computing the prompt embeddings.
        """
        # set lora scale so that monkey patched LoRA
        # function of text encoder can correctly access it
        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
            self._lora_scale = lora_scale

            # dynamically adjust the LoRA scale
            scale_lora_layers(self.text_encoder, lora_scale)

        if prompt is not None and isinstance(prompt, str):
            batch_size = 1
        elif prompt is not None and isinstance(prompt, list):
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        if prompt_embeds is None:
            # textual inversion: process multi-vector tokens if necessary
            if isinstance(self, TextualInversionLoaderMixin):
                prompt = self.maybe_convert_prompt(prompt, self.tokenizer)

            text_inputs = self.tokenizer(
                prompt,
                padding="max_length",
                max_length=self.tokenizer.model_max_length,
                truncation=True,
                return_tensors="np",
            )
            text_input_ids = text_inputs.input_ids
            untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="np").input_ids

            if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not np.array_equal(
                text_input_ids, untruncated_ids
            ):
                removed_text = self.tokenizer.batch_decode(untruncated_ids[:, self.tokenizer.model_max_length - 1 : -1])
                logger.warning(
                    "The following part of your input was truncated because CLIP can only handle sequences up to"
                    f" {self.tokenizer.model_max_length} tokens: {removed_text}"
                )

            if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
                attention_mask = ms.Tensor(text_inputs.attention_mask)
            else:
                attention_mask = None

            if clip_skip is None:
                prompt_embeds = self.text_encoder(ms.Tensor(text_input_ids), attention_mask=attention_mask)
                prompt_embeds = prompt_embeds[0]
            else:
                prompt_embeds = self.text_encoder(
                    ms.Tensor(text_input_ids), attention_mask=attention_mask, output_hidden_states=True
                )
                # Access the `hidden_states` first, that contains a tuple of
                # all the hidden states from the encoder layers. Then index into
                # the tuple to access the hidden states from the desired layer.
                prompt_embeds = prompt_embeds[-1][-(clip_skip + 1)]
                # We also need to apply the final LayerNorm here to not mess with the
                # representations. The `last_hidden_states` that we typically use for
                # obtaining the final prompt representations passes through the LayerNorm
                # layer.
                prompt_embeds = self.text_encoder.text_model.final_layer_norm(prompt_embeds)

        if self.text_encoder is not None:
            prompt_embeds_dtype = self.text_encoder.dtype
        elif self.unet is not None:
            prompt_embeds_dtype = self.unet.dtype
        else:
            prompt_embeds_dtype = prompt_embeds.dtype

        prompt_embeds = prompt_embeds.to(dtype=prompt_embeds_dtype)

        bs_embed, seq_len, _ = prompt_embeds.shape
        # duplicate text embeddings for each generation per prompt, using mps friendly method
        prompt_embeds = prompt_embeds.tile((1, num_images_per_prompt, 1))
        prompt_embeds = prompt_embeds.view(bs_embed * num_images_per_prompt, seq_len, -1)

        # get unconditional embeddings for classifier free guidance
        if do_classifier_free_guidance and negative_prompt_embeds is None:
            uncond_tokens: List[str]
            if negative_prompt is None:
                uncond_tokens = [""] * batch_size
            elif prompt is not None and type(prompt) is not type(negative_prompt):
                raise TypeError(
                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
                    f" {type(prompt)}."
                )
            elif isinstance(negative_prompt, str):
                uncond_tokens = [negative_prompt]
            elif batch_size != len(negative_prompt):
                raise ValueError(
                    f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
                    f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
                    " the batch size of `prompt`."
                )
            else:
                uncond_tokens = negative_prompt

            # textual inversion: process multi-vector tokens if necessary
            if isinstance(self, TextualInversionLoaderMixin):
                uncond_tokens = self.maybe_convert_prompt(uncond_tokens, self.tokenizer)

            max_length = prompt_embeds.shape[1]
            uncond_input = self.tokenizer(
                uncond_tokens,
                padding="max_length",
                max_length=max_length,
                truncation=True,
                return_tensors="np",
            )

            if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
                attention_mask = ms.Tensor(uncond_input.attention_mask)
            else:
                attention_mask = None

            negative_prompt_embeds = self.text_encoder(
                ms.Tensor(uncond_input.input_ids),
                attention_mask=attention_mask,
            )
            negative_prompt_embeds = negative_prompt_embeds[0]

        if do_classifier_free_guidance:
            # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
            seq_len = negative_prompt_embeds.shape[1]

            negative_prompt_embeds = negative_prompt_embeds.to(dtype=prompt_embeds_dtype)

            negative_prompt_embeds = negative_prompt_embeds.tile((1, num_images_per_prompt, 1))
            negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)

        if self.text_encoder is not None:
            if isinstance(self, LoraLoaderMixin):
                # Retrieve the original scale by scaling back the LoRA layers
                unscale_lora_layers(self.text_encoder, lora_scale)

        return prompt_embeds, negative_prompt_embeds

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_image
    def encode_image(self, image, num_images_per_prompt, output_hidden_states=None):
        dtype = next(self.image_encoder.get_parameters()).dtype

        if not isinstance(image, ms.Tensor):
            image = self.feature_extractor(image, return_tensors="np").pixel_values
            image = ms.Tensor(image)

        image = image.to(dtype=dtype)
        if output_hidden_states:
            image_enc_hidden_states = self.image_encoder(image, output_hidden_states=True)[2][-2]
            image_enc_hidden_states = image_enc_hidden_states.repeat_interleave(num_images_per_prompt, dim=0)
            uncond_image_enc_hidden_states = self.image_encoder(ops.zeros_like(image), output_hidden_states=True)[2][-2]
            uncond_image_enc_hidden_states = uncond_image_enc_hidden_states.repeat_interleave(
                num_images_per_prompt, dim=0
            )
            return image_enc_hidden_states, uncond_image_enc_hidden_states
        else:
            image_embeds = self.image_encoder(image)[0]
            image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
            uncond_image_embeds = ops.zeros_like(image_embeds)

            return image_embeds, uncond_image_embeds

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_ip_adapter_image_embeds
    def prepare_ip_adapter_image_embeds(
        self, ip_adapter_image, ip_adapter_image_embeds, num_images_per_prompt, do_classifier_free_guidance
    ):
        if ip_adapter_image_embeds is None:
            if not isinstance(ip_adapter_image, list):
                ip_adapter_image = [ip_adapter_image]

            if len(ip_adapter_image) != len(self.unet.encoder_hid_proj.image_projection_layers):
                raise ValueError(
                    f"`ip_adapter_image` must have same length as the number of IP Adapters. Got {len(ip_adapter_image)} images and {len(self.unet.encoder_hid_proj.image_projection_layers)} IP Adapters."  # noqa: E501
                )

            image_embeds = []
            for single_ip_adapter_image, image_proj_layer in zip(
                ip_adapter_image, self.unet.encoder_hid_proj.image_projection_layers
            ):
                output_hidden_state = not isinstance(image_proj_layer, ImageProjection)
                single_image_embeds, single_negative_image_embeds = self.encode_image(
                    single_ip_adapter_image, 1, output_hidden_state
                )
                single_image_embeds = ops.stack([single_image_embeds] * num_images_per_prompt, axis=0)
                single_negative_image_embeds = ops.stack([single_negative_image_embeds] * num_images_per_prompt, axis=0)

                if do_classifier_free_guidance:
                    single_image_embeds = ops.cat([single_negative_image_embeds, single_image_embeds])

                image_embeds.append(single_image_embeds)
        else:
            repeat_dims = [1]
            image_embeds = []
            for single_image_embeds in ip_adapter_image_embeds:
                if do_classifier_free_guidance:
                    single_negative_image_embeds, single_image_embeds = single_image_embeds.chunk(2)
                    single_image_embeds = single_image_embeds.tile(
                        (num_images_per_prompt, *(repeat_dims * len(single_image_embeds.shape[1:])))
                    )
                    single_negative_image_embeds = single_negative_image_embeds.tile(
                        (num_images_per_prompt, *(repeat_dims * len(single_negative_image_embeds.shape[1:])))
                    )
                    single_image_embeds = ops.cat([single_negative_image_embeds, single_image_embeds])
                else:
                    single_image_embeds = single_image_embeds.tile(
                        (num_images_per_prompt, *(repeat_dims * len(single_image_embeds.shape[1:])))
                    )
                image_embeds.append(single_image_embeds)

        return image_embeds

    # Copied from diffusers.pipelines.text_to_video_synthesis/pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
    def decode_latents(self, latents):
        latents = 1 / self.vae.config.scaling_factor * latents

        batch_size, channels, num_frames, height, width = latents.shape
        latents = latents.permute(0, 2, 1, 3, 4).reshape(batch_size * num_frames, channels, height, width)

        image = self.vae.decode(latents)[0]
        video = image[None, :].reshape((batch_size, num_frames, -1) + image.shape[2:]).permute(0, 2, 1, 3, 4)
        # we always cast to float32 as this does not cause significant overhead and is compatible with bfloat16
        video = video.float()
        return video

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
    def prepare_extra_step_kwargs(self, generator, eta):
        # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
        # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
        # and should be between [0, 1]

        accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
        extra_step_kwargs = {}
        if accepts_eta:
            extra_step_kwargs["eta"] = eta

        # check if the scheduler accepts generator
        accepts_generator = "generator" in set(inspect.signature(self.scheduler.step).parameters.keys())
        if accepts_generator:
            extra_step_kwargs["generator"] = generator
        return extra_step_kwargs

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.check_inputs
    def check_inputs(
        self,
        prompt,
        height,
        width,
        callback_steps,
        negative_prompt=None,
        prompt_embeds=None,
        negative_prompt_embeds=None,
        ip_adapter_image=None,
        ip_adapter_image_embeds=None,
        callback_on_step_end_tensor_inputs=None,
    ):
        if height % 8 != 0 or width % 8 != 0:
            raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")

        if callback_steps is not None and (not isinstance(callback_steps, int) or callback_steps <= 0):
            raise ValueError(
                f"`callback_steps` has to be a positive integer but is {callback_steps} of type"
                f" {type(callback_steps)}."
            )
        if callback_on_step_end_tensor_inputs is not None and not all(
            k in self._callback_tensor_inputs for k in callback_on_step_end_tensor_inputs
        ):
            raise ValueError(
                f"`callback_on_step_end_tensor_inputs` has to be in {self._callback_tensor_inputs}, but found {[k for k in callback_on_step_end_tensor_inputs if k not in self._callback_tensor_inputs]}"  # noqa: E501
            )

        if prompt is not None and prompt_embeds is not None:
            raise ValueError(
                f"Cannot forward both `prompt`: {prompt} and `prompt_embeds`: {prompt_embeds}. Please make sure to"
                " only forward one of the two."
            )
        elif prompt is None and prompt_embeds is None:
            raise ValueError(
                "Provide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined."
            )
        elif prompt is not None and (not isinstance(prompt, str) and not isinstance(prompt, list)):
            raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")

        if negative_prompt is not None and negative_prompt_embeds is not None:
            raise ValueError(
                f"Cannot forward both `negative_prompt`: {negative_prompt} and `negative_prompt_embeds`:"
                f" {negative_prompt_embeds}. Please make sure to only forward one of the two."
            )

        if prompt_embeds is not None and negative_prompt_embeds is not None:
            if prompt_embeds.shape != negative_prompt_embeds.shape:
                raise ValueError(
                    "`prompt_embeds` and `negative_prompt_embeds` must have the same shape when passed directly, but"
                    f" got: `prompt_embeds` {prompt_embeds.shape} != `negative_prompt_embeds`"
                    f" {negative_prompt_embeds.shape}."
                )

        if ip_adapter_image is not None and ip_adapter_image_embeds is not None:
            raise ValueError(
                "Provide either `ip_adapter_image` or `ip_adapter_image_embeds`. Cannot leave both `ip_adapter_image` and `ip_adapter_image_embeds` defined."
            )

        if ip_adapter_image_embeds is not None:
            if not isinstance(ip_adapter_image_embeds, list):
                raise ValueError(
                    f"`ip_adapter_image_embeds` has to be of type `list` but is {type(ip_adapter_image_embeds)}"
                )
            elif ip_adapter_image_embeds[0].ndim not in [3, 4]:
                raise ValueError(
                    f"`ip_adapter_image_embeds` has to be a list of 3D or 4D tensors but is {ip_adapter_image_embeds[0].ndim}D"
                )

    # Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.prepare_latents
    def prepare_latents(
        self, batch_size, num_channels_latents, num_frames, height, width, dtype, generator, latents=None
    ):
        shape = (
            batch_size,
            num_channels_latents,
            num_frames,
            height // self.vae_scale_factor,
            width // self.vae_scale_factor,
        )
        if isinstance(generator, list) and len(generator) != batch_size:
            raise ValueError(
                f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
                f" size of {batch_size}. Make sure the batch size matches the length of the generators."
            )

        if latents is None:
            latents = randn_tensor(shape, generator=generator, dtype=dtype)

        # scale the initial noise by the standard deviation required by the scheduler
        latents = (latents * self.scheduler.init_noise_sigma).to(dtype)
        return latents

    @property
    def guidance_scale(self):
        return self._guidance_scale

    @property
    def clip_skip(self):
        return self._clip_skip

    # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
    # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
    # corresponds to doing no classifier free guidance.
    @property
    def do_classifier_free_guidance(self):
        return self._guidance_scale > 1

    @property
    def cross_attention_kwargs(self):
        return self._cross_attention_kwargs

    @property
    def num_timesteps(self):
        return self._num_timesteps

    def __call__(
        self,
        prompt: Union[str, List[str]] = None,
        num_frames: Optional[int] = 16,
        height: Optional[int] = None,
        width: Optional[int] = None,
        num_inference_steps: int = 50,
        guidance_scale: float = 7.5,
        negative_prompt: Optional[Union[str, List[str]]] = None,
        num_videos_per_prompt: Optional[int] = 1,
        eta: float = 0.0,
        generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
        latents: Optional[ms.Tensor] = None,
        prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        ip_adapter_image: Optional[PipelineImageInput] = None,
        ip_adapter_image_embeds: Optional[List[ms.Tensor]] = None,
        output_type: Optional[str] = "pil",
        return_dict: bool = False,
        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
        clip_skip: Optional[int] = None,
        callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
        **kwargs,
    ):
        r"""
        The call function to the pipeline for generation.

        Args:
            prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`.
            height (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
                The height in pixels of the generated video.
            width (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
                The width in pixels of the generated video.
            num_frames (`int`, *optional*, defaults to 16):
                The number of video frames that are generated. Defaults to 16 frames which at 8 frames per seconds
                amounts to 2 seconds of video.
            num_inference_steps (`int`, *optional*, defaults to 50):
                The number of denoising steps. More denoising steps usually lead to a higher quality videos at the
                expense of slower inference.
            guidance_scale (`float`, *optional*, defaults to 7.5):
                A higher guidance scale value encourages the model to generate images closely linked to the text
                `prompt` at the expense of lower image quality. Guidance scale is enabled when `guidance_scale > 1`.
            negative_prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts to guide what to not include in image generation. If not defined, you need to
                pass `negative_prompt_embeds` instead. Ignored when not using guidance (`guidance_scale < 1`).
            eta (`float`, *optional*, defaults to 0.0):
                Corresponds to parameter eta (η) from the [DDIM](https://arxiv.org/abs/2010.02502) paper. Only applies
                to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
            generator (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
                A [`np.random.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
                generation deterministic.
            latents (`ms.Tensor`, *optional*):
                Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for video
                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                tensor is generated by sampling using the supplied random `generator`. Latents should be of shape
                `(batch_size, num_channel, num_frames, height, width)`.
            prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
                provided, text embeddings are generated from the `prompt` input argument.
            negative_prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
                not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
            ip_adapter_image: (`PipelineImageInput`, *optional*):
                Optional image input to work with IP Adapters.
            ip_adapter_image_embeds (`List[mindspore.Tensor]`, *optional*):
                Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
                IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should
                contain the negative image embedding if `do_classifier_free_guidance` is set to `True`. If not
                provided, embeddings are computed from the `ip_adapter_image` input argument.
            output_type (`str`, *optional*, defaults to `"pil"`):
                The output format of the generated video. Choose between `ms.Tensor`, `PIL.Image` or
                `np.array`.
            return_dict (`bool`, *optional*, defaults to `False`):
                Whether or not to return a [`~pipelines.text_to_video_synthesis.TextToVideoSDPipelineOutput`] instead
                of a plain tuple.
            cross_attention_kwargs (`dict`, *optional*):
                A kwargs dictionary that if specified is passed along to the [`AttentionProcessor`] as defined in
                [`self.processor`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
            clip_skip (`int`, *optional*):
                Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
                the output of the pre-final layer will be used for computing the prompt embeddings.
            callback_on_step_end (`Callable`, *optional*):
                A function that calls at the end of each denoising steps during the inference. The function is called
                with the following arguments: `callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int,
                callback_kwargs: Dict)`. `callback_kwargs` will include a list of all tensors as specified by
                `callback_on_step_end_tensor_inputs`.
            callback_on_step_end_tensor_inputs (`List`, *optional*):
                The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
                will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
                `._callback_tensor_inputs` attribute of your pipeine class.

        Examples:

        Returns:
            [`~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput`] or `tuple`:
                If `return_dict` is `True`, [`~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput`] is
                returned, otherwise a `tuple` is returned where the first element is a list with the generated frames.
        """

        callback = kwargs.pop("callback", None)
        callback_steps = kwargs.pop("callback_steps", None)

        if callback is not None:
            deprecate(
                "callback",
                "1.0.0",
                "Passing `callback` as an input argument to `__call__` is deprecated, consider using `callback_on_step_end`",
            )
        if callback_steps is not None:
            deprecate(
                "callback_steps",
                "1.0.0",
                "Passing `callback_steps` as an input argument to `__call__` is deprecated, consider using `callback_on_step_end`",
            )

        # 0. Default height and width to unet
        height = height or self.unet.config.sample_size * self.vae_scale_factor
        width = width or self.unet.config.sample_size * self.vae_scale_factor

        num_videos_per_prompt = 1

        # 1. Check inputs. Raise error if not correct
        self.check_inputs(
            prompt,
            height,
            width,
            callback_steps,
            negative_prompt,
            prompt_embeds,
            negative_prompt_embeds,
            ip_adapter_image,
            ip_adapter_image_embeds,
            callback_on_step_end_tensor_inputs,
        )

        self._guidance_scale = guidance_scale
        self._clip_skip = clip_skip
        self._cross_attention_kwargs = cross_attention_kwargs

        # 2. Define call parameters
        if prompt is not None and isinstance(prompt, str):
            batch_size = 1
        elif prompt is not None and isinstance(prompt, list):
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        # 3. Encode input prompt
        text_encoder_lora_scale = (
            self.cross_attention_kwargs.get("scale", None) if self.cross_attention_kwargs is not None else None
        )
        prompt_embeds, negative_prompt_embeds = self.encode_prompt(
            prompt,
            num_videos_per_prompt,
            self.do_classifier_free_guidance,
            negative_prompt,
            prompt_embeds=prompt_embeds,
            negative_prompt_embeds=negative_prompt_embeds,
            lora_scale=text_encoder_lora_scale,
            clip_skip=self.clip_skip,
        )
        # For classifier free guidance, we need to do two forward passes.
        # Here we concatenate the unconditional and text embeddings into a single batch
        # to avoid doing two forward passes
        if self.do_classifier_free_guidance:
            prompt_embeds = ops.cat([negative_prompt_embeds, prompt_embeds])

        if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
            image_embeds = self.prepare_ip_adapter_image_embeds(
                ip_adapter_image,
                ip_adapter_image_embeds,
                batch_size * num_videos_per_prompt,
                self.do_classifier_free_guidance,
            )

        # 4. Prepare timesteps
        self.scheduler.set_timesteps(num_inference_steps)
        timesteps = self.scheduler.timesteps

        # 5. Prepare latent variables
        num_channels_latents = self.unet.config.in_channels
        latents = self.prepare_latents(
            batch_size * num_videos_per_prompt,
            num_channels_latents,
            num_frames,
            height,
            width,
            prompt_embeds.dtype,
            generator,
            latents,
        )

        # 6. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
        extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)

        # 7. Add image embeds for IP-Adapter
        added_cond_kwargs = (
            {"image_embeds": image_embeds}
            if ip_adapter_image is not None or ip_adapter_image_embeds is not None
            else None
        )

        # self.free_init_enabled relies on `FreeInitMixin` that involves FFT implemented by the framework,
        # which is currently incomplete within the MindSpore. Therefore, we have disabled this functionality.
        # if self.free_init_enabled: ...

        self._num_timesteps = len(timesteps)
        num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order

        # 8. Denoising loop
        with self.progress_bar(total=self._num_timesteps) as progress_bar:
            for i, t in enumerate(timesteps):
                # expand the latents if we are doing classifier free guidance
                latent_model_input = ops.cat([latents] * 2) if self.do_classifier_free_guidance else latents
                # TODO: method of scheduler should not change the dtype of input.
                #  Remove the casting after cuiyushi confirm that.
                tmp_dtype = latent_model_input.dtype
                latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
                latent_model_input = latent_model_input.to(tmp_dtype)

                # predict the noise residual
                noise_pred = self.unet(
                    latent_model_input,
                    t,
                    encoder_hidden_states=prompt_embeds,
                    cross_attention_kwargs=cross_attention_kwargs,
                    added_cond_kwargs=ms.mutable(added_cond_kwargs) if added_cond_kwargs else added_cond_kwargs,
                )[0]

                # perform guidance
                if self.do_classifier_free_guidance:
                    noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
                    noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)

                # compute the previous noisy sample x_t -> x_t-1
                # TODO: method of scheduler should not change the dtype of input.
                #  Remove the casting after cuiyushi confirm that.
                tmp_dtype = latents.dtype
                latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]
                latents = latents.to(tmp_dtype)

                if callback_on_step_end is not None:
                    callback_kwargs = {}
                    for k in callback_on_step_end_tensor_inputs:
                        callback_kwargs[k] = locals()[k]
                    callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)

                    latents = callback_outputs.pop("latents", latents)
                    prompt_embeds = callback_outputs.pop("prompt_embeds", prompt_embeds)
                    negative_prompt_embeds = callback_outputs.pop("negative_prompt_embeds", negative_prompt_embeds)

                # call the callback, if provided
                if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
                    progress_bar.update()
                    if callback is not None and i % callback_steps == 0:
                        callback(i, t, latents)

        # 9. Post processing
        if output_type == "latent":
            video = latents
        else:
            video_tensor = self.decode_latents(latents)
            video = self.video_processor.postprocess_video(video=video_tensor, output_type=output_type)

        if not return_dict:
            return (video,)

        return AnimateDiffPipelineOutput(frames=video)

mindone.diffusers.pipelines.AnimateDiffPipeline.__call__(prompt=None, num_frames=16, height=None, width=None, num_inference_steps=50, guidance_scale=7.5, negative_prompt=None, num_videos_per_prompt=1, eta=0.0, generator=None, latents=None, prompt_embeds=None, negative_prompt_embeds=None, ip_adapter_image=None, ip_adapter_image_embeds=None, output_type='pil', return_dict=False, cross_attention_kwargs=None, clip_skip=None, callback_on_step_end=None, callback_on_step_end_tensor_inputs=['latents'], **kwargs)

The call function to the pipeline for generation.

PARAMETER DESCRIPTION
prompt

The prompt or prompts to guide image generation. If not defined, you need to pass prompt_embeds.

TYPE: `str` or `List[str]`, *optional* DEFAULT: None

height

The height in pixels of the generated video.

TYPE: `int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor` DEFAULT: None

width

The width in pixels of the generated video.

TYPE: `int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor` DEFAULT: None

num_frames

The number of video frames that are generated. Defaults to 16 frames which at 8 frames per seconds amounts to 2 seconds of video.

TYPE: `int`, *optional*, defaults to 16 DEFAULT: 16

num_inference_steps

The number of denoising steps. More denoising steps usually lead to a higher quality videos at the expense of slower inference.

TYPE: `int`, *optional*, defaults to 50 DEFAULT: 50

guidance_scale

A higher guidance scale value encourages the model to generate images closely linked to the text prompt at the expense of lower image quality. Guidance scale is enabled when guidance_scale > 1.

TYPE: `float`, *optional*, defaults to 7.5 DEFAULT: 7.5

negative_prompt

The prompt or prompts to guide what to not include in image generation. If not defined, you need to pass negative_prompt_embeds instead. Ignored when not using guidance (guidance_scale < 1).

TYPE: `str` or `List[str]`, *optional* DEFAULT: None

eta

Corresponds to parameter eta (η) from the DDIM paper. Only applies to the [~schedulers.DDIMScheduler], and is ignored in other schedulers.

TYPE: `float`, *optional*, defaults to 0.0 DEFAULT: 0.0

generator

A np.random.Generator to make generation deterministic.

TYPE: `np.random.Generator` or `List[np.random.Generator]`, *optional* DEFAULT: None

latents

Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for video generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor is generated by sampling using the supplied random generator. Latents should be of shape (batch_size, num_channel, num_frames, height, width).

TYPE: `ms.Tensor`, *optional* DEFAULT: None

prompt_embeds

Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not provided, text embeddings are generated from the prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

negative_prompt_embeds

Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not provided, negative_prompt_embeds are generated from the negative_prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

ip_adapter_image

(PipelineImageInput, optional): Optional image input to work with IP Adapters.

TYPE: Optional[PipelineImageInput] DEFAULT: None

ip_adapter_image_embeds

Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of IP-adapters. Each element should be a tensor of shape (batch_size, num_images, emb_dim). It should contain the negative image embedding if do_classifier_free_guidance is set to True. If not provided, embeddings are computed from the ip_adapter_image input argument.

TYPE: `List[mindspore.Tensor]`, *optional* DEFAULT: None

output_type

The output format of the generated video. Choose between ms.Tensor, PIL.Image or np.array.

TYPE: `str`, *optional*, defaults to `"pil"` DEFAULT: 'pil'

return_dict

Whether or not to return a [~pipelines.text_to_video_synthesis.TextToVideoSDPipelineOutput] instead of a plain tuple.

TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False

cross_attention_kwargs

A kwargs dictionary that if specified is passed along to the [AttentionProcessor] as defined in self.processor.

TYPE: `dict`, *optional* DEFAULT: None

clip_skip

Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that the output of the pre-final layer will be used for computing the prompt embeddings.

TYPE: `int`, *optional* DEFAULT: None

callback_on_step_end

A function that calls at the end of each denoising steps during the inference. The function is called with the following arguments: callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict). callback_kwargs will include a list of all tensors as specified by callback_on_step_end_tensor_inputs.

TYPE: `Callable`, *optional* DEFAULT: None

callback_on_step_end_tensor_inputs

The list of tensor inputs for the callback_on_step_end function. The tensors specified in the list will be passed as callback_kwargs argument. You will only be able to include variables listed in the ._callback_tensor_inputs attribute of your pipeine class.

TYPE: `List`, *optional* DEFAULT: ['latents']

RETURNS DESCRIPTION

[~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput] or tuple: If return_dict is True, [~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput] is returned, otherwise a tuple is returned where the first element is a list with the generated frames.
Source code in mindone/diffusers/pipelines/animatediff/pipeline_animatediff.py 
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
def __call__(
    self,
    prompt: Union[str, List[str]] = None,
    num_frames: Optional[int] = 16,
    height: Optional[int] = None,
    width: Optional[int] = None,
    num_inference_steps: int = 50,
    guidance_scale: float = 7.5,
    negative_prompt: Optional[Union[str, List[str]]] = None,
    num_videos_per_prompt: Optional[int] = 1,
    eta: float = 0.0,
    generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
    latents: Optional[ms.Tensor] = None,
    prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    ip_adapter_image: Optional[PipelineImageInput] = None,
    ip_adapter_image_embeds: Optional[List[ms.Tensor]] = None,
    output_type: Optional[str] = "pil",
    return_dict: bool = False,
    cross_attention_kwargs: Optional[Dict[str, Any]] = None,
    clip_skip: Optional[int] = None,
    callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
    callback_on_step_end_tensor_inputs: List[str] = ["latents"],
    **kwargs,
):
    r"""
    The call function to the pipeline for generation.

    Args:
        prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`.
        height (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
            The height in pixels of the generated video.
        width (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
            The width in pixels of the generated video.
        num_frames (`int`, *optional*, defaults to 16):
            The number of video frames that are generated. Defaults to 16 frames which at 8 frames per seconds
            amounts to 2 seconds of video.
        num_inference_steps (`int`, *optional*, defaults to 50):
            The number of denoising steps. More denoising steps usually lead to a higher quality videos at the
            expense of slower inference.
        guidance_scale (`float`, *optional*, defaults to 7.5):
            A higher guidance scale value encourages the model to generate images closely linked to the text
            `prompt` at the expense of lower image quality. Guidance scale is enabled when `guidance_scale > 1`.
        negative_prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts to guide what to not include in image generation. If not defined, you need to
            pass `negative_prompt_embeds` instead. Ignored when not using guidance (`guidance_scale < 1`).
        eta (`float`, *optional*, defaults to 0.0):
            Corresponds to parameter eta (η) from the [DDIM](https://arxiv.org/abs/2010.02502) paper. Only applies
            to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
        generator (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
            A [`np.random.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
            generation deterministic.
        latents (`ms.Tensor`, *optional*):
            Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for video
            generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
            tensor is generated by sampling using the supplied random `generator`. Latents should be of shape
            `(batch_size, num_channel, num_frames, height, width)`.
        prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
            provided, text embeddings are generated from the `prompt` input argument.
        negative_prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
            not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
        ip_adapter_image: (`PipelineImageInput`, *optional*):
            Optional image input to work with IP Adapters.
        ip_adapter_image_embeds (`List[mindspore.Tensor]`, *optional*):
            Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
            IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should
            contain the negative image embedding if `do_classifier_free_guidance` is set to `True`. If not
            provided, embeddings are computed from the `ip_adapter_image` input argument.
        output_type (`str`, *optional*, defaults to `"pil"`):
            The output format of the generated video. Choose between `ms.Tensor`, `PIL.Image` or
            `np.array`.
        return_dict (`bool`, *optional*, defaults to `False`):
            Whether or not to return a [`~pipelines.text_to_video_synthesis.TextToVideoSDPipelineOutput`] instead
            of a plain tuple.
        cross_attention_kwargs (`dict`, *optional*):
            A kwargs dictionary that if specified is passed along to the [`AttentionProcessor`] as defined in
            [`self.processor`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
        clip_skip (`int`, *optional*):
            Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
            the output of the pre-final layer will be used for computing the prompt embeddings.
        callback_on_step_end (`Callable`, *optional*):
            A function that calls at the end of each denoising steps during the inference. The function is called
            with the following arguments: `callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int,
            callback_kwargs: Dict)`. `callback_kwargs` will include a list of all tensors as specified by
            `callback_on_step_end_tensor_inputs`.
        callback_on_step_end_tensor_inputs (`List`, *optional*):
            The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
            will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
            `._callback_tensor_inputs` attribute of your pipeine class.

    Examples:

    Returns:
        [`~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput`] or `tuple`:
            If `return_dict` is `True`, [`~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput`] is
            returned, otherwise a `tuple` is returned where the first element is a list with the generated frames.
    """

    callback = kwargs.pop("callback", None)
    callback_steps = kwargs.pop("callback_steps", None)

    if callback is not None:
        deprecate(
            "callback",
            "1.0.0",
            "Passing `callback` as an input argument to `__call__` is deprecated, consider using `callback_on_step_end`",
        )
    if callback_steps is not None:
        deprecate(
            "callback_steps",
            "1.0.0",
            "Passing `callback_steps` as an input argument to `__call__` is deprecated, consider using `callback_on_step_end`",
        )

    # 0. Default height and width to unet
    height = height or self.unet.config.sample_size * self.vae_scale_factor
    width = width or self.unet.config.sample_size * self.vae_scale_factor

    num_videos_per_prompt = 1

    # 1. Check inputs. Raise error if not correct
    self.check_inputs(
        prompt,
        height,
        width,
        callback_steps,
        negative_prompt,
        prompt_embeds,
        negative_prompt_embeds,
        ip_adapter_image,
        ip_adapter_image_embeds,
        callback_on_step_end_tensor_inputs,
    )

    self._guidance_scale = guidance_scale
    self._clip_skip = clip_skip
    self._cross_attention_kwargs = cross_attention_kwargs

    # 2. Define call parameters
    if prompt is not None and isinstance(prompt, str):
        batch_size = 1
    elif prompt is not None and isinstance(prompt, list):
        batch_size = len(prompt)
    else:
        batch_size = prompt_embeds.shape[0]

    # 3. Encode input prompt
    text_encoder_lora_scale = (
        self.cross_attention_kwargs.get("scale", None) if self.cross_attention_kwargs is not None else None
    )
    prompt_embeds, negative_prompt_embeds = self.encode_prompt(
        prompt,
        num_videos_per_prompt,
        self.do_classifier_free_guidance,
        negative_prompt,
        prompt_embeds=prompt_embeds,
        negative_prompt_embeds=negative_prompt_embeds,
        lora_scale=text_encoder_lora_scale,
        clip_skip=self.clip_skip,
    )
    # For classifier free guidance, we need to do two forward passes.
    # Here we concatenate the unconditional and text embeddings into a single batch
    # to avoid doing two forward passes
    if self.do_classifier_free_guidance:
        prompt_embeds = ops.cat([negative_prompt_embeds, prompt_embeds])

    if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
        image_embeds = self.prepare_ip_adapter_image_embeds(
            ip_adapter_image,
            ip_adapter_image_embeds,
            batch_size * num_videos_per_prompt,
            self.do_classifier_free_guidance,
        )

    # 4. Prepare timesteps
    self.scheduler.set_timesteps(num_inference_steps)
    timesteps = self.scheduler.timesteps

    # 5. Prepare latent variables
    num_channels_latents = self.unet.config.in_channels
    latents = self.prepare_latents(
        batch_size * num_videos_per_prompt,
        num_channels_latents,
        num_frames,
        height,
        width,
        prompt_embeds.dtype,
        generator,
        latents,
    )

    # 6. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
    extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)

    # 7. Add image embeds for IP-Adapter
    added_cond_kwargs = (
        {"image_embeds": image_embeds}
        if ip_adapter_image is not None or ip_adapter_image_embeds is not None
        else None
    )

    # self.free_init_enabled relies on `FreeInitMixin` that involves FFT implemented by the framework,
    # which is currently incomplete within the MindSpore. Therefore, we have disabled this functionality.
    # if self.free_init_enabled: ...

    self._num_timesteps = len(timesteps)
    num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order

    # 8. Denoising loop
    with self.progress_bar(total=self._num_timesteps) as progress_bar:
        for i, t in enumerate(timesteps):
            # expand the latents if we are doing classifier free guidance
            latent_model_input = ops.cat([latents] * 2) if self.do_classifier_free_guidance else latents
            # TODO: method of scheduler should not change the dtype of input.
            #  Remove the casting after cuiyushi confirm that.
            tmp_dtype = latent_model_input.dtype
            latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
            latent_model_input = latent_model_input.to(tmp_dtype)

            # predict the noise residual
            noise_pred = self.unet(
                latent_model_input,
                t,
                encoder_hidden_states=prompt_embeds,
                cross_attention_kwargs=cross_attention_kwargs,
                added_cond_kwargs=ms.mutable(added_cond_kwargs) if added_cond_kwargs else added_cond_kwargs,
            )[0]

            # perform guidance
            if self.do_classifier_free_guidance:
                noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
                noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)

            # compute the previous noisy sample x_t -> x_t-1
            # TODO: method of scheduler should not change the dtype of input.
            #  Remove the casting after cuiyushi confirm that.
            tmp_dtype = latents.dtype
            latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]
            latents = latents.to(tmp_dtype)

            if callback_on_step_end is not None:
                callback_kwargs = {}
                for k in callback_on_step_end_tensor_inputs:
                    callback_kwargs[k] = locals()[k]
                callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)

                latents = callback_outputs.pop("latents", latents)
                prompt_embeds = callback_outputs.pop("prompt_embeds", prompt_embeds)
                negative_prompt_embeds = callback_outputs.pop("negative_prompt_embeds", negative_prompt_embeds)

            # call the callback, if provided
            if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
                progress_bar.update()
                if callback is not None and i % callback_steps == 0:
                    callback(i, t, latents)

    # 9. Post processing
    if output_type == "latent":
        video = latents
    else:
        video_tensor = self.decode_latents(latents)
        video = self.video_processor.postprocess_video(video=video_tensor, output_type=output_type)

    if not return_dict:
        return (video,)

    return AnimateDiffPipelineOutput(frames=video)

mindone.diffusers.pipelines.AnimateDiffPipeline.encode_prompt(prompt, num_images_per_prompt, do_classifier_free_guidance, negative_prompt=None, prompt_embeds=None, negative_prompt_embeds=None, lora_scale=None, clip_skip=None)

Encodes the prompt into text encoder hidden states.

PARAMETER DESCRIPTION
prompt

prompt to be encoded

TYPE: `str` or `List[str]`, *optional*

num_images_per_prompt

number of images that should be generated per prompt

TYPE: `int`

do_classifier_free_guidance

whether to use classifier free guidance or not

TYPE: `bool`

negative_prompt

The prompt or prompts not to guide the image generation. If not defined, one has to pass negative_prompt_embeds instead. Ignored when not using guidance (i.e., ignored if guidance_scale is less than 1).

TYPE: `str` or `List[str]`, *optional* DEFAULT: None

prompt_embeds

Pre-generated text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, text embeddings will be generated from prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

negative_prompt_embeds

Pre-generated negative text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, negative_prompt_embeds will be generated from negative_prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

lora_scale

A LoRA scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.

TYPE: `float`, *optional* DEFAULT: None

clip_skip

Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that the output of the pre-final layer will be used for computing the prompt embeddings.

TYPE: `int`, *optional* DEFAULT: None

Source code in mindone/diffusers/pipelines/animatediff/pipeline_animatediff.py 
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
def encode_prompt(
    self,
    prompt,
    num_images_per_prompt,
    do_classifier_free_guidance,
    negative_prompt=None,
    prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    lora_scale: Optional[float] = None,
    clip_skip: Optional[int] = None,
):
    r"""
    Encodes the prompt into text encoder hidden states.

    Args:
        prompt (`str` or `List[str]`, *optional*):
            prompt to be encoded
        num_images_per_prompt (`int`):
            number of images that should be generated per prompt
        do_classifier_free_guidance (`bool`):
            whether to use classifier free guidance or not
        negative_prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts not to guide the image generation. If not defined, one has to pass
            `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
            less than `1`).
        prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
            provided, text embeddings will be generated from `prompt` input argument.
        negative_prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
            weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
            argument.
        lora_scale (`float`, *optional*):
            A LoRA scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
        clip_skip (`int`, *optional*):
            Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
            the output of the pre-final layer will be used for computing the prompt embeddings.
    """
    # set lora scale so that monkey patched LoRA
    # function of text encoder can correctly access it
    if lora_scale is not None and isinstance(self, LoraLoaderMixin):
        self._lora_scale = lora_scale

        # dynamically adjust the LoRA scale
        scale_lora_layers(self.text_encoder, lora_scale)

    if prompt is not None and isinstance(prompt, str):
        batch_size = 1
    elif prompt is not None and isinstance(prompt, list):
        batch_size = len(prompt)
    else:
        batch_size = prompt_embeds.shape[0]

    if prompt_embeds is None:
        # textual inversion: process multi-vector tokens if necessary
        if isinstance(self, TextualInversionLoaderMixin):
            prompt = self.maybe_convert_prompt(prompt, self.tokenizer)

        text_inputs = self.tokenizer(
            prompt,
            padding="max_length",
            max_length=self.tokenizer.model_max_length,
            truncation=True,
            return_tensors="np",
        )
        text_input_ids = text_inputs.input_ids
        untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="np").input_ids

        if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not np.array_equal(
            text_input_ids, untruncated_ids
        ):
            removed_text = self.tokenizer.batch_decode(untruncated_ids[:, self.tokenizer.model_max_length - 1 : -1])
            logger.warning(
                "The following part of your input was truncated because CLIP can only handle sequences up to"
                f" {self.tokenizer.model_max_length} tokens: {removed_text}"
            )

        if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
            attention_mask = ms.Tensor(text_inputs.attention_mask)
        else:
            attention_mask = None

        if clip_skip is None:
            prompt_embeds = self.text_encoder(ms.Tensor(text_input_ids), attention_mask=attention_mask)
            prompt_embeds = prompt_embeds[0]
        else:
            prompt_embeds = self.text_encoder(
                ms.Tensor(text_input_ids), attention_mask=attention_mask, output_hidden_states=True
            )
            # Access the `hidden_states` first, that contains a tuple of
            # all the hidden states from the encoder layers. Then index into
            # the tuple to access the hidden states from the desired layer.
            prompt_embeds = prompt_embeds[-1][-(clip_skip + 1)]
            # We also need to apply the final LayerNorm here to not mess with the
            # representations. The `last_hidden_states` that we typically use for
            # obtaining the final prompt representations passes through the LayerNorm
            # layer.
            prompt_embeds = self.text_encoder.text_model.final_layer_norm(prompt_embeds)

    if self.text_encoder is not None:
        prompt_embeds_dtype = self.text_encoder.dtype
    elif self.unet is not None:
        prompt_embeds_dtype = self.unet.dtype
    else:
        prompt_embeds_dtype = prompt_embeds.dtype

    prompt_embeds = prompt_embeds.to(dtype=prompt_embeds_dtype)

    bs_embed, seq_len, _ = prompt_embeds.shape
    # duplicate text embeddings for each generation per prompt, using mps friendly method
    prompt_embeds = prompt_embeds.tile((1, num_images_per_prompt, 1))
    prompt_embeds = prompt_embeds.view(bs_embed * num_images_per_prompt, seq_len, -1)

    # get unconditional embeddings for classifier free guidance
    if do_classifier_free_guidance and negative_prompt_embeds is None:
        uncond_tokens: List[str]
        if negative_prompt is None:
            uncond_tokens = [""] * batch_size
        elif prompt is not None and type(prompt) is not type(negative_prompt):
            raise TypeError(
                f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
                f" {type(prompt)}."
            )
        elif isinstance(negative_prompt, str):
            uncond_tokens = [negative_prompt]
        elif batch_size != len(negative_prompt):
            raise ValueError(
                f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
                f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
                " the batch size of `prompt`."
            )
        else:
            uncond_tokens = negative_prompt

        # textual inversion: process multi-vector tokens if necessary
        if isinstance(self, TextualInversionLoaderMixin):
            uncond_tokens = self.maybe_convert_prompt(uncond_tokens, self.tokenizer)

        max_length = prompt_embeds.shape[1]
        uncond_input = self.tokenizer(
            uncond_tokens,
            padding="max_length",
            max_length=max_length,
            truncation=True,
            return_tensors="np",
        )

        if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
            attention_mask = ms.Tensor(uncond_input.attention_mask)
        else:
            attention_mask = None

        negative_prompt_embeds = self.text_encoder(
            ms.Tensor(uncond_input.input_ids),
            attention_mask=attention_mask,
        )
        negative_prompt_embeds = negative_prompt_embeds[0]

    if do_classifier_free_guidance:
        # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
        seq_len = negative_prompt_embeds.shape[1]

        negative_prompt_embeds = negative_prompt_embeds.to(dtype=prompt_embeds_dtype)

        negative_prompt_embeds = negative_prompt_embeds.tile((1, num_images_per_prompt, 1))
        negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)

    if self.text_encoder is not None:
        if isinstance(self, LoraLoaderMixin):
            # Retrieve the original scale by scaling back the LoRA layers
            unscale_lora_layers(self.text_encoder, lora_scale)

    return prompt_embeds, negative_prompt_embeds

mindone.diffusers.pipelines.AnimateDiffControlNetPipeline

Bases: DiffusionPipeline, TextualInversionLoaderMixin, IPAdapterMixin, StableDiffusionLoraLoaderMixin

Pipeline for text-to-video generation with ControlNet guidance.

This model inherits from [DiffusionPipeline]. Check the superclass documentation for the generic methods implemented for all pipelines (downloading, saving, running on a particular device, etc.).

The pipeline also inherits the following loading methods
  • [~loaders.TextualInversionLoaderMixin.load_textual_inversion] for loading textual inversion embeddings
  • [~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights] for loading LoRA weights
  • [~loaders.StableDiffusionLoraLoaderMixin.save_lora_weights] for saving LoRA weights
  • [~loaders.IPAdapterMixin.load_ip_adapter] for loading IP Adapters
PARAMETER DESCRIPTION
vae

Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.

TYPE: [`AutoencoderKL`]

text_encoder

Frozen text-encoder (clip-vit-large-patch14).

TYPE: [`CLIPTextModel`]

tokenizer

A [~transformers.CLIPTokenizer] to tokenize text.

TYPE: `CLIPTokenizer`

unet

A [UNet2DConditionModel] used to create a UNetMotionModel to denoise the encoded video latents.

TYPE: [`UNet2DConditionModel`]

motion_adapter

A [MotionAdapter] to be used in combination with unet to denoise the encoded video latents.

TYPE: [`MotionAdapter`]

scheduler

A scheduler to be used in combination with unet to denoise the encoded image latents. Can be one of [DDIMScheduler], [LMSDiscreteScheduler], or [PNDMScheduler].

TYPE: [`SchedulerMixin`]

Source code in mindone/diffusers/pipelines/animatediff/pipeline_animatediff_controlnet.py 
 109
 110
 111
 112
 113
 114
 115
 116
 117
 118
 119
 120
 121
 122
 123
 124
 125
 126
 127
 128
 129
 130
 131
 132
 133
 134
 135
 136
 137
 138
 139
 140
 141
 142
 143
 144
 145
 146
 147
 148
 149
 150
 151
 152
 153
 154
 155
 156
 157
 158
 159
 160
 161
 162
 163
 164
 165
 166
 167
 168
 169
 170
 171
 172
 173
 174
 175
 176
 177
 178
 179
 180
 181
 182
 183
 184
 185
 186
 187
 188
 189
 190
 191
 192
 193
 194
 195
 196
 197
 198
 199
 200
 201
 202
 203
 204
 205
 206
 207
 208
 209
 210
 211
 212
 213
 214
 215
 216
 217
 218
 219
 220
 221
 222
 223
 224
 225
 226
 227
 228
 229
 230
 231
 232
 233
 234
 235
 236
 237
 238
 239
 240
 241
 242
 243
 244
 245
 246
 247
 248
 249
 250
 251
 252
 253
 254
 255
 256
 257
 258
 259
 260
 261
 262
 263
 264
 265
 266
 267
 268
 269
 270
 271
 272
 273
 274
 275
 276
 277
 278
 279
 280
 281
 282
 283
 284
 285
 286
 287
 288
 289
 290
 291
 292
 293
 294
 295
 296
 297
 298
 299
 300
 301
 302
 303
 304
 305
 306
 307
 308
 309
 310
 311
 312
 313
 314
 315
 316
 317
 318
 319
 320
 321
 322
 323
 324
 325
 326
 327
 328
 329
 330
 331
 332
 333
 334
 335
 336
 337
 338
 339
 340
 341
 342
 343
 344
 345
 346
 347
 348
 349
 350
 351
 352
 353
 354
 355
 356
 357
 358
 359
 360
 361
 362
 363
 364
 365
 366
 367
 368
 369
 370
 371
 372
 373
 374
 375
 376
 377
 378
 379
 380
 381
 382
 383
 384
 385
 386
 387
 388
 389
 390
 391
 392
 393
 394
 395
 396
 397
 398
 399
 400
 401
 402
 403
 404
 405
 406
 407
 408
 409
 410
 411
 412
 413
 414
 415
 416
 417
 418
 419
 420
 421
 422
 423
 424
 425
 426
 427
 428
 429
 430
 431
 432
 433
 434
 435
 436
 437
 438
 439
 440
 441
 442
 443
 444
 445
 446
 447
 448
 449
 450
 451
 452
 453
 454
 455
 456
 457
 458
 459
 460
 461
 462
 463
 464
 465
 466
 467
 468
 469
 470
 471
 472
 473
 474
 475
 476
 477
 478
 479
 480
 481
 482
 483
 484
 485
 486
 487
 488
 489
 490
 491
 492
 493
 494
 495
 496
 497
 498
 499
 500
 501
 502
 503
 504
 505
 506
 507
 508
 509
 510
 511
 512
 513
 514
 515
 516
 517
 518
 519
 520
 521
 522
 523
 524
 525
 526
 527
 528
 529
 530
 531
 532
 533
 534
 535
 536
 537
 538
 539
 540
 541
 542
 543
 544
 545
 546
 547
 548
 549
 550
 551
 552
 553
 554
 555
 556
 557
 558
 559
 560
 561
 562
 563
 564
 565
 566
 567
 568
 569
 570
 571
 572
 573
 574
 575
 576
 577
 578
 579
 580
 581
 582
 583
 584
 585
 586
 587
 588
 589
 590
 591
 592
 593
 594
 595
 596
 597
 598
 599
 600
 601
 602
 603
 604
 605
 606
 607
 608
 609
 610
 611
 612
 613
 614
 615
 616
 617
 618
 619
 620
 621
 622
 623
 624
 625
 626
 627
 628
 629
 630
 631
 632
 633
 634
 635
 636
 637
 638
 639
 640
 641
 642
 643
 644
 645
 646
 647
 648
 649
 650
 651
 652
 653
 654
 655
 656
 657
 658
 659
 660
 661
 662
 663
 664
 665
 666
 667
 668
 669
 670
 671
 672
 673
 674
 675
 676
 677
 678
 679
 680
 681
 682
 683
 684
 685
 686
 687
 688
 689
 690
 691
 692
 693
 694
 695
 696
 697
 698
 699
 700
 701
 702
 703
 704
 705
 706
 707
 708
 709
 710
 711
 712
 713
 714
 715
 716
 717
 718
 719
 720
 721
 722
 723
 724
 725
 726
 727
 728
 729
 730
 731
 732
 733
 734
 735
 736
 737
 738
 739
 740
 741
 742
 743
 744
 745
 746
 747
 748
 749
 750
 751
 752
 753
 754
 755
 756
 757
 758
 759
 760
 761
 762
 763
 764
 765
 766
 767
 768
 769
 770
 771
 772
 773
 774
 775
 776
 777
 778
 779
 780
 781
 782
 783
 784
 785
 786
 787
 788
 789
 790
 791
 792
 793
 794
 795
 796
 797
 798
 799
 800
 801
 802
 803
 804
 805
 806
 807
 808
 809
 810
 811
 812
 813
 814
 815
 816
 817
 818
 819
 820
 821
 822
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
class AnimateDiffControlNetPipeline(
    DiffusionPipeline,
    TextualInversionLoaderMixin,
    IPAdapterMixin,
    StableDiffusionLoraLoaderMixin,
):
    r"""
    Pipeline for text-to-video generation with ControlNet guidance.

    This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods
    implemented for all pipelines (downloading, saving, running on a particular device, etc.).

    The pipeline also inherits the following loading methods:
        - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
        - [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] for loading LoRA weights
        - [`~loaders.StableDiffusionLoraLoaderMixin.save_lora_weights`] for saving LoRA weights
        - [`~loaders.IPAdapterMixin.load_ip_adapter`] for loading IP Adapters

    Args:
        vae ([`AutoencoderKL`]):
            Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
        text_encoder ([`CLIPTextModel`]):
            Frozen text-encoder ([clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14)).
        tokenizer (`CLIPTokenizer`):
            A [`~transformers.CLIPTokenizer`] to tokenize text.
        unet ([`UNet2DConditionModel`]):
            A [`UNet2DConditionModel`] used to create a UNetMotionModel to denoise the encoded video latents.
        motion_adapter ([`MotionAdapter`]):
            A [`MotionAdapter`] to be used in combination with `unet` to denoise the encoded video latents.
        scheduler ([`SchedulerMixin`]):
            A scheduler to be used in combination with `unet` to denoise the encoded image latents. Can be one of
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
    """

    model_cpu_offload_seq = "text_encoder->unet->vae"
    _optional_components = ["feature_extractor", "image_encoder"]
    _callback_tensor_inputs = ["latents", "prompt_embeds", "negative_prompt_embeds"]

    def __init__(
        self,
        vae: AutoencoderKL,
        text_encoder: CLIPTextModel,
        tokenizer: CLIPTokenizer,
        unet: Union[UNet2DConditionModel, UNetMotionModel],
        motion_adapter: MotionAdapter,
        controlnet: Union[ControlNetModel, List[ControlNetModel], Tuple[ControlNetModel], MultiControlNetModel],
        scheduler: KarrasDiffusionSchedulers,
        feature_extractor: Optional[CLIPImageProcessor] = None,
        image_encoder: Optional[CLIPVisionModelWithProjection] = None,
    ):
        super().__init__()
        if isinstance(unet, UNet2DConditionModel):
            unet = UNetMotionModel.from_unet2d(unet, motion_adapter)

        if isinstance(controlnet, (list, tuple)):
            controlnet = MultiControlNetModel(controlnet)

        self.register_modules(
            vae=vae,
            text_encoder=text_encoder,
            tokenizer=tokenizer,
            unet=unet,
            motion_adapter=motion_adapter,
            controlnet=controlnet,
            scheduler=scheduler,
            feature_extractor=feature_extractor,
            image_encoder=image_encoder,
        )
        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
        self.video_processor = VideoProcessor(vae_scale_factor=self.vae_scale_factor)
        self.control_video_processor = VideoProcessor(
            vae_scale_factor=self.vae_scale_factor, do_convert_rgb=True, do_normalize=False
        )

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_prompt with num_images_per_prompt -> num_videos_per_prompt  # noqa: E501
    def encode_prompt(
        self,
        prompt,
        num_images_per_prompt,
        do_classifier_free_guidance,
        negative_prompt=None,
        prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        lora_scale: Optional[float] = None,
        clip_skip: Optional[int] = None,
    ):
        r"""
        Encodes the prompt into text encoder hidden states.

        Args:
            prompt (`str` or `List[str]`, *optional*):
                prompt to be encoded
            num_images_per_prompt (`int`):
                number of images that should be generated per prompt
            do_classifier_free_guidance (`bool`):
                whether to use classifier free guidance or not
            negative_prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts not to guide the image generation. If not defined, one has to pass
                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
                less than `1`).
            prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                provided, text embeddings will be generated from `prompt` input argument.
            negative_prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                argument.
            lora_scale (`float`, *optional*):
                A LoRA scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
            clip_skip (`int`, *optional*):
                Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
                the output of the pre-final layer will be used for computing the prompt embeddings.
        """
        # set lora scale so that monkey patched LoRA
        # function of text encoder can correctly access it
        if lora_scale is not None and isinstance(self, StableDiffusionLoraLoaderMixin):
            self._lora_scale = lora_scale

            # dynamically adjust the LoRA scale
            scale_lora_layers(self.text_encoder, lora_scale)

        if prompt is not None and isinstance(prompt, str):
            batch_size = 1
        elif prompt is not None and isinstance(prompt, list):
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        if prompt_embeds is None:
            # textual inversion: process multi-vector tokens if necessary
            if isinstance(self, TextualInversionLoaderMixin):
                prompt = self.maybe_convert_prompt(prompt, self.tokenizer)

            text_inputs = self.tokenizer(
                prompt,
                padding="max_length",
                max_length=self.tokenizer.model_max_length,
                truncation=True,
                return_tensors="np",
            )
            text_input_ids = text_inputs.input_ids
            untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="np").input_ids

            if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not np.array_equal(
                text_input_ids, untruncated_ids
            ):
                removed_text = self.tokenizer.batch_decode(untruncated_ids[:, self.tokenizer.model_max_length - 1 : -1])
                logger.warning(
                    "The following part of your input was truncated because CLIP can only handle sequences up to"
                    f" {self.tokenizer.model_max_length} tokens: {removed_text}"
                )

            if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
                attention_mask = ms.Tensor(text_inputs.attention_mask)
            else:
                attention_mask = None

            text_input_ids = ms.Tensor(text_input_ids)
            if clip_skip is None:
                prompt_embeds = self.text_encoder(text_input_ids, attention_mask=attention_mask)
                prompt_embeds = prompt_embeds[0]
            else:
                prompt_embeds = self.text_encoder(
                    text_input_ids, attention_mask=attention_mask, output_hidden_states=True
                )
                # Access the `hidden_states` first, that contains a tuple of
                # all the hidden states from the encoder layers. Then index into
                # the tuple to access the hidden states from the desired layer.
                prompt_embeds = prompt_embeds[-1][-(clip_skip + 1)]
                # We also need to apply the final LayerNorm here to not mess with the
                # representations. The `last_hidden_states` that we typically use for
                # obtaining the final prompt representations passes through the LayerNorm
                # layer.
                prompt_embeds = self.text_encoder.text_model.final_layer_norm(prompt_embeds)

        if self.text_encoder is not None:
            prompt_embeds_dtype = self.text_encoder.dtype
        elif self.unet is not None:
            prompt_embeds_dtype = self.unet.dtype
        else:
            prompt_embeds_dtype = prompt_embeds.dtype

        prompt_embeds = prompt_embeds.to(dtype=prompt_embeds_dtype)

        bs_embed, seq_len, _ = prompt_embeds.shape
        # duplicate text embeddings for each generation per prompt, using mps friendly method
        prompt_embeds = prompt_embeds.tile((1, num_images_per_prompt, 1))
        prompt_embeds = prompt_embeds.view(bs_embed * num_images_per_prompt, seq_len, -1)

        # get unconditional embeddings for classifier free guidance
        if do_classifier_free_guidance and negative_prompt_embeds is None:
            uncond_tokens: List[str]
            if negative_prompt is None:
                uncond_tokens = [""] * batch_size
            elif prompt is not None and type(prompt) is not type(negative_prompt):
                raise TypeError(
                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
                    f" {type(prompt)}."
                )
            elif isinstance(negative_prompt, str):
                uncond_tokens = [negative_prompt]
            elif batch_size != len(negative_prompt):
                raise ValueError(
                    f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
                    f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
                    " the batch size of `prompt`."
                )
            else:
                uncond_tokens = negative_prompt

            # textual inversion: process multi-vector tokens if necessary
            if isinstance(self, TextualInversionLoaderMixin):
                uncond_tokens = self.maybe_convert_prompt(uncond_tokens, self.tokenizer)

            max_length = prompt_embeds.shape[1]
            uncond_input = self.tokenizer(
                uncond_tokens,
                padding="max_length",
                max_length=max_length,
                truncation=True,
                return_tensors="np",
            )

            if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
                attention_mask = ms.Tensor(uncond_input.attention_mask)
            else:
                attention_mask = None

            negative_prompt_embeds = self.text_encoder(
                ms.Tensor(uncond_input.input_ids),
                attention_mask=attention_mask,
            )
            negative_prompt_embeds = negative_prompt_embeds[0]

        if do_classifier_free_guidance:
            # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
            seq_len = negative_prompt_embeds.shape[1]

            negative_prompt_embeds = negative_prompt_embeds.to(dtype=prompt_embeds_dtype)

            negative_prompt_embeds = negative_prompt_embeds.tile((1, num_images_per_prompt, 1))
            negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)

        if self.text_encoder is not None:
            if isinstance(self, StableDiffusionLoraLoaderMixin):
                # Retrieve the original scale by scaling back the LoRA layers
                unscale_lora_layers(self.text_encoder, lora_scale)

        return prompt_embeds, negative_prompt_embeds

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_image
    def encode_image(self, image, num_images_per_prompt, output_hidden_states=None):
        dtype = next(self.image_encoder.get_parameters()).dtype

        if not isinstance(image, ms.Tensor):
            image = self.feature_extractor(image, return_tensors="np").pixel_values
            image = ms.Tensor(image)

        image = image.to(dtype=dtype)
        if output_hidden_states:
            image_enc_hidden_states = self.image_encoder(image, output_hidden_states=True)[2][-2]
            image_enc_hidden_states = image_enc_hidden_states.repeat_interleave(num_images_per_prompt, dim=0)
            uncond_image_enc_hidden_states = self.image_encoder(ops.zeros_like(image), output_hidden_states=True)[2][-2]
            uncond_image_enc_hidden_states = uncond_image_enc_hidden_states.repeat_interleave(
                num_images_per_prompt, dim=0
            )
            return image_enc_hidden_states, uncond_image_enc_hidden_states
        else:
            image_embeds = self.image_encoder(image)[0]
            image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
            uncond_image_embeds = ops.zeros_like(image_embeds)

            return image_embeds, uncond_image_embeds

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_ip_adapter_image_embeds  # noqa: E501
    def prepare_ip_adapter_image_embeds(
        self, ip_adapter_image, ip_adapter_image_embeds, num_images_per_prompt, do_classifier_free_guidance
    ):
        image_embeds = []
        if do_classifier_free_guidance:
            negative_image_embeds = []
        if ip_adapter_image_embeds is None:
            if not isinstance(ip_adapter_image, list):
                ip_adapter_image = [ip_adapter_image]

            if len(ip_adapter_image) != len(self.unet.encoder_hid_proj.image_projection_layers):
                raise ValueError(
                    f"`ip_adapter_image` must have same length as the number of IP Adapters. Got {len(ip_adapter_image)} images and {len(self.unet.encoder_hid_proj.image_projection_layers)} IP Adapters."  # noqa: E501
                )

            for single_ip_adapter_image, image_proj_layer in zip(
                ip_adapter_image, self.unet.encoder_hid_proj.image_projection_layers
            ):
                output_hidden_state = not isinstance(image_proj_layer, ImageProjection)
                single_image_embeds, single_negative_image_embeds = self.encode_image(
                    single_ip_adapter_image, 1, output_hidden_state
                )

                image_embeds.append(single_image_embeds[None, :])
                if do_classifier_free_guidance:
                    negative_image_embeds.append(single_negative_image_embeds[None, :])
        else:
            for single_image_embeds in ip_adapter_image_embeds:
                if do_classifier_free_guidance:
                    single_negative_image_embeds, single_image_embeds = single_image_embeds.chunk(2)
                    negative_image_embeds.append(single_negative_image_embeds)
                image_embeds.append(single_image_embeds)

        ip_adapter_image_embeds = []
        for i, single_image_embeds in enumerate(image_embeds):
            single_image_embeds = ops.cat([single_image_embeds] * num_images_per_prompt, axis=0)
            if do_classifier_free_guidance:
                single_negative_image_embeds = ops.cat([negative_image_embeds[i]] * num_images_per_prompt, axis=0)
                single_image_embeds = ops.cat([single_negative_image_embeds, single_image_embeds], axis=0)

            ip_adapter_image_embeds.append(single_image_embeds)

        return ip_adapter_image_embeds

    # Copied from diffusers.pipelines.animatediff.pipeline_animatediff.AnimateDiffPipeline.decode_latents
    def decode_latents(self, latents, decode_chunk_size: int = 16):
        latents = 1 / self.vae.config.scaling_factor * latents

        batch_size, channels, num_frames, height, width = latents.shape
        latents = latents.permute(0, 2, 1, 3, 4).reshape(batch_size * num_frames, channels, height, width)

        video = []
        for i in range(0, latents.shape[0], decode_chunk_size):
            batch_latents = latents[i : i + decode_chunk_size]
            batch_latents = self.vae.decode(batch_latents)[0]
            video.append(batch_latents)

        video = ops.cat(video)
        video = video[None, :].reshape((batch_size, num_frames, -1) + video.shape[2:]).permute(0, 2, 1, 3, 4)
        # we always cast to float32 as this does not cause significant overhead and is compatible with bfloat16
        video = video.float()
        return video

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
    def prepare_extra_step_kwargs(self, generator, eta):
        # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
        # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
        # and should be between [0, 1]

        accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
        extra_step_kwargs = {}
        if accepts_eta:
            extra_step_kwargs["eta"] = eta

        # check if the scheduler accepts generator
        accepts_generator = "generator" in set(inspect.signature(self.scheduler.step).parameters.keys())
        if accepts_generator:
            extra_step_kwargs["generator"] = generator
        return extra_step_kwargs

    def check_inputs(
        self,
        prompt,
        height,
        width,
        num_frames,
        negative_prompt=None,
        prompt_embeds=None,
        negative_prompt_embeds=None,
        callback_on_step_end_tensor_inputs=None,
        video=None,
        controlnet_conditioning_scale=1.0,
        control_guidance_start=0.0,
        control_guidance_end=1.0,
    ):
        if height % 8 != 0 or width % 8 != 0:
            raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")

        if callback_on_step_end_tensor_inputs is not None and not all(
            k in self._callback_tensor_inputs for k in callback_on_step_end_tensor_inputs
        ):
            raise ValueError(
                f"`callback_on_step_end_tensor_inputs` has to be in {self._callback_tensor_inputs}, but found"
                f"{[k for k in callback_on_step_end_tensor_inputs if k not in self._callback_tensor_inputs]}"
            )

        if prompt is not None and prompt_embeds is not None:
            raise ValueError(
                f"Cannot forward both `prompt`: {prompt} and `prompt_embeds`: {prompt_embeds}. Please make sure to"
                " only forward one of the two."
            )
        elif prompt is None and prompt_embeds is None:
            raise ValueError(
                "Provide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined."
            )
        elif prompt is not None and (not isinstance(prompt, str) and not isinstance(prompt, list)):
            raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")

        if negative_prompt is not None and negative_prompt_embeds is not None:
            raise ValueError(
                f"Cannot forward both `negative_prompt`: {negative_prompt} and `negative_prompt_embeds`:"
                f" {negative_prompt_embeds}. Please make sure to only forward one of the two."
            )

        if prompt_embeds is not None and negative_prompt_embeds is not None:
            if prompt_embeds.shape != negative_prompt_embeds.shape:
                raise ValueError(
                    "`prompt_embeds` and `negative_prompt_embeds` must have the same shape when passed directly, but"
                    f" got: `prompt_embeds` {prompt_embeds.shape} != `negative_prompt_embeds`"
                    f" {negative_prompt_embeds.shape}."
                )

        # `prompt` needs more sophisticated handling when there are multiple
        # conditionings.
        if isinstance(self.controlnet, MultiControlNetModel):
            if isinstance(prompt, list):
                logger.warning(
                    f"You have {len(self.controlnet.nets)} ControlNets and you have passed {len(prompt)}"
                    " prompts. The conditionings will be fixed across the prompts."
                )

        # Check `image`
        if isinstance(self.controlnet, ControlNetModel):
            if not isinstance(video, list):
                raise TypeError(f"For single controlnet, `image` must be of type `list` but got {type(video)}")
            if len(video) != num_frames:
                raise ValueError(f"Excepted image to have length {num_frames} but got {len(video)=}")
        elif isinstance(self.controlnet, MultiControlNetModel):
            if not isinstance(video, list) or not isinstance(video[0], list):
                raise TypeError(f"For multiple controlnets: `image` must be type list of lists but got {type(video)=}")
            if len(video[0]) != num_frames:
                raise ValueError(f"Expected length of image sublist as {num_frames} but got {len(video[0])=}")
            if any(len(img) != len(video[0]) for img in video):
                raise ValueError("All conditioning frame batches for multicontrolnet must be same size")
        else:
            assert False

        # Check `controlnet_conditioning_scale`
        if isinstance(self.controlnet, ControlNetModel):
            if not isinstance(controlnet_conditioning_scale, float):
                raise TypeError("For single controlnet: `controlnet_conditioning_scale` must be type `float`.")
        elif isinstance(self.controlnet, MultiControlNetModel):
            if isinstance(controlnet_conditioning_scale, list):
                if any(isinstance(i, list) for i in controlnet_conditioning_scale):
                    raise ValueError("A single batch of multiple conditionings are supported at the moment.")
            elif isinstance(controlnet_conditioning_scale, list) and len(controlnet_conditioning_scale) != len(
                self.controlnet.nets
            ):
                raise ValueError(
                    "For multiple controlnets: When `controlnet_conditioning_scale` is specified as `list`, it must have"
                    " the same length as the number of controlnets"
                )
        else:
            assert False

        if not isinstance(control_guidance_start, (tuple, list)):
            control_guidance_start = [control_guidance_start]

        if not isinstance(control_guidance_end, (tuple, list)):
            control_guidance_end = [control_guidance_end]

        if len(control_guidance_start) != len(control_guidance_end):
            raise ValueError(
                f"`control_guidance_start` has {len(control_guidance_start)} elements, but `control_guidance_end` has"
                f"{len(control_guidance_end)} elements. Make sure to provide the same number of elements to each list."
            )

        if isinstance(self.controlnet, MultiControlNetModel):
            if len(control_guidance_start) != len(self.controlnet.nets):
                raise ValueError(
                    f"`control_guidance_start`: {control_guidance_start} has {len(control_guidance_start)} elements but"
                    f"there are {len(self.controlnet.nets)} controlnets available. Make sure to provide"
                    f"{len(self.controlnet.nets)}."
                )

        for start, end in zip(control_guidance_start, control_guidance_end):
            if start >= end:
                raise ValueError(
                    f"control guidance start: {start} cannot be larger or equal to control guidance end: {end}."
                )
            if start < 0.0:
                raise ValueError(f"control guidance start: {start} can't be smaller than 0.")
            if end > 1.0:
                raise ValueError(f"control guidance end: {end} can't be larger than 1.0.")

    # Copied from diffusers.pipelines.animatediff.pipeline_animatediff.AnimateDiffPipeline.prepare_latents
    def prepare_latents(
        self, batch_size, num_channels_latents, num_frames, height, width, dtype, generator, latents=None
    ):
        if isinstance(generator, list) and len(generator) != batch_size:
            raise ValueError(
                f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
                f" size of {batch_size}. Make sure the batch size matches the length of the generators."
            )

        shape = (
            batch_size,
            num_channels_latents,
            num_frames,
            height // self.vae_scale_factor,
            width // self.vae_scale_factor,
        )

        if latents is None:
            latents = randn_tensor(shape, generator=generator, dtype=dtype)

        # scale the initial noise by the standard deviation required by the scheduler
        latents = latents * self.scheduler.init_noise_sigma
        return latents

    def prepare_video(
        self,
        video,
        width,
        height,
        batch_size,
        num_videos_per_prompt,
        dtype,
        do_classifier_free_guidance=False,
        guess_mode=False,
    ):
        video = self.control_video_processor.preprocess_video(video, height=height, width=width).to(dtype=ms.float32)
        video = video.permute(0, 2, 1, 3, 4).flatten(start_dim=0, end_dim=1)
        video_batch_size = video.shape[0]

        if video_batch_size == 1:
            repeat_by = batch_size
        else:
            # image batch size is the same as prompt batch size
            repeat_by = num_videos_per_prompt

        video = video.repeat_interleave(repeat_by, dim=0)
        video = video.to(dtype=dtype)

        if do_classifier_free_guidance and not guess_mode:
            video = ops.cat([video] * 2)

        return video

    @property
    def guidance_scale(self):
        return self._guidance_scale

    @property
    def clip_skip(self):
        return self._clip_skip

    # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
    # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
    # corresponds to doing no classifier free guidance.
    @property
    def do_classifier_free_guidance(self):
        return self._guidance_scale > 1

    @property
    def cross_attention_kwargs(self):
        return self._cross_attention_kwargs

    @property
    def num_timesteps(self):
        return self._num_timesteps

    def __call__(
        self,
        prompt: Union[str, List[str]] = None,
        num_frames: Optional[int] = 16,
        height: Optional[int] = None,
        width: Optional[int] = None,
        num_inference_steps: int = 50,
        guidance_scale: float = 7.5,
        negative_prompt: Optional[Union[str, List[str]]] = None,
        num_videos_per_prompt: Optional[int] = 1,
        eta: float = 0.0,
        generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
        latents: Optional[ms.Tensor] = None,
        prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        ip_adapter_image: Optional[PipelineImageInput] = None,
        ip_adapter_image_embeds: Optional[PipelineImageInput] = None,
        conditioning_frames: Optional[List[PipelineImageInput]] = None,
        output_type: Optional[str] = "pil",
        return_dict: bool = False,
        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
        controlnet_conditioning_scale: Union[float, List[float]] = 1.0,
        guess_mode: bool = False,
        control_guidance_start: Union[float, List[float]] = 0.0,
        control_guidance_end: Union[float, List[float]] = 1.0,
        clip_skip: Optional[int] = None,
        callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
        decode_chunk_size: int = 16,
    ):
        r"""
        The call function to the pipeline for generation.

        Args:
            prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`.
            height (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
                The height in pixels of the generated video.
            width (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
                The width in pixels of the generated video.
            num_frames (`int`, *optional*, defaults to 16):
                The number of video frames that are generated. Defaults to 16 frames which at 8 frames per seconds
                amounts to 2 seconds of video.
            num_inference_steps (`int`, *optional*, defaults to 50):
                The number of denoising steps. More denoising steps usually lead to a higher quality videos at the
                expense of slower inference.
            guidance_scale (`float`, *optional*, defaults to 7.5):
                A higher guidance scale value encourages the model to generate images closely linked to the text
                `prompt` at the expense of lower image quality. Guidance scale is enabled when `guidance_scale > 1`.
            negative_prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts to guide what to not include in image generation. If not defined, you need to
                pass `negative_prompt_embeds` instead. Ignored when not using guidance (`guidance_scale < 1`).
            eta (`float`, *optional*, defaults to 0.0):
                Corresponds to parameter eta (η) from the [DDIM](https://arxiv.org/abs/2010.02502) paper. Only applies
                to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
            generator (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
                A [`np.random.Generator`](https://numpy.org/doc/stable/reference/random/generator.html) to make
                generation deterministic.
            latents (`ms.Tensor`, *optional*):
                Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for video
                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                tensor is generated by sampling using the supplied random `generator`. Latents should be of shape
                `(batch_size, num_channel, num_frames, height, width)`.
            prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
                provided, text embeddings are generated from the `prompt` input argument.
            negative_prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
                not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
            ip_adapter_image (`PipelineImageInput`, *optional*):
                Optional image input to work with IP Adapters.
            ip_adapter_image_embeds (`List[ms.Tensor]`, *optional*):
                Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
                IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should
                contain the negative image embedding if `do_classifier_free_guidance` is set to `True`. If not
                provided, embeddings are computed from the `ip_adapter_image` input argument.
            conditioning_frames (`List[PipelineImageInput]`, *optional*):
                The ControlNet input condition to provide guidance to the `unet` for generation. If multiple
                ControlNets are specified, images must be passed as a list such that each element of the list can be
                correctly batched for input to a single ControlNet.
            output_type (`str`, *optional*, defaults to `"pil"`):
                The output format of the generated video. Choose between `ms.Tensor`, `PIL.Image` or `np.array`.
            return_dict (`bool`, *optional*, defaults to `False`):
                Whether or not to return a [`~pipelines.text_to_video_synthesis.TextToVideoSDPipelineOutput`] instead
                of a plain tuple.
            cross_attention_kwargs (`dict`, *optional*):
                A kwargs dictionary that if specified is passed along to the [`AttentionProcessor`] as defined in
                [`self.processor`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
            controlnet_conditioning_scale (`float` or `List[float]`, *optional*, defaults to 1.0):
                The outputs of the ControlNet are multiplied by `controlnet_conditioning_scale` before they are added
                to the residual in the original `unet`. If multiple ControlNets are specified in `init`, you can set
                the corresponding scale as a list.
            guess_mode (`bool`, *optional*, defaults to `False`):
                The ControlNet encoder tries to recognize the content of the input image even if you remove all
                prompts. A `guidance_scale` value between 3.0 and 5.0 is recommended.
            control_guidance_start (`float` or `List[float]`, *optional*, defaults to 0.0):
                The percentage of total steps at which the ControlNet starts applying.
            control_guidance_end (`float` or `List[float]`, *optional*, defaults to 1.0):
                The percentage of total steps at which the ControlNet stops applying.
            clip_skip (`int`, *optional*):
                Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
                the output of the pre-final layer will be used for computing the prompt embeddings.
            callback_on_step_end (`Callable`, *optional*):
                A function that calls at the end of each denoising steps during the inference. The function is called
                with the following arguments: `callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int,
                callback_kwargs: Dict)`. `callback_kwargs` will include a list of all tensors as specified by
                `callback_on_step_end_tensor_inputs`.
            callback_on_step_end_tensor_inputs (`List`, *optional*):
                The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
                will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
                `._callback_tensor_inputs` attribute of your pipeline class.

        Examples:

        Returns:
            [`~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput`] or `tuple`:
                If `return_dict` is `True`, [`~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput`] is
                returned, otherwise a `tuple` is returned where the first element is a list with the generated frames.
        """
        controlnet = self.controlnet

        # align format for control guidance
        if not isinstance(control_guidance_start, list) and isinstance(control_guidance_end, list):
            control_guidance_start = len(control_guidance_end) * [control_guidance_start]
        elif not isinstance(control_guidance_end, list) and isinstance(control_guidance_start, list):
            control_guidance_end = len(control_guidance_start) * [control_guidance_end]
        elif not isinstance(control_guidance_start, list) and not isinstance(control_guidance_end, list):
            mult = len(controlnet.nets) if isinstance(controlnet, MultiControlNetModel) else 1
            control_guidance_start, control_guidance_end = (
                mult * [control_guidance_start],
                mult * [control_guidance_end],
            )

        # 0. Default height and width to unet
        height = height or self.unet.config.sample_size * self.vae_scale_factor
        width = width or self.unet.config.sample_size * self.vae_scale_factor

        num_videos_per_prompt = 1

        # 1. Check inputs. Raise error if not correct
        self.check_inputs(
            prompt=prompt,
            height=height,
            width=width,
            num_frames=num_frames,
            negative_prompt=negative_prompt,
            callback_on_step_end_tensor_inputs=callback_on_step_end_tensor_inputs,
            prompt_embeds=prompt_embeds,
            negative_prompt_embeds=negative_prompt_embeds,
            video=conditioning_frames,
            controlnet_conditioning_scale=controlnet_conditioning_scale,
            control_guidance_start=control_guidance_start,
            control_guidance_end=control_guidance_end,
        )

        self._guidance_scale = guidance_scale
        self._clip_skip = clip_skip
        self._cross_attention_kwargs = cross_attention_kwargs

        # 2. Define call parameters
        if prompt is not None and isinstance(prompt, str):
            batch_size = 1
        elif prompt is not None and isinstance(prompt, list):
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        if isinstance(controlnet, MultiControlNetModel) and isinstance(controlnet_conditioning_scale, float):
            controlnet_conditioning_scale = [controlnet_conditioning_scale] * len(controlnet.nets)

        global_pool_conditions = (
            controlnet.config.global_pool_conditions
            if isinstance(controlnet, ControlNetModel)
            else controlnet.nets[0].config.global_pool_conditions
        )
        guess_mode = guess_mode or global_pool_conditions

        # 3. Encode input prompt
        text_encoder_lora_scale = (
            cross_attention_kwargs.get("scale", None) if cross_attention_kwargs is not None else None
        )
        prompt_embeds, negative_prompt_embeds = self.encode_prompt(
            prompt,
            num_videos_per_prompt,
            self.do_classifier_free_guidance,
            negative_prompt,
            prompt_embeds=prompt_embeds,
            negative_prompt_embeds=negative_prompt_embeds,
            lora_scale=text_encoder_lora_scale,
            clip_skip=self.clip_skip,
        )
        # For classifier free guidance, we need to do two forward passes.
        # Here we concatenate the unconditional and text embeddings into a single batch
        # to avoid doing two forward passes
        if self.do_classifier_free_guidance:
            prompt_embeds = ops.cat([negative_prompt_embeds, prompt_embeds])

        if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
            image_embeds = self.prepare_ip_adapter_image_embeds(
                ip_adapter_image,
                ip_adapter_image_embeds,
                batch_size * num_videos_per_prompt,
                self.do_classifier_free_guidance,
            )

        if isinstance(controlnet, ControlNetModel):
            conditioning_frames = self.prepare_video(
                video=conditioning_frames,
                width=width,
                height=height,
                batch_size=batch_size * num_videos_per_prompt * num_frames,
                num_videos_per_prompt=num_videos_per_prompt,
                dtype=controlnet.dtype,
                do_classifier_free_guidance=self.do_classifier_free_guidance,
                guess_mode=guess_mode,
            )
        elif isinstance(controlnet, MultiControlNetModel):
            cond_prepared_videos = []
            for frame_ in conditioning_frames:
                prepared_video = self.prepare_video(
                    video=frame_,
                    width=width,
                    height=height,
                    batch_size=batch_size * num_videos_per_prompt * num_frames,
                    num_videos_per_prompt=num_videos_per_prompt,
                    dtype=controlnet.dtype,
                    do_classifier_free_guidance=self.do_classifier_free_guidance,
                    guess_mode=guess_mode,
                )
                cond_prepared_videos.append(prepared_video)
            conditioning_frames = cond_prepared_videos
        else:
            assert False

        # 4. Prepare timesteps
        self.scheduler.set_timesteps(num_inference_steps)
        timesteps = self.scheduler.timesteps

        # 5. Prepare latent variables
        num_channels_latents = self.unet.config.in_channels
        latents = self.prepare_latents(
            batch_size * num_videos_per_prompt,
            num_channels_latents,
            num_frames,
            height,
            width,
            prompt_embeds.dtype,
            generator,
            latents,
        )

        # 6. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
        extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)

        # 7. Add image embeds for IP-Adapter
        added_cond_kwargs = (
            {"image_embeds": image_embeds}
            if ip_adapter_image is not None or ip_adapter_image_embeds is not None
            else None
        )

        # 7.1 Create tensor stating which controlnets to keep
        controlnet_keep = []
        for i in range(len(timesteps)):
            keeps = [
                1.0 - float(i / len(timesteps) < s or (i + 1) / len(timesteps) > e)
                for s, e in zip(control_guidance_start, control_guidance_end)
            ]
            controlnet_keep.append(keeps[0] if isinstance(controlnet, ControlNetModel) else keeps)

        self._num_timesteps = len(timesteps)
        num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order

        # 8. Denoising loop
        with self.progress_bar(total=self._num_timesteps) as progress_bar:
            for i, t in enumerate(timesteps):
                # expand the latents if we are doing classifier free guidance
                latent_model_input = ops.cat([latents] * 2) if self.do_classifier_free_guidance else latents
                latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)

                if guess_mode and self.do_classifier_free_guidance:
                    # Infer ControlNet only for the conditional batch.
                    control_model_input = latents
                    control_model_input = self.scheduler.scale_model_input(control_model_input, t)
                    controlnet_prompt_embeds = prompt_embeds.chunk(2)[1]
                else:
                    control_model_input = latent_model_input
                    controlnet_prompt_embeds = prompt_embeds
                controlnet_prompt_embeds = controlnet_prompt_embeds.repeat_interleave(num_frames, dim=0)

                if isinstance(controlnet_keep[i], list):
                    cond_scale = [c * s for c, s in zip(controlnet_conditioning_scale, controlnet_keep[i])]
                else:
                    controlnet_cond_scale = controlnet_conditioning_scale
                    if isinstance(controlnet_cond_scale, list):
                        controlnet_cond_scale = controlnet_cond_scale[0]
                    cond_scale = controlnet_cond_scale * controlnet_keep[i]

                control_model_input = ops.swapaxes(control_model_input, 1, 2)
                control_model_input = control_model_input.reshape(
                    (-1, control_model_input.shape[2], control_model_input.shape[3], control_model_input.shape[4])
                )

                down_block_res_samples, mid_block_res_sample = self.controlnet(
                    control_model_input,
                    t,
                    encoder_hidden_states=controlnet_prompt_embeds,
                    controlnet_cond=conditioning_frames,
                    conditioning_scale=cond_scale,
                    guess_mode=guess_mode,
                    return_dict=False,
                )

                # predict the noise residual
                noise_pred = self.unet(
                    latent_model_input,
                    t,
                    encoder_hidden_states=prompt_embeds,
                    cross_attention_kwargs=self.cross_attention_kwargs,
                    added_cond_kwargs=ms.mutable(added_cond_kwargs) if added_cond_kwargs else added_cond_kwargs,
                    down_block_additional_residuals=ms.mutable(down_block_res_samples),
                    mid_block_additional_residual=mid_block_res_sample,
                )[0]

                # perform guidance
                if self.do_classifier_free_guidance:
                    noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
                    noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)

                # compute the previous noisy sample x_t -> x_t-1
                latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs)[0]

                if callback_on_step_end is not None:
                    callback_kwargs = {}
                    for k in callback_on_step_end_tensor_inputs:
                        callback_kwargs[k] = locals()[k]
                    callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)

                    latents = callback_outputs.pop("latents", latents)
                    prompt_embeds = callback_outputs.pop("prompt_embeds", prompt_embeds)
                    negative_prompt_embeds = callback_outputs.pop("negative_prompt_embeds", negative_prompt_embeds)

                # call the callback, if provided
                if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
                    progress_bar.update()

        # 9. Post processing
        if output_type == "latent":
            video = latents
        else:
            video_tensor = self.decode_latents(latents, decode_chunk_size)
            video = self.video_processor.postprocess_video(video=video_tensor, output_type=output_type)

        if not return_dict:
            return (video,)

        return AnimateDiffPipelineOutput(frames=video)

mindone.diffusers.pipelines.AnimateDiffControlNetPipeline.__call__(prompt=None, num_frames=16, height=None, width=None, num_inference_steps=50, guidance_scale=7.5, negative_prompt=None, num_videos_per_prompt=1, eta=0.0, generator=None, latents=None, prompt_embeds=None, negative_prompt_embeds=None, ip_adapter_image=None, ip_adapter_image_embeds=None, conditioning_frames=None, output_type='pil', return_dict=False, cross_attention_kwargs=None, controlnet_conditioning_scale=1.0, guess_mode=False, control_guidance_start=0.0, control_guidance_end=1.0, clip_skip=None, callback_on_step_end=None, callback_on_step_end_tensor_inputs=['latents'], decode_chunk_size=16)

The call function to the pipeline for generation.

PARAMETER DESCRIPTION
prompt

The prompt or prompts to guide image generation. If not defined, you need to pass prompt_embeds.

TYPE: `str` or `List[str]`, *optional* DEFAULT: None

height

The height in pixels of the generated video.

TYPE: `int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor` DEFAULT: None

width

The width in pixels of the generated video.

TYPE: `int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor` DEFAULT: None

num_frames

The number of video frames that are generated. Defaults to 16 frames which at 8 frames per seconds amounts to 2 seconds of video.

TYPE: `int`, *optional*, defaults to 16 DEFAULT: 16

num_inference_steps

The number of denoising steps. More denoising steps usually lead to a higher quality videos at the expense of slower inference.

TYPE: `int`, *optional*, defaults to 50 DEFAULT: 50

guidance_scale

A higher guidance scale value encourages the model to generate images closely linked to the text prompt at the expense of lower image quality. Guidance scale is enabled when guidance_scale > 1.

TYPE: `float`, *optional*, defaults to 7.5 DEFAULT: 7.5

negative_prompt

The prompt or prompts to guide what to not include in image generation. If not defined, you need to pass negative_prompt_embeds instead. Ignored when not using guidance (guidance_scale < 1).

TYPE: `str` or `List[str]`, *optional* DEFAULT: None

eta

Corresponds to parameter eta (η) from the DDIM paper. Only applies to the [~schedulers.DDIMScheduler], and is ignored in other schedulers.

TYPE: `float`, *optional*, defaults to 0.0 DEFAULT: 0.0

generator

A np.random.Generator to make generation deterministic.

TYPE: `np.random.Generator` or `List[np.random.Generator]`, *optional* DEFAULT: None

latents

Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for video generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor is generated by sampling using the supplied random generator. Latents should be of shape (batch_size, num_channel, num_frames, height, width).

TYPE: `ms.Tensor`, *optional* DEFAULT: None

prompt_embeds

Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not provided, text embeddings are generated from the prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

negative_prompt_embeds

Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not provided, negative_prompt_embeds are generated from the negative_prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

ip_adapter_image

Optional image input to work with IP Adapters.

TYPE: `PipelineImageInput`, *optional* DEFAULT: None

ip_adapter_image_embeds

Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of IP-adapters. Each element should be a tensor of shape (batch_size, num_images, emb_dim). It should contain the negative image embedding if do_classifier_free_guidance is set to True. If not provided, embeddings are computed from the ip_adapter_image input argument.

TYPE: `List[ms.Tensor]`, *optional* DEFAULT: None

conditioning_frames

The ControlNet input condition to provide guidance to the unet for generation. If multiple ControlNets are specified, images must be passed as a list such that each element of the list can be correctly batched for input to a single ControlNet.

TYPE: `List[PipelineImageInput]`, *optional* DEFAULT: None

output_type

The output format of the generated video. Choose between ms.Tensor, PIL.Image or np.array.

TYPE: `str`, *optional*, defaults to `"pil"` DEFAULT: 'pil'

return_dict

Whether or not to return a [~pipelines.text_to_video_synthesis.TextToVideoSDPipelineOutput] instead of a plain tuple.

TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False

cross_attention_kwargs

A kwargs dictionary that if specified is passed along to the [AttentionProcessor] as defined in self.processor.

TYPE: `dict`, *optional* DEFAULT: None

controlnet_conditioning_scale

The outputs of the ControlNet are multiplied by controlnet_conditioning_scale before they are added to the residual in the original unet. If multiple ControlNets are specified in init, you can set the corresponding scale as a list.

TYPE: `float` or `List[float]`, *optional*, defaults to 1.0 DEFAULT: 1.0

guess_mode

The ControlNet encoder tries to recognize the content of the input image even if you remove all prompts. A guidance_scale value between 3.0 and 5.0 is recommended.

TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False

control_guidance_start

The percentage of total steps at which the ControlNet starts applying.

TYPE: `float` or `List[float]`, *optional*, defaults to 0.0 DEFAULT: 0.0

control_guidance_end

The percentage of total steps at which the ControlNet stops applying.

TYPE: `float` or `List[float]`, *optional*, defaults to 1.0 DEFAULT: 1.0

clip_skip

Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that the output of the pre-final layer will be used for computing the prompt embeddings.

TYPE: `int`, *optional* DEFAULT: None

callback_on_step_end

A function that calls at the end of each denoising steps during the inference. The function is called with the following arguments: callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict). callback_kwargs will include a list of all tensors as specified by callback_on_step_end_tensor_inputs.

TYPE: `Callable`, *optional* DEFAULT: None

callback_on_step_end_tensor_inputs

The list of tensor inputs for the callback_on_step_end function. The tensors specified in the list will be passed as callback_kwargs argument. You will only be able to include variables listed in the ._callback_tensor_inputs attribute of your pipeline class.

TYPE: `List`, *optional* DEFAULT: ['latents']

RETURNS DESCRIPTION

[~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput] or tuple: If return_dict is True, [~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput] is returned, otherwise a tuple is returned where the first element is a list with the generated frames.
Source code in mindone/diffusers/pipelines/animatediff/pipeline_animatediff_controlnet.py 
 667
 668
 669
 670
 671
 672
 673
 674
 675
 676
 677
 678
 679
 680
 681
 682
 683
 684
 685
 686
 687
 688
 689
 690
 691
 692
 693
 694
 695
 696
 697
 698
 699
 700
 701
 702
 703
 704
 705
 706
 707
 708
 709
 710
 711
 712
 713
 714
 715
 716
 717
 718
 719
 720
 721
 722
 723
 724
 725
 726
 727
 728
 729
 730
 731
 732
 733
 734
 735
 736
 737
 738
 739
 740
 741
 742
 743
 744
 745
 746
 747
 748
 749
 750
 751
 752
 753
 754
 755
 756
 757
 758
 759
 760
 761
 762
 763
 764
 765
 766
 767
 768
 769
 770
 771
 772
 773
 774
 775
 776
 777
 778
 779
 780
 781
 782
 783
 784
 785
 786
 787
 788
 789
 790
 791
 792
 793
 794
 795
 796
 797
 798
 799
 800
 801
 802
 803
 804
 805
 806
 807
 808
 809
 810
 811
 812
 813
 814
 815
 816
 817
 818
 819
 820
 821
 822
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
def __call__(
    self,
    prompt: Union[str, List[str]] = None,
    num_frames: Optional[int] = 16,
    height: Optional[int] = None,
    width: Optional[int] = None,
    num_inference_steps: int = 50,
    guidance_scale: float = 7.5,
    negative_prompt: Optional[Union[str, List[str]]] = None,
    num_videos_per_prompt: Optional[int] = 1,
    eta: float = 0.0,
    generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
    latents: Optional[ms.Tensor] = None,
    prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    ip_adapter_image: Optional[PipelineImageInput] = None,
    ip_adapter_image_embeds: Optional[PipelineImageInput] = None,
    conditioning_frames: Optional[List[PipelineImageInput]] = None,
    output_type: Optional[str] = "pil",
    return_dict: bool = False,
    cross_attention_kwargs: Optional[Dict[str, Any]] = None,
    controlnet_conditioning_scale: Union[float, List[float]] = 1.0,
    guess_mode: bool = False,
    control_guidance_start: Union[float, List[float]] = 0.0,
    control_guidance_end: Union[float, List[float]] = 1.0,
    clip_skip: Optional[int] = None,
    callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
    callback_on_step_end_tensor_inputs: List[str] = ["latents"],
    decode_chunk_size: int = 16,
):
    r"""
    The call function to the pipeline for generation.

    Args:
        prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`.
        height (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
            The height in pixels of the generated video.
        width (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
            The width in pixels of the generated video.
        num_frames (`int`, *optional*, defaults to 16):
            The number of video frames that are generated. Defaults to 16 frames which at 8 frames per seconds
            amounts to 2 seconds of video.
        num_inference_steps (`int`, *optional*, defaults to 50):
            The number of denoising steps. More denoising steps usually lead to a higher quality videos at the
            expense of slower inference.
        guidance_scale (`float`, *optional*, defaults to 7.5):
            A higher guidance scale value encourages the model to generate images closely linked to the text
            `prompt` at the expense of lower image quality. Guidance scale is enabled when `guidance_scale > 1`.
        negative_prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts to guide what to not include in image generation. If not defined, you need to
            pass `negative_prompt_embeds` instead. Ignored when not using guidance (`guidance_scale < 1`).
        eta (`float`, *optional*, defaults to 0.0):
            Corresponds to parameter eta (η) from the [DDIM](https://arxiv.org/abs/2010.02502) paper. Only applies
            to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
        generator (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
            A [`np.random.Generator`](https://numpy.org/doc/stable/reference/random/generator.html) to make
            generation deterministic.
        latents (`ms.Tensor`, *optional*):
            Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for video
            generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
            tensor is generated by sampling using the supplied random `generator`. Latents should be of shape
            `(batch_size, num_channel, num_frames, height, width)`.
        prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
            provided, text embeddings are generated from the `prompt` input argument.
        negative_prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
            not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
        ip_adapter_image (`PipelineImageInput`, *optional*):
            Optional image input to work with IP Adapters.
        ip_adapter_image_embeds (`List[ms.Tensor]`, *optional*):
            Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
            IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should
            contain the negative image embedding if `do_classifier_free_guidance` is set to `True`. If not
            provided, embeddings are computed from the `ip_adapter_image` input argument.
        conditioning_frames (`List[PipelineImageInput]`, *optional*):
            The ControlNet input condition to provide guidance to the `unet` for generation. If multiple
            ControlNets are specified, images must be passed as a list such that each element of the list can be
            correctly batched for input to a single ControlNet.
        output_type (`str`, *optional*, defaults to `"pil"`):
            The output format of the generated video. Choose between `ms.Tensor`, `PIL.Image` or `np.array`.
        return_dict (`bool`, *optional*, defaults to `False`):
            Whether or not to return a [`~pipelines.text_to_video_synthesis.TextToVideoSDPipelineOutput`] instead
            of a plain tuple.
        cross_attention_kwargs (`dict`, *optional*):
            A kwargs dictionary that if specified is passed along to the [`AttentionProcessor`] as defined in
            [`self.processor`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
        controlnet_conditioning_scale (`float` or `List[float]`, *optional*, defaults to 1.0):
            The outputs of the ControlNet are multiplied by `controlnet_conditioning_scale` before they are added
            to the residual in the original `unet`. If multiple ControlNets are specified in `init`, you can set
            the corresponding scale as a list.
        guess_mode (`bool`, *optional*, defaults to `False`):
            The ControlNet encoder tries to recognize the content of the input image even if you remove all
            prompts. A `guidance_scale` value between 3.0 and 5.0 is recommended.
        control_guidance_start (`float` or `List[float]`, *optional*, defaults to 0.0):
            The percentage of total steps at which the ControlNet starts applying.
        control_guidance_end (`float` or `List[float]`, *optional*, defaults to 1.0):
            The percentage of total steps at which the ControlNet stops applying.
        clip_skip (`int`, *optional*):
            Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
            the output of the pre-final layer will be used for computing the prompt embeddings.
        callback_on_step_end (`Callable`, *optional*):
            A function that calls at the end of each denoising steps during the inference. The function is called
            with the following arguments: `callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int,
            callback_kwargs: Dict)`. `callback_kwargs` will include a list of all tensors as specified by
            `callback_on_step_end_tensor_inputs`.
        callback_on_step_end_tensor_inputs (`List`, *optional*):
            The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
            will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
            `._callback_tensor_inputs` attribute of your pipeline class.

    Examples:

    Returns:
        [`~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput`] or `tuple`:
            If `return_dict` is `True`, [`~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput`] is
            returned, otherwise a `tuple` is returned where the first element is a list with the generated frames.
    """
    controlnet = self.controlnet

    # align format for control guidance
    if not isinstance(control_guidance_start, list) and isinstance(control_guidance_end, list):
        control_guidance_start = len(control_guidance_end) * [control_guidance_start]
    elif not isinstance(control_guidance_end, list) and isinstance(control_guidance_start, list):
        control_guidance_end = len(control_guidance_start) * [control_guidance_end]
    elif not isinstance(control_guidance_start, list) and not isinstance(control_guidance_end, list):
        mult = len(controlnet.nets) if isinstance(controlnet, MultiControlNetModel) else 1
        control_guidance_start, control_guidance_end = (
            mult * [control_guidance_start],
            mult * [control_guidance_end],
        )

    # 0. Default height and width to unet
    height = height or self.unet.config.sample_size * self.vae_scale_factor
    width = width or self.unet.config.sample_size * self.vae_scale_factor

    num_videos_per_prompt = 1

    # 1. Check inputs. Raise error if not correct
    self.check_inputs(
        prompt=prompt,
        height=height,
        width=width,
        num_frames=num_frames,
        negative_prompt=negative_prompt,
        callback_on_step_end_tensor_inputs=callback_on_step_end_tensor_inputs,
        prompt_embeds=prompt_embeds,
        negative_prompt_embeds=negative_prompt_embeds,
        video=conditioning_frames,
        controlnet_conditioning_scale=controlnet_conditioning_scale,
        control_guidance_start=control_guidance_start,
        control_guidance_end=control_guidance_end,
    )

    self._guidance_scale = guidance_scale
    self._clip_skip = clip_skip
    self._cross_attention_kwargs = cross_attention_kwargs

    # 2. Define call parameters
    if prompt is not None and isinstance(prompt, str):
        batch_size = 1
    elif prompt is not None and isinstance(prompt, list):
        batch_size = len(prompt)
    else:
        batch_size = prompt_embeds.shape[0]

    if isinstance(controlnet, MultiControlNetModel) and isinstance(controlnet_conditioning_scale, float):
        controlnet_conditioning_scale = [controlnet_conditioning_scale] * len(controlnet.nets)

    global_pool_conditions = (
        controlnet.config.global_pool_conditions
        if isinstance(controlnet, ControlNetModel)
        else controlnet.nets[0].config.global_pool_conditions
    )
    guess_mode = guess_mode or global_pool_conditions

    # 3. Encode input prompt
    text_encoder_lora_scale = (
        cross_attention_kwargs.get("scale", None) if cross_attention_kwargs is not None else None
    )
    prompt_embeds, negative_prompt_embeds = self.encode_prompt(
        prompt,
        num_videos_per_prompt,
        self.do_classifier_free_guidance,
        negative_prompt,
        prompt_embeds=prompt_embeds,
        negative_prompt_embeds=negative_prompt_embeds,
        lora_scale=text_encoder_lora_scale,
        clip_skip=self.clip_skip,
    )
    # For classifier free guidance, we need to do two forward passes.
    # Here we concatenate the unconditional and text embeddings into a single batch
    # to avoid doing two forward passes
    if self.do_classifier_free_guidance:
        prompt_embeds = ops.cat([negative_prompt_embeds, prompt_embeds])

    if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
        image_embeds = self.prepare_ip_adapter_image_embeds(
            ip_adapter_image,
            ip_adapter_image_embeds,
            batch_size * num_videos_per_prompt,
            self.do_classifier_free_guidance,
        )

    if isinstance(controlnet, ControlNetModel):
        conditioning_frames = self.prepare_video(
            video=conditioning_frames,
            width=width,
            height=height,
            batch_size=batch_size * num_videos_per_prompt * num_frames,
            num_videos_per_prompt=num_videos_per_prompt,
            dtype=controlnet.dtype,
            do_classifier_free_guidance=self.do_classifier_free_guidance,
            guess_mode=guess_mode,
        )
    elif isinstance(controlnet, MultiControlNetModel):
        cond_prepared_videos = []
        for frame_ in conditioning_frames:
            prepared_video = self.prepare_video(
                video=frame_,
                width=width,
                height=height,
                batch_size=batch_size * num_videos_per_prompt * num_frames,
                num_videos_per_prompt=num_videos_per_prompt,
                dtype=controlnet.dtype,
                do_classifier_free_guidance=self.do_classifier_free_guidance,
                guess_mode=guess_mode,
            )
            cond_prepared_videos.append(prepared_video)
        conditioning_frames = cond_prepared_videos
    else:
        assert False

    # 4. Prepare timesteps
    self.scheduler.set_timesteps(num_inference_steps)
    timesteps = self.scheduler.timesteps

    # 5. Prepare latent variables
    num_channels_latents = self.unet.config.in_channels
    latents = self.prepare_latents(
        batch_size * num_videos_per_prompt,
        num_channels_latents,
        num_frames,
        height,
        width,
        prompt_embeds.dtype,
        generator,
        latents,
    )

    # 6. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
    extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)

    # 7. Add image embeds for IP-Adapter
    added_cond_kwargs = (
        {"image_embeds": image_embeds}
        if ip_adapter_image is not None or ip_adapter_image_embeds is not None
        else None
    )

    # 7.1 Create tensor stating which controlnets to keep
    controlnet_keep = []
    for i in range(len(timesteps)):
        keeps = [
            1.0 - float(i / len(timesteps) < s or (i + 1) / len(timesteps) > e)
            for s, e in zip(control_guidance_start, control_guidance_end)
        ]
        controlnet_keep.append(keeps[0] if isinstance(controlnet, ControlNetModel) else keeps)

    self._num_timesteps = len(timesteps)
    num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order

    # 8. Denoising loop
    with self.progress_bar(total=self._num_timesteps) as progress_bar:
        for i, t in enumerate(timesteps):
            # expand the latents if we are doing classifier free guidance
            latent_model_input = ops.cat([latents] * 2) if self.do_classifier_free_guidance else latents
            latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)

            if guess_mode and self.do_classifier_free_guidance:
                # Infer ControlNet only for the conditional batch.
                control_model_input = latents
                control_model_input = self.scheduler.scale_model_input(control_model_input, t)
                controlnet_prompt_embeds = prompt_embeds.chunk(2)[1]
            else:
                control_model_input = latent_model_input
                controlnet_prompt_embeds = prompt_embeds
            controlnet_prompt_embeds = controlnet_prompt_embeds.repeat_interleave(num_frames, dim=0)

            if isinstance(controlnet_keep[i], list):
                cond_scale = [c * s for c, s in zip(controlnet_conditioning_scale, controlnet_keep[i])]
            else:
                controlnet_cond_scale = controlnet_conditioning_scale
                if isinstance(controlnet_cond_scale, list):
                    controlnet_cond_scale = controlnet_cond_scale[0]
                cond_scale = controlnet_cond_scale * controlnet_keep[i]

            control_model_input = ops.swapaxes(control_model_input, 1, 2)
            control_model_input = control_model_input.reshape(
                (-1, control_model_input.shape[2], control_model_input.shape[3], control_model_input.shape[4])
            )

            down_block_res_samples, mid_block_res_sample = self.controlnet(
                control_model_input,
                t,
                encoder_hidden_states=controlnet_prompt_embeds,
                controlnet_cond=conditioning_frames,
                conditioning_scale=cond_scale,
                guess_mode=guess_mode,
                return_dict=False,
            )

            # predict the noise residual
            noise_pred = self.unet(
                latent_model_input,
                t,
                encoder_hidden_states=prompt_embeds,
                cross_attention_kwargs=self.cross_attention_kwargs,
                added_cond_kwargs=ms.mutable(added_cond_kwargs) if added_cond_kwargs else added_cond_kwargs,
                down_block_additional_residuals=ms.mutable(down_block_res_samples),
                mid_block_additional_residual=mid_block_res_sample,
            )[0]

            # perform guidance
            if self.do_classifier_free_guidance:
                noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
                noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)

            # compute the previous noisy sample x_t -> x_t-1
            latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs)[0]

            if callback_on_step_end is not None:
                callback_kwargs = {}
                for k in callback_on_step_end_tensor_inputs:
                    callback_kwargs[k] = locals()[k]
                callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)

                latents = callback_outputs.pop("latents", latents)
                prompt_embeds = callback_outputs.pop("prompt_embeds", prompt_embeds)
                negative_prompt_embeds = callback_outputs.pop("negative_prompt_embeds", negative_prompt_embeds)

            # call the callback, if provided
            if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
                progress_bar.update()

    # 9. Post processing
    if output_type == "latent":
        video = latents
    else:
        video_tensor = self.decode_latents(latents, decode_chunk_size)
        video = self.video_processor.postprocess_video(video=video_tensor, output_type=output_type)

    if not return_dict:
        return (video,)

    return AnimateDiffPipelineOutput(frames=video)

mindone.diffusers.pipelines.AnimateDiffControlNetPipeline.encode_prompt(prompt, num_images_per_prompt, do_classifier_free_guidance, negative_prompt=None, prompt_embeds=None, negative_prompt_embeds=None, lora_scale=None, clip_skip=None)

Encodes the prompt into text encoder hidden states.

PARAMETER DESCRIPTION
prompt

prompt to be encoded

TYPE: `str` or `List[str]`, *optional*

num_images_per_prompt

number of images that should be generated per prompt

TYPE: `int`

do_classifier_free_guidance

whether to use classifier free guidance or not

TYPE: `bool`

negative_prompt

The prompt or prompts not to guide the image generation. If not defined, one has to pass negative_prompt_embeds instead. Ignored when not using guidance (i.e., ignored if guidance_scale is less than 1).

TYPE: `str` or `List[str]`, *optional* DEFAULT: None

prompt_embeds

Pre-generated text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, text embeddings will be generated from prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

negative_prompt_embeds

Pre-generated negative text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, negative_prompt_embeds will be generated from negative_prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

lora_scale

A LoRA scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.

TYPE: `float`, *optional* DEFAULT: None

clip_skip

Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that the output of the pre-final layer will be used for computing the prompt embeddings.

TYPE: `int`, *optional* DEFAULT: None

Source code in mindone/diffusers/pipelines/animatediff/pipeline_animatediff_controlnet.py 
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
def encode_prompt(
    self,
    prompt,
    num_images_per_prompt,
    do_classifier_free_guidance,
    negative_prompt=None,
    prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    lora_scale: Optional[float] = None,
    clip_skip: Optional[int] = None,
):
    r"""
    Encodes the prompt into text encoder hidden states.

    Args:
        prompt (`str` or `List[str]`, *optional*):
            prompt to be encoded
        num_images_per_prompt (`int`):
            number of images that should be generated per prompt
        do_classifier_free_guidance (`bool`):
            whether to use classifier free guidance or not
        negative_prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts not to guide the image generation. If not defined, one has to pass
            `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
            less than `1`).
        prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
            provided, text embeddings will be generated from `prompt` input argument.
        negative_prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
            weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
            argument.
        lora_scale (`float`, *optional*):
            A LoRA scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
        clip_skip (`int`, *optional*):
            Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
            the output of the pre-final layer will be used for computing the prompt embeddings.
    """
    # set lora scale so that monkey patched LoRA
    # function of text encoder can correctly access it
    if lora_scale is not None and isinstance(self, StableDiffusionLoraLoaderMixin):
        self._lora_scale = lora_scale

        # dynamically adjust the LoRA scale
        scale_lora_layers(self.text_encoder, lora_scale)

    if prompt is not None and isinstance(prompt, str):
        batch_size = 1
    elif prompt is not None and isinstance(prompt, list):
        batch_size = len(prompt)
    else:
        batch_size = prompt_embeds.shape[0]

    if prompt_embeds is None:
        # textual inversion: process multi-vector tokens if necessary
        if isinstance(self, TextualInversionLoaderMixin):
            prompt = self.maybe_convert_prompt(prompt, self.tokenizer)

        text_inputs = self.tokenizer(
            prompt,
            padding="max_length",
            max_length=self.tokenizer.model_max_length,
            truncation=True,
            return_tensors="np",
        )
        text_input_ids = text_inputs.input_ids
        untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="np").input_ids

        if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not np.array_equal(
            text_input_ids, untruncated_ids
        ):
            removed_text = self.tokenizer.batch_decode(untruncated_ids[:, self.tokenizer.model_max_length - 1 : -1])
            logger.warning(
                "The following part of your input was truncated because CLIP can only handle sequences up to"
                f" {self.tokenizer.model_max_length} tokens: {removed_text}"
            )

        if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
            attention_mask = ms.Tensor(text_inputs.attention_mask)
        else:
            attention_mask = None

        text_input_ids = ms.Tensor(text_input_ids)
        if clip_skip is None:
            prompt_embeds = self.text_encoder(text_input_ids, attention_mask=attention_mask)
            prompt_embeds = prompt_embeds[0]
        else:
            prompt_embeds = self.text_encoder(
                text_input_ids, attention_mask=attention_mask, output_hidden_states=True
            )
            # Access the `hidden_states` first, that contains a tuple of
            # all the hidden states from the encoder layers. Then index into
            # the tuple to access the hidden states from the desired layer.
            prompt_embeds = prompt_embeds[-1][-(clip_skip + 1)]
            # We also need to apply the final LayerNorm here to not mess with the
            # representations. The `last_hidden_states` that we typically use for
            # obtaining the final prompt representations passes through the LayerNorm
            # layer.
            prompt_embeds = self.text_encoder.text_model.final_layer_norm(prompt_embeds)

    if self.text_encoder is not None:
        prompt_embeds_dtype = self.text_encoder.dtype
    elif self.unet is not None:
        prompt_embeds_dtype = self.unet.dtype
    else:
        prompt_embeds_dtype = prompt_embeds.dtype

    prompt_embeds = prompt_embeds.to(dtype=prompt_embeds_dtype)

    bs_embed, seq_len, _ = prompt_embeds.shape
    # duplicate text embeddings for each generation per prompt, using mps friendly method
    prompt_embeds = prompt_embeds.tile((1, num_images_per_prompt, 1))
    prompt_embeds = prompt_embeds.view(bs_embed * num_images_per_prompt, seq_len, -1)

    # get unconditional embeddings for classifier free guidance
    if do_classifier_free_guidance and negative_prompt_embeds is None:
        uncond_tokens: List[str]
        if negative_prompt is None:
            uncond_tokens = [""] * batch_size
        elif prompt is not None and type(prompt) is not type(negative_prompt):
            raise TypeError(
                f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
                f" {type(prompt)}."
            )
        elif isinstance(negative_prompt, str):
            uncond_tokens = [negative_prompt]
        elif batch_size != len(negative_prompt):
            raise ValueError(
                f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
                f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
                " the batch size of `prompt`."
            )
        else:
            uncond_tokens = negative_prompt

        # textual inversion: process multi-vector tokens if necessary
        if isinstance(self, TextualInversionLoaderMixin):
            uncond_tokens = self.maybe_convert_prompt(uncond_tokens, self.tokenizer)

        max_length = prompt_embeds.shape[1]
        uncond_input = self.tokenizer(
            uncond_tokens,
            padding="max_length",
            max_length=max_length,
            truncation=True,
            return_tensors="np",
        )

        if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
            attention_mask = ms.Tensor(uncond_input.attention_mask)
        else:
            attention_mask = None

        negative_prompt_embeds = self.text_encoder(
            ms.Tensor(uncond_input.input_ids),
            attention_mask=attention_mask,
        )
        negative_prompt_embeds = negative_prompt_embeds[0]

    if do_classifier_free_guidance:
        # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
        seq_len = negative_prompt_embeds.shape[1]

        negative_prompt_embeds = negative_prompt_embeds.to(dtype=prompt_embeds_dtype)

        negative_prompt_embeds = negative_prompt_embeds.tile((1, num_images_per_prompt, 1))
        negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)

    if self.text_encoder is not None:
        if isinstance(self, StableDiffusionLoraLoaderMixin):
            # Retrieve the original scale by scaling back the LoRA layers
            unscale_lora_layers(self.text_encoder, lora_scale)

    return prompt_embeds, negative_prompt_embeds

mindone.diffusers.pipelines.AnimateDiffSparseControlNetPipeline

Bases: DiffusionPipeline, TextualInversionLoaderMixin, IPAdapterMixin, StableDiffusionLoraLoaderMixin

Pipeline for controlled text-to-video generation using the method described in SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models.

This model inherits from [DiffusionPipeline]. Check the superclass documentation for the generic methods implemented for all pipelines (downloading, saving, running on a particular device, etc.).

The pipeline also inherits the following loading methods
  • [~loaders.TextualInversionLoaderMixin.load_textual_inversion] for loading textual inversion embeddings
  • [~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights] for loading LoRA weights
  • [~loaders.StableDiffusionLoraLoaderMixin.save_lora_weights] for saving LoRA weights
  • [~loaders.IPAdapterMixin.load_ip_adapter] for loading IP Adapters
PARAMETER DESCRIPTION
vae

Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.

TYPE: [`AutoencoderKL`]

text_encoder

Frozen text-encoder (clip-vit-large-patch14).

TYPE: [`CLIPTextModel`]

tokenizer

A [~transformers.CLIPTokenizer] to tokenize text.

TYPE: `CLIPTokenizer`

unet

A [UNet2DConditionModel] used to create a UNetMotionModel to denoise the encoded video latents.

TYPE: [`UNet2DConditionModel`]

motion_adapter

A [MotionAdapter] to be used in combination with unet to denoise the encoded video latents.

TYPE: [`MotionAdapter`]

scheduler

A scheduler to be used in combination with unet to denoise the encoded image latents. Can be one of [DDIMScheduler], [LMSDiscreteScheduler], or [PNDMScheduler].

TYPE: [`SchedulerMixin`]

Source code in mindone/diffusers/pipelines/animatediff/pipeline_animatediff_sparsectrl.py 
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
class AnimateDiffSparseControlNetPipeline(
    DiffusionPipeline,
    TextualInversionLoaderMixin,
    IPAdapterMixin,
    StableDiffusionLoraLoaderMixin,
):
    r"""
    Pipeline for controlled text-to-video generation using the method described in [SparseCtrl: Adding Sparse Controls
    to Text-to-Video Diffusion Models](https://arxiv.org/abs/2311.16933).

    This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods
    implemented for all pipelines (downloading, saving, running on a particular device, etc.).

    The pipeline also inherits the following loading methods:
        - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
        - [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] for loading LoRA weights
        - [`~loaders.StableDiffusionLoraLoaderMixin.save_lora_weights`] for saving LoRA weights
        - [`~loaders.IPAdapterMixin.load_ip_adapter`] for loading IP Adapters

    Args:
        vae ([`AutoencoderKL`]):
            Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
        text_encoder ([`CLIPTextModel`]):
            Frozen text-encoder ([clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14)).
        tokenizer (`CLIPTokenizer`):
            A [`~transformers.CLIPTokenizer`] to tokenize text.
        unet ([`UNet2DConditionModel`]):
            A [`UNet2DConditionModel`] used to create a UNetMotionModel to denoise the encoded video latents.
        motion_adapter ([`MotionAdapter`]):
            A [`MotionAdapter`] to be used in combination with `unet` to denoise the encoded video latents.
        scheduler ([`SchedulerMixin`]):
            A scheduler to be used in combination with `unet` to denoise the encoded image latents. Can be one of
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
    """

    model_cpu_offload_seq = "text_encoder->image_encoder->unet->vae"
    _optional_components = ["feature_extractor", "image_encoder", "motion_adapter"]
    _callback_tensor_inputs = ["latents", "prompt_embeds", "negative_prompt_embeds"]

    def __init__(
        self,
        vae: AutoencoderKL,
        text_encoder: CLIPTextModel,
        tokenizer: CLIPTokenizer,
        unet: Union[UNet2DConditionModel, UNetMotionModel],
        motion_adapter: MotionAdapter,
        controlnet: SparseControlNetModel,
        scheduler: KarrasDiffusionSchedulers,
        feature_extractor: CLIPImageProcessor = None,
        image_encoder: CLIPVisionModelWithProjection = None,
    ):
        super().__init__()
        if isinstance(unet, UNet2DConditionModel):
            unet = UNetMotionModel.from_unet2d(unet, motion_adapter)

        self.register_modules(
            vae=vae,
            text_encoder=text_encoder,
            tokenizer=tokenizer,
            unet=unet,
            motion_adapter=motion_adapter,
            controlnet=controlnet,
            scheduler=scheduler,
            feature_extractor=feature_extractor,
            image_encoder=image_encoder,
        )
        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
        self.video_processor = VideoProcessor(do_resize=False, vae_scale_factor=self.vae_scale_factor)
        self.control_image_processor = VaeImageProcessor(
            vae_scale_factor=self.vae_scale_factor, do_convert_rgb=True, do_normalize=False
        )

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_prompt
    # with num_images_per_prompt -> num_videos_per_prompt
    def encode_prompt(
        self,
        prompt,
        num_images_per_prompt,
        do_classifier_free_guidance,
        negative_prompt=None,
        prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        lora_scale: Optional[float] = None,
        clip_skip: Optional[int] = None,
    ):
        r"""
        Encodes the prompt into text encoder hidden states.

        Args:
            prompt (`str` or `List[str]`, *optional*):
                prompt to be encoded
            num_images_per_prompt (`int`):
                number of images that should be generated per prompt
            do_classifier_free_guidance (`bool`):
                whether to use classifier free guidance or not
            negative_prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts not to guide the image generation. If not defined, one has to pass
                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
                less than `1`).
            prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                provided, text embeddings will be generated from `prompt` input argument.
            negative_prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                argument.
            lora_scale (`float`, *optional*):
                A LoRA scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
            clip_skip (`int`, *optional*):
                Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
                the output of the pre-final layer will be used for computing the prompt embeddings.
        """
        # set lora scale so that monkey patched LoRA
        # function of text encoder can correctly access it
        if lora_scale is not None and isinstance(self, StableDiffusionLoraLoaderMixin):
            self._lora_scale = lora_scale

            # dynamically adjust the LoRA scale
            scale_lora_layers(self.text_encoder, lora_scale)

        if prompt is not None and isinstance(prompt, str):
            batch_size = 1
        elif prompt is not None and isinstance(prompt, list):
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        if prompt_embeds is None:
            # textual inversion: process multi-vector tokens if necessary
            if isinstance(self, TextualInversionLoaderMixin):
                prompt = self.maybe_convert_prompt(prompt, self.tokenizer)

            text_inputs = self.tokenizer(
                prompt,
                padding="max_length",
                max_length=self.tokenizer.model_max_length,
                truncation=True,
                return_tensors="np",
            )
            text_input_ids = text_inputs.input_ids
            untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="np").input_ids

            if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not np.array_equal(
                text_input_ids, untruncated_ids
            ):
                removed_text = self.tokenizer.batch_decode(untruncated_ids[:, self.tokenizer.model_max_length - 1 : -1])
                logger.warning(
                    "The following part of your input was truncated because CLIP can only handle sequences up to"
                    f" {self.tokenizer.model_max_length} tokens: {removed_text}"
                )

            if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
                attention_mask = ms.Tensor(text_inputs.attention_mask)
            else:
                attention_mask = None

            text_input_ids = ms.Tensor(text_input_ids)
            if clip_skip is None:
                prompt_embeds = self.text_encoder(text_input_ids, attention_mask=attention_mask)
                prompt_embeds = prompt_embeds[0]
            else:
                prompt_embeds = self.text_encoder(
                    text_input_ids, attention_mask=attention_mask, output_hidden_states=True
                )
                # Access the `hidden_states` first, that contains a tuple of
                # all the hidden states from the encoder layers. Then index into
                # the tuple to access the hidden states from the desired layer.
                prompt_embeds = prompt_embeds[-1][-(clip_skip + 1)]
                # We also need to apply the final LayerNorm here to not mess with the
                # representations. The `last_hidden_states` that we typically use for
                # obtaining the final prompt representations passes through the LayerNorm
                # layer.
                prompt_embeds = self.text_encoder.text_model.final_layer_norm(prompt_embeds)

        if self.text_encoder is not None:
            prompt_embeds_dtype = self.text_encoder.dtype
        elif self.unet is not None:
            prompt_embeds_dtype = self.unet.dtype
        else:
            prompt_embeds_dtype = prompt_embeds.dtype

        prompt_embeds = prompt_embeds.to(dtype=prompt_embeds_dtype)

        bs_embed, seq_len, _ = prompt_embeds.shape
        # duplicate text embeddings for each generation per prompt, using mps friendly method
        prompt_embeds = prompt_embeds.tile((1, num_images_per_prompt, 1))
        prompt_embeds = prompt_embeds.view(bs_embed * num_images_per_prompt, seq_len, -1)

        # get unconditional embeddings for classifier free guidance
        if do_classifier_free_guidance and negative_prompt_embeds is None:
            uncond_tokens: List[str]
            if negative_prompt is None:
                uncond_tokens = [""] * batch_size
            elif prompt is not None and type(prompt) is not type(negative_prompt):
                raise TypeError(
                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
                    f" {type(prompt)}."
                )
            elif isinstance(negative_prompt, str):
                uncond_tokens = [negative_prompt]
            elif batch_size != len(negative_prompt):
                raise ValueError(
                    f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
                    f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
                    " the batch size of `prompt`."
                )
            else:
                uncond_tokens = negative_prompt

            # textual inversion: process multi-vector tokens if necessary
            if isinstance(self, TextualInversionLoaderMixin):
                uncond_tokens = self.maybe_convert_prompt(uncond_tokens, self.tokenizer)

            max_length = prompt_embeds.shape[1]
            uncond_input = self.tokenizer(
                uncond_tokens,
                padding="max_length",
                max_length=max_length,
                truncation=True,
                return_tensors="np",
            )

            if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
                attention_mask = ms.Tensor(uncond_input.attention_mask)
            else:
                attention_mask = None

            negative_prompt_embeds = self.text_encoder(
                ms.Tensor(uncond_input.input_ids),
                attention_mask=attention_mask,
            )
            negative_prompt_embeds = negative_prompt_embeds[0]

        if do_classifier_free_guidance:
            # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
            seq_len = negative_prompt_embeds.shape[1]

            negative_prompt_embeds = negative_prompt_embeds.to(dtype=prompt_embeds_dtype)

            negative_prompt_embeds = negative_prompt_embeds.tile((1, num_images_per_prompt, 1))
            negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)

        if self.text_encoder is not None:
            if isinstance(self, StableDiffusionLoraLoaderMixin):
                # Retrieve the original scale by scaling back the LoRA layers
                unscale_lora_layers(self.text_encoder, lora_scale)

        return prompt_embeds, negative_prompt_embeds

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_image
    def encode_image(self, image, num_images_per_prompt, output_hidden_states=None):
        dtype = next(self.image_encoder.get_parameters()).dtype

        if not isinstance(image, ms.Tensor):
            image = self.feature_extractor(image, return_tensors="np").pixel_values
            image = ms.Tensor(image)

        image = image.to(dtype=dtype)
        if output_hidden_states:
            image_enc_hidden_states = self.image_encoder(image, output_hidden_states=True)[2][-2]
            image_enc_hidden_states = image_enc_hidden_states.repeat_interleave(num_images_per_prompt, dim=0)
            uncond_image_enc_hidden_states = self.image_encoder(ops.zeros_like(image), output_hidden_states=True)[2][-2]
            uncond_image_enc_hidden_states = uncond_image_enc_hidden_states.repeat_interleave(
                num_images_per_prompt, dim=0
            )
            return image_enc_hidden_states, uncond_image_enc_hidden_states
        else:
            image_embeds = self.image_encoder(image)[0]
            image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
            uncond_image_embeds = ops.zeros_like(image_embeds)

            return image_embeds, uncond_image_embeds

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_ip_adapter_image_embeds
    def prepare_ip_adapter_image_embeds(
        self, ip_adapter_image, ip_adapter_image_embeds, num_images_per_prompt, do_classifier_free_guidance
    ):
        image_embeds = []
        if do_classifier_free_guidance:
            negative_image_embeds = []
        if ip_adapter_image_embeds is None:
            if not isinstance(ip_adapter_image, list):
                ip_adapter_image = [ip_adapter_image]

            if len(ip_adapter_image) != len(self.unet.encoder_hid_proj.image_projection_layers):
                raise ValueError(
                    f"`ip_adapter_image` must have same length as the number of IP Adapters. Got"
                    f"{len(ip_adapter_image)} images and {len(self.unet.encoder_hid_proj.image_projection_layers)} IP"
                    f"Adapters."
                )

            for single_ip_adapter_image, image_proj_layer in zip(
                ip_adapter_image, self.unet.encoder_hid_proj.image_projection_layers
            ):
                output_hidden_state = not isinstance(image_proj_layer, ImageProjection)
                single_image_embeds, single_negative_image_embeds = self.encode_image(
                    single_ip_adapter_image, 1, output_hidden_state
                )

                image_embeds.append(single_image_embeds[None, :])
                if do_classifier_free_guidance:
                    negative_image_embeds.append(single_negative_image_embeds[None, :])
        else:
            for single_image_embeds in ip_adapter_image_embeds:
                if do_classifier_free_guidance:
                    single_negative_image_embeds, single_image_embeds = single_image_embeds.chunk(2)
                    negative_image_embeds.append(single_negative_image_embeds)
                image_embeds.append(single_image_embeds)

        ip_adapter_image_embeds = []
        for i, single_image_embeds in enumerate(image_embeds):
            single_image_embeds = ops.cat([single_image_embeds] * num_images_per_prompt, axis=0)
            if do_classifier_free_guidance:
                single_negative_image_embeds = ops.cat([negative_image_embeds[i]] * num_images_per_prompt, axis=0)
                single_image_embeds = ops.cat([single_negative_image_embeds, single_image_embeds], axis=0)

            ip_adapter_image_embeds.append(single_image_embeds)

        return ip_adapter_image_embeds

    # Copied from diffusers.pipelines.text_to_video_synthesis/pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
    def decode_latents(self, latents):
        latents = 1 / self.vae.config.scaling_factor * latents

        batch_size, channels, num_frames, height, width = latents.shape
        latents = latents.permute(0, 2, 1, 3, 4).reshape(batch_size * num_frames, channels, height, width)

        image = self.vae.decode(latents)[0]
        video = image[None, :].reshape((batch_size, num_frames, -1) + image.shape[2:]).permute(0, 2, 1, 3, 4)
        # we always cast to float32 as this does not cause significant overhead and is compatible with bfloat16
        video = video.float()
        return video

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
    def prepare_extra_step_kwargs(self, generator, eta):
        # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
        # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
        # and should be between [0, 1]

        accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
        extra_step_kwargs = {}
        if accepts_eta:
            extra_step_kwargs["eta"] = eta

        # check if the scheduler accepts generator
        accepts_generator = "generator" in set(inspect.signature(self.scheduler.step).parameters.keys())
        if accepts_generator:
            extra_step_kwargs["generator"] = generator
        return extra_step_kwargs

    def check_inputs(
        self,
        prompt,
        height,
        width,
        negative_prompt=None,
        prompt_embeds=None,
        negative_prompt_embeds=None,
        ip_adapter_image=None,
        ip_adapter_image_embeds=None,
        callback_on_step_end_tensor_inputs=None,
        image=None,
        controlnet_conditioning_scale: float = 1.0,
    ):
        if height % 8 != 0 or width % 8 != 0:
            raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")

        if callback_on_step_end_tensor_inputs is not None and not all(
            k in self._callback_tensor_inputs for k in callback_on_step_end_tensor_inputs
        ):
            raise ValueError(
                f"`callback_on_step_end_tensor_inputs` has to be in {self._callback_tensor_inputs}, but found"
                f"{[k for k in callback_on_step_end_tensor_inputs if k not in self._callback_tensor_inputs]}"
            )

        if prompt is not None and prompt_embeds is not None:
            raise ValueError(
                f"Cannot forward both `prompt`: {prompt} and `prompt_embeds`: {prompt_embeds}. Please make sure to"
                " only forward one of the two."
            )
        elif prompt is None and prompt_embeds is None:
            raise ValueError(
                "Provide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined."
            )
        elif prompt is not None and (not isinstance(prompt, str) and not isinstance(prompt, list)):
            raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")

        if negative_prompt is not None and negative_prompt_embeds is not None:
            raise ValueError(
                f"Cannot forward both `negative_prompt`: {negative_prompt} and `negative_prompt_embeds`:"
                f" {negative_prompt_embeds}. Please make sure to only forward one of the two."
            )

        if prompt_embeds is not None and negative_prompt_embeds is not None:
            if prompt_embeds.shape != negative_prompt_embeds.shape:
                raise ValueError(
                    "`prompt_embeds` and `negative_prompt_embeds` must have the same shape when passed directly, but"
                    f" got: `prompt_embeds` {prompt_embeds.shape} != `negative_prompt_embeds`"
                    f" {negative_prompt_embeds.shape}."
                )

        if ip_adapter_image is not None and ip_adapter_image_embeds is not None:
            raise ValueError(
                "Provide either `ip_adapter_image` or `ip_adapter_image_embeds`. Cannot leave both `ip_adapter_image` and `ip_adapter_image_embeds` defined."
            )

        if ip_adapter_image_embeds is not None:
            if not isinstance(ip_adapter_image_embeds, list):
                raise ValueError(
                    f"`ip_adapter_image_embeds` has to be of type `list` but is {type(ip_adapter_image_embeds)}"
                )
            elif ip_adapter_image_embeds[0].ndim not in [3, 4]:
                raise ValueError(
                    f"`ip_adapter_image_embeds` has to be a list of 3D or 4D tensors but is {ip_adapter_image_embeds[0].ndim}D"
                )

        # check `image`
        if isinstance(self.controlnet, SparseControlNetModel):
            if isinstance(image, list):
                for image_ in image:
                    self.check_image(image_, prompt, prompt_embeds)
            else:
                self.check_image(image, prompt, prompt_embeds)
        else:
            assert False

        # Check `controlnet_conditioning_scale`
        if isinstance(self.controlnet, SparseControlNetModel):
            if not isinstance(controlnet_conditioning_scale, float):
                raise TypeError("For single controlnet: `controlnet_conditioning_scale` must be type `float`.")
        else:
            assert False

    # Copied from diffusers.pipelines.controlnet.pipeline_controlnet.StableDiffusionControlNetPipeline.check_image
    def check_image(self, image, prompt, prompt_embeds):
        image_is_pil = isinstance(image, PIL.Image.Image)
        image_is_tensor = isinstance(image, ms.Tensor)
        image_is_np = isinstance(image, np.ndarray)
        image_is_pil_list = isinstance(image, list) and isinstance(image[0], PIL.Image.Image)
        image_is_tensor_list = isinstance(image, list) and isinstance(image[0], ms.Tensor)
        image_is_np_list = isinstance(image, list) and isinstance(image[0], np.ndarray)

        if (
            not image_is_pil
            and not image_is_tensor
            and not image_is_np
            and not image_is_pil_list
            and not image_is_tensor_list
            and not image_is_np_list
        ):
            raise TypeError(
                f"image must be passed and be one of PIL image, numpy array, mindspore tensor, list of PIL images, list"
                f"of numpy arrays or list of mindspore tensors, but is {type(image)}"
            )

        if image_is_pil:
            image_batch_size = 1
        else:
            image_batch_size = len(image)

        if prompt is not None and isinstance(prompt, str):
            prompt_batch_size = 1
        elif prompt is not None and isinstance(prompt, list):
            prompt_batch_size = len(prompt)
        elif prompt_embeds is not None:
            prompt_batch_size = prompt_embeds.shape[0]

        if image_batch_size != 1 and image_batch_size != prompt_batch_size:
            raise ValueError(
                f"If image batch size is not 1, image batch size must be same as prompt batch size. image batch size:"
                f"{image_batch_size}, prompt batch size: {prompt_batch_size}"
            )

    # Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.prepare_latents
    def prepare_latents(
        self, batch_size, num_channels_latents, num_frames, height, width, dtype, generator, latents=None
    ):
        shape = (
            batch_size,
            num_channels_latents,
            num_frames,
            height // self.vae_scale_factor,
            width // self.vae_scale_factor,
        )
        if isinstance(generator, list) and len(generator) != batch_size:
            raise ValueError(
                f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
                f" size of {batch_size}. Make sure the batch size matches the length of the generators."
            )

        if latents is None:
            latents = randn_tensor(shape, generator=generator, dtype=dtype)

        # scale the initial noise by the standard deviation required by the scheduler
        latents = latents * self.scheduler.init_noise_sigma
        return latents

    def prepare_image(self, image, width, height, dtype):
        image = self.control_image_processor.preprocess(image, height=height, width=width)
        controlnet_images = image.unsqueeze(0).to(dtype)
        batch_size, num_frames, channels, height, width = controlnet_images.shape

        # TODO: remove below line
        assert controlnet_images.min() >= 0 and controlnet_images.max() <= 1

        if self.controlnet.use_simplified_condition_embedding:
            controlnet_images = controlnet_images.reshape(batch_size * num_frames, channels, height, width)
            controlnet_images = 2 * controlnet_images - 1
            conditioning_frames = (
                retrieve_latents(self.vae, self.vae.encode(controlnet_images)[0]) * self.vae.config.scaling_factor
            )
            conditioning_frames = conditioning_frames.reshape(
                batch_size, num_frames, 4, height // self.vae_scale_factor, width // self.vae_scale_factor
            )
        else:
            conditioning_frames = controlnet_images

        conditioning_frames = conditioning_frames.permute(0, 2, 1, 3, 4)  # [b, c, f, h, w]
        return conditioning_frames

    def prepare_sparse_control_conditioning(
        self,
        conditioning_frames: ms.Tensor,
        num_frames: int,
        controlnet_frame_indices: int,
        dtype: ms.dtype,
    ) -> Tuple[ms.Tensor, ms.Tensor]:
        assert conditioning_frames.shape[2] >= len(controlnet_frame_indices)

        batch_size, channels, _, height, width = conditioning_frames.shape
        controlnet_cond = ops.zeros((batch_size, channels, num_frames, height, width), dtype=dtype)
        controlnet_cond_mask = ops.zeros((batch_size, 1, num_frames, height, width), dtype=dtype)
        controlnet_cond[:, :, controlnet_frame_indices] = conditioning_frames[:, :, : len(controlnet_frame_indices)]
        controlnet_cond_mask[:, :, controlnet_frame_indices] = 1

        return controlnet_cond, controlnet_cond_mask

    @property
    def guidance_scale(self):
        return self._guidance_scale

    @property
    def clip_skip(self):
        return self._clip_skip

    # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
    # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
    # corresponds to doing no classifier free guidance.
    @property
    def do_classifier_free_guidance(self):
        return self._guidance_scale > 1

    @property
    def cross_attention_kwargs(self):
        return self._cross_attention_kwargs

    @property
    def num_timesteps(self):
        return self._num_timesteps

    def __call__(
        self,
        prompt: Optional[Union[str, List[str]]] = None,
        height: Optional[int] = None,
        width: Optional[int] = None,
        num_frames: int = 16,
        num_inference_steps: int = 50,
        guidance_scale: float = 7.5,
        negative_prompt: Optional[Union[str, List[str]]] = None,
        num_videos_per_prompt: int = 1,
        eta: float = 0.0,
        generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
        latents: Optional[ms.Tensor] = None,
        prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        ip_adapter_image: Optional[PipelineImageInput] = None,
        ip_adapter_image_embeds: Optional[List[ms.Tensor]] = None,
        conditioning_frames: Optional[List[PipelineImageInput]] = None,
        output_type: str = "pil",
        return_dict: bool = False,
        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
        controlnet_conditioning_scale: Union[float, List[float]] = 1.0,
        controlnet_frame_indices: List[int] = [0],
        guess_mode: bool = False,
        clip_skip: Optional[int] = None,
        callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
    ):
        r"""
        The call function to the pipeline for generation.

        Args:
            prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`.
            height (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
                The height in pixels of the generated video.
            width (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
                The width in pixels of the generated video.
            num_frames (`int`, *optional*, defaults to 16):
                The number of video frames that are generated. Defaults to 16 frames which at 8 frames per seconds
                amounts to 2 seconds of video.
            num_inference_steps (`int`, *optional*, defaults to 50):
                The number of denoising steps. More denoising steps usually lead to a higher quality videos at the
                expense of slower inference.
            guidance_scale (`float`, *optional*, defaults to 7.5):
                A higher guidance scale value encourages the model to generate images closely linked to the text
                `prompt` at the expense of lower image quality. Guidance scale is enabled when `guidance_scale > 1`.
            negative_prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts to guide what to not include in image generation. If not defined, you need to
                pass `negative_prompt_embeds` instead. Ignored when not using guidance (`guidance_scale < 1`).
            eta (`float`, *optional*, defaults to 0.0):
                Corresponds to parameter eta (η) from the [DDIM](https://arxiv.org/abs/2010.02502) paper. Only applies
                to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
            generator (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
                A [`np.random.Generator`](https://numpy.org/doc/stable/reference/random/generator.html) to make
                generation deterministic.
            latents (`ms.Tensor`, *optional*):
                Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for video
                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                tensor is generated by sampling using the supplied random `generator`. Latents should be of shape
                `(batch_size, num_channel, num_frames, height, width)`.
            prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
                provided, text embeddings are generated from the `prompt` input argument.
            negative_prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
                not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
            ip_adapter_image: (`PipelineImageInput`, *optional*):
                Optional image input to work with IP Adapters.
            ip_adapter_image_embeds (`List[ms.Tensor]`, *optional*):
                Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
                IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should
                contain the negative image embedding if `do_classifier_free_guidance` is set to `True`. If not
                provided, embeddings are computed from the `ip_adapter_image` input argument.
            conditioning_frames (`List[PipelineImageInput]`, *optional*):
                The SparseControlNet input to provide guidance to the `unet` for generation.
            output_type (`str`, *optional*, defaults to `"pil"`):
                The output format of the generated video. Choose between `ms.Tensor`, `PIL.Image` or `np.array`.
            return_dict (`bool`, *optional*, defaults to `False`):
                Whether or not to return a [`~pipelines.text_to_video_synthesis.TextToVideoSDPipelineOutput`] instead
                of a plain tuple.
            cross_attention_kwargs (`dict`, *optional*):
                A kwargs dictionary that if specified is passed along to the [`AttentionProcessor`] as defined in
                [`self.processor`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
            controlnet_conditioning_scale (`float` or `List[float]`, *optional*, defaults to 1.0):
                The outputs of the ControlNet are multiplied by `controlnet_conditioning_scale` before they are added
                to the residual in the original `unet`. If multiple ControlNets are specified in `init`, you can set
                the corresponding scale as a list.
            controlnet_frame_indices (`List[int]`):
                The indices where the conditioning frames must be applied for generation. Multiple frames can be
                provided to guide the model to generate similar structure outputs, where the `unet` can
                "fill-in-the-gaps" for interpolation videos, or a single frame could be provided for general expected
                structure. Must have the same length as `conditioning_frames`.
            clip_skip (`int`, *optional*):
                Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
                the output of the pre-final layer will be used for computing the prompt embeddings.
            callback_on_step_end (`Callable`, *optional*):
                A function that calls at the end of each denoising steps during the inference. The function is called
                with the following arguments: `callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int,
                callback_kwargs: Dict)`. `callback_kwargs` will include a list of all tensors as specified by
                `callback_on_step_end_tensor_inputs`.
            callback_on_step_end_tensor_inputs (`List`, *optional*):
                The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
                will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
                `._callback_tensor_inputs` attribute of your pipeline class.

        Examples:

        Returns:
            [`~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput`] or `tuple`:
                If `return_dict` is `True`, [`~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput`] is
                returned, otherwise a `tuple` is returned where the first element is a list with the generated frames.
        """
        controlnet = self.controlnet

        # 0. Default height and width to unet
        height = height or self.unet.config.sample_size * self.vae_scale_factor
        width = width or self.unet.config.sample_size * self.vae_scale_factor
        num_videos_per_prompt = 1

        # 1. Check inputs. Raise error if not correct
        self.check_inputs(
            prompt=prompt,
            height=height,
            width=width,
            negative_prompt=negative_prompt,
            prompt_embeds=prompt_embeds,
            negative_prompt_embeds=negative_prompt_embeds,
            ip_adapter_image=ip_adapter_image,
            ip_adapter_image_embeds=ip_adapter_image_embeds,
            callback_on_step_end_tensor_inputs=callback_on_step_end_tensor_inputs,
            image=conditioning_frames,
            controlnet_conditioning_scale=controlnet_conditioning_scale,
        )

        self._guidance_scale = guidance_scale
        self._clip_skip = clip_skip
        self._cross_attention_kwargs = cross_attention_kwargs

        # 2. Define call parameters
        if prompt is not None and isinstance(prompt, str):
            batch_size = 1
        elif prompt is not None and isinstance(prompt, list):
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        global_pool_conditions = (
            controlnet.config.global_pool_conditions
            if isinstance(controlnet, SparseControlNetModel)
            else controlnet.nets[0].config.global_pool_conditions
        )
        guess_mode = guess_mode or global_pool_conditions

        # 3. Encode input prompt
        text_encoder_lora_scale = (
            self.cross_attention_kwargs.get("scale", None) if self.cross_attention_kwargs is not None else None
        )
        prompt_embeds, negative_prompt_embeds = self.encode_prompt(
            prompt,
            num_videos_per_prompt,
            self.do_classifier_free_guidance,
            negative_prompt,
            prompt_embeds=prompt_embeds,
            negative_prompt_embeds=negative_prompt_embeds,
            lora_scale=text_encoder_lora_scale,
            clip_skip=self.clip_skip,
        )
        # For classifier free guidance, we need to do two forward passes.
        # Here we concatenate the unconditional and text embeddings into a single batch
        # to avoid doing two forward passes
        if self.do_classifier_free_guidance:
            prompt_embeds = ops.cat([negative_prompt_embeds, prompt_embeds])

        # 4. Prepare IP-Adapter embeddings
        if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
            image_embeds = self.prepare_ip_adapter_image_embeds(
                ip_adapter_image,
                ip_adapter_image_embeds,
                batch_size * num_videos_per_prompt,
                self.do_classifier_free_guidance,
            )

        # 5. Prepare controlnet conditioning
        conditioning_frames = self.prepare_image(conditioning_frames, width, height, controlnet.dtype)
        controlnet_cond, controlnet_cond_mask = self.prepare_sparse_control_conditioning(
            conditioning_frames, num_frames, controlnet_frame_indices, controlnet.dtype
        )

        # 6. Prepare timesteps
        self.scheduler.set_timesteps(num_inference_steps)
        timesteps = self.scheduler.timesteps

        # 7. Prepare latent variables
        num_channels_latents = self.unet.config.in_channels
        latents = self.prepare_latents(
            batch_size * num_videos_per_prompt,
            num_channels_latents,
            num_frames,
            height,
            width,
            prompt_embeds.dtype,
            generator,
            latents,
        )

        # 8. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
        extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)

        # 9. Add image embeds for IP-Adapter
        added_cond_kwargs = (
            {"image_embeds": image_embeds}
            if ip_adapter_image is not None or ip_adapter_image_embeds is not None
            else None
        )

        self._num_timesteps = len(timesteps)
        num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order

        # 10. Denoising loop
        with self.progress_bar(total=self._num_timesteps) as progress_bar:
            for i, t in enumerate(timesteps):
                # expand the latents if we are doing classifier free guidance
                latent_model_input = ops.cat([latents] * 2) if self.do_classifier_free_guidance else latents
                latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)

                if guess_mode and self.do_classifier_free_guidance:
                    # Infer SparseControlNetModel only for the conditional batch.
                    control_model_input = latents
                    control_model_input = self.scheduler.scale_model_input(control_model_input, t)
                    controlnet_prompt_embeds = prompt_embeds.chunk(2)[1]
                else:
                    control_model_input = latent_model_input
                    controlnet_prompt_embeds = prompt_embeds

                down_block_res_samples, mid_block_res_sample = self.controlnet(
                    control_model_input,
                    t,
                    encoder_hidden_states=controlnet_prompt_embeds,
                    controlnet_cond=controlnet_cond,
                    conditioning_mask=controlnet_cond_mask,
                    conditioning_scale=controlnet_conditioning_scale,
                    guess_mode=guess_mode,
                    return_dict=False,
                )

                # predict the noise residual
                noise_pred = self.unet(
                    latent_model_input,
                    t,
                    encoder_hidden_states=prompt_embeds,
                    cross_attention_kwargs=cross_attention_kwargs,
                    added_cond_kwargs=ms.mutable(added_cond_kwargs) if added_cond_kwargs else added_cond_kwargs,
                    down_block_additional_residuals=ms.mutable(down_block_res_samples),
                    mid_block_additional_residual=mid_block_res_sample,
                )[0]

                # perform guidance
                if self.do_classifier_free_guidance:
                    noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
                    noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)

                # compute the previous noisy sample x_t -> x_t-1
                latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs)[0]

                if callback_on_step_end is not None:
                    callback_kwargs = {}
                    for k in callback_on_step_end_tensor_inputs:
                        callback_kwargs[k] = locals()[k]
                    callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)

                    latents = callback_outputs.pop("latents", latents)
                    prompt_embeds = callback_outputs.pop("prompt_embeds", prompt_embeds)
                    negative_prompt_embeds = callback_outputs.pop("negative_prompt_embeds", negative_prompt_embeds)

                # call the callback, if provided
                if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
                    progress_bar.update()

        # 11. Post processing
        if output_type == "latent":
            video = latents
        else:
            video_tensor = self.decode_latents(latents)
            video = self.video_processor.postprocess_video(video=video_tensor, output_type=output_type)

        if not return_dict:
            return (video,)

        return AnimateDiffPipelineOutput(frames=video)

mindone.diffusers.pipelines.AnimateDiffSparseControlNetPipeline.__call__(prompt=None, height=None, width=None, num_frames=16, num_inference_steps=50, guidance_scale=7.5, negative_prompt=None, num_videos_per_prompt=1, eta=0.0, generator=None, latents=None, prompt_embeds=None, negative_prompt_embeds=None, ip_adapter_image=None, ip_adapter_image_embeds=None, conditioning_frames=None, output_type='pil', return_dict=False, cross_attention_kwargs=None, controlnet_conditioning_scale=1.0, controlnet_frame_indices=[0], guess_mode=False, clip_skip=None, callback_on_step_end=None, callback_on_step_end_tensor_inputs=['latents'])

The call function to the pipeline for generation.

PARAMETER DESCRIPTION
prompt

The prompt or prompts to guide image generation. If not defined, you need to pass prompt_embeds.

TYPE: `str` or `List[str]`, *optional* DEFAULT: None

height

The height in pixels of the generated video.

TYPE: `int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor` DEFAULT: None

width

The width in pixels of the generated video.

TYPE: `int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor` DEFAULT: None

num_frames

The number of video frames that are generated. Defaults to 16 frames which at 8 frames per seconds amounts to 2 seconds of video.

TYPE: `int`, *optional*, defaults to 16 DEFAULT: 16

num_inference_steps

The number of denoising steps. More denoising steps usually lead to a higher quality videos at the expense of slower inference.

TYPE: `int`, *optional*, defaults to 50 DEFAULT: 50

guidance_scale

A higher guidance scale value encourages the model to generate images closely linked to the text prompt at the expense of lower image quality. Guidance scale is enabled when guidance_scale > 1.

TYPE: `float`, *optional*, defaults to 7.5 DEFAULT: 7.5

negative_prompt

The prompt or prompts to guide what to not include in image generation. If not defined, you need to pass negative_prompt_embeds instead. Ignored when not using guidance (guidance_scale < 1).

TYPE: `str` or `List[str]`, *optional* DEFAULT: None

eta

Corresponds to parameter eta (η) from the DDIM paper. Only applies to the [~schedulers.DDIMScheduler], and is ignored in other schedulers.

TYPE: `float`, *optional*, defaults to 0.0 DEFAULT: 0.0

generator

A np.random.Generator to make generation deterministic.

TYPE: `np.random.Generator` or `List[np.random.Generator]`, *optional* DEFAULT: None

latents

Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for video generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor is generated by sampling using the supplied random generator. Latents should be of shape (batch_size, num_channel, num_frames, height, width).

TYPE: `ms.Tensor`, *optional* DEFAULT: None

prompt_embeds

Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not provided, text embeddings are generated from the prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

negative_prompt_embeds

Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not provided, negative_prompt_embeds are generated from the negative_prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

ip_adapter_image

(PipelineImageInput, optional): Optional image input to work with IP Adapters.

TYPE: Optional[PipelineImageInput] DEFAULT: None

ip_adapter_image_embeds

Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of IP-adapters. Each element should be a tensor of shape (batch_size, num_images, emb_dim). It should contain the negative image embedding if do_classifier_free_guidance is set to True. If not provided, embeddings are computed from the ip_adapter_image input argument.

TYPE: `List[ms.Tensor]`, *optional* DEFAULT: None

conditioning_frames

The SparseControlNet input to provide guidance to the unet for generation.

TYPE: `List[PipelineImageInput]`, *optional* DEFAULT: None

output_type

The output format of the generated video. Choose between ms.Tensor, PIL.Image or np.array.

TYPE: `str`, *optional*, defaults to `"pil"` DEFAULT: 'pil'

return_dict

Whether or not to return a [~pipelines.text_to_video_synthesis.TextToVideoSDPipelineOutput] instead of a plain tuple.

TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False

cross_attention_kwargs

A kwargs dictionary that if specified is passed along to the [AttentionProcessor] as defined in self.processor.

TYPE: `dict`, *optional* DEFAULT: None

controlnet_conditioning_scale

The outputs of the ControlNet are multiplied by controlnet_conditioning_scale before they are added to the residual in the original unet. If multiple ControlNets are specified in init, you can set the corresponding scale as a list.

TYPE: `float` or `List[float]`, *optional*, defaults to 1.0 DEFAULT: 1.0

controlnet_frame_indices

The indices where the conditioning frames must be applied for generation. Multiple frames can be provided to guide the model to generate similar structure outputs, where the unet can "fill-in-the-gaps" for interpolation videos, or a single frame could be provided for general expected structure. Must have the same length as conditioning_frames.

TYPE: `List[int]` DEFAULT: [0]

clip_skip

Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that the output of the pre-final layer will be used for computing the prompt embeddings.

TYPE: `int`, *optional* DEFAULT: None

callback_on_step_end

A function that calls at the end of each denoising steps during the inference. The function is called with the following arguments: callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict). callback_kwargs will include a list of all tensors as specified by callback_on_step_end_tensor_inputs.

TYPE: `Callable`, *optional* DEFAULT: None

callback_on_step_end_tensor_inputs

The list of tensor inputs for the callback_on_step_end function. The tensors specified in the list will be passed as callback_kwargs argument. You will only be able to include variables listed in the ._callback_tensor_inputs attribute of your pipeline class.

TYPE: `List`, *optional* DEFAULT: ['latents']

RETURNS DESCRIPTION

[~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput] or tuple: If return_dict is True, [~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput] is returned, otherwise a tuple is returned where the first element is a list with the generated frames.
Source code in mindone/diffusers/pipelines/animatediff/pipeline_animatediff_sparsectrl.py 
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
def __call__(
    self,
    prompt: Optional[Union[str, List[str]]] = None,
    height: Optional[int] = None,
    width: Optional[int] = None,
    num_frames: int = 16,
    num_inference_steps: int = 50,
    guidance_scale: float = 7.5,
    negative_prompt: Optional[Union[str, List[str]]] = None,
    num_videos_per_prompt: int = 1,
    eta: float = 0.0,
    generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
    latents: Optional[ms.Tensor] = None,
    prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    ip_adapter_image: Optional[PipelineImageInput] = None,
    ip_adapter_image_embeds: Optional[List[ms.Tensor]] = None,
    conditioning_frames: Optional[List[PipelineImageInput]] = None,
    output_type: str = "pil",
    return_dict: bool = False,
    cross_attention_kwargs: Optional[Dict[str, Any]] = None,
    controlnet_conditioning_scale: Union[float, List[float]] = 1.0,
    controlnet_frame_indices: List[int] = [0],
    guess_mode: bool = False,
    clip_skip: Optional[int] = None,
    callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
    callback_on_step_end_tensor_inputs: List[str] = ["latents"],
):
    r"""
    The call function to the pipeline for generation.

    Args:
        prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`.
        height (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
            The height in pixels of the generated video.
        width (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
            The width in pixels of the generated video.
        num_frames (`int`, *optional*, defaults to 16):
            The number of video frames that are generated. Defaults to 16 frames which at 8 frames per seconds
            amounts to 2 seconds of video.
        num_inference_steps (`int`, *optional*, defaults to 50):
            The number of denoising steps. More denoising steps usually lead to a higher quality videos at the
            expense of slower inference.
        guidance_scale (`float`, *optional*, defaults to 7.5):
            A higher guidance scale value encourages the model to generate images closely linked to the text
            `prompt` at the expense of lower image quality. Guidance scale is enabled when `guidance_scale > 1`.
        negative_prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts to guide what to not include in image generation. If not defined, you need to
            pass `negative_prompt_embeds` instead. Ignored when not using guidance (`guidance_scale < 1`).
        eta (`float`, *optional*, defaults to 0.0):
            Corresponds to parameter eta (η) from the [DDIM](https://arxiv.org/abs/2010.02502) paper. Only applies
            to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
        generator (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
            A [`np.random.Generator`](https://numpy.org/doc/stable/reference/random/generator.html) to make
            generation deterministic.
        latents (`ms.Tensor`, *optional*):
            Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for video
            generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
            tensor is generated by sampling using the supplied random `generator`. Latents should be of shape
            `(batch_size, num_channel, num_frames, height, width)`.
        prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
            provided, text embeddings are generated from the `prompt` input argument.
        negative_prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
            not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
        ip_adapter_image: (`PipelineImageInput`, *optional*):
            Optional image input to work with IP Adapters.
        ip_adapter_image_embeds (`List[ms.Tensor]`, *optional*):
            Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
            IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should
            contain the negative image embedding if `do_classifier_free_guidance` is set to `True`. If not
            provided, embeddings are computed from the `ip_adapter_image` input argument.
        conditioning_frames (`List[PipelineImageInput]`, *optional*):
            The SparseControlNet input to provide guidance to the `unet` for generation.
        output_type (`str`, *optional*, defaults to `"pil"`):
            The output format of the generated video. Choose between `ms.Tensor`, `PIL.Image` or `np.array`.
        return_dict (`bool`, *optional*, defaults to `False`):
            Whether or not to return a [`~pipelines.text_to_video_synthesis.TextToVideoSDPipelineOutput`] instead
            of a plain tuple.
        cross_attention_kwargs (`dict`, *optional*):
            A kwargs dictionary that if specified is passed along to the [`AttentionProcessor`] as defined in
            [`self.processor`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
        controlnet_conditioning_scale (`float` or `List[float]`, *optional*, defaults to 1.0):
            The outputs of the ControlNet are multiplied by `controlnet_conditioning_scale` before they are added
            to the residual in the original `unet`. If multiple ControlNets are specified in `init`, you can set
            the corresponding scale as a list.
        controlnet_frame_indices (`List[int]`):
            The indices where the conditioning frames must be applied for generation. Multiple frames can be
            provided to guide the model to generate similar structure outputs, where the `unet` can
            "fill-in-the-gaps" for interpolation videos, or a single frame could be provided for general expected
            structure. Must have the same length as `conditioning_frames`.
        clip_skip (`int`, *optional*):
            Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
            the output of the pre-final layer will be used for computing the prompt embeddings.
        callback_on_step_end (`Callable`, *optional*):
            A function that calls at the end of each denoising steps during the inference. The function is called
            with the following arguments: `callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int,
            callback_kwargs: Dict)`. `callback_kwargs` will include a list of all tensors as specified by
            `callback_on_step_end_tensor_inputs`.
        callback_on_step_end_tensor_inputs (`List`, *optional*):
            The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
            will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
            `._callback_tensor_inputs` attribute of your pipeline class.

    Examples:

    Returns:
        [`~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput`] or `tuple`:
            If `return_dict` is `True`, [`~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput`] is
            returned, otherwise a `tuple` is returned where the first element is a list with the generated frames.
    """
    controlnet = self.controlnet

    # 0. Default height and width to unet
    height = height or self.unet.config.sample_size * self.vae_scale_factor
    width = width or self.unet.config.sample_size * self.vae_scale_factor
    num_videos_per_prompt = 1

    # 1. Check inputs. Raise error if not correct
    self.check_inputs(
        prompt=prompt,
        height=height,
        width=width,
        negative_prompt=negative_prompt,
        prompt_embeds=prompt_embeds,
        negative_prompt_embeds=negative_prompt_embeds,
        ip_adapter_image=ip_adapter_image,
        ip_adapter_image_embeds=ip_adapter_image_embeds,
        callback_on_step_end_tensor_inputs=callback_on_step_end_tensor_inputs,
        image=conditioning_frames,
        controlnet_conditioning_scale=controlnet_conditioning_scale,
    )

    self._guidance_scale = guidance_scale
    self._clip_skip = clip_skip
    self._cross_attention_kwargs = cross_attention_kwargs

    # 2. Define call parameters
    if prompt is not None and isinstance(prompt, str):
        batch_size = 1
    elif prompt is not None and isinstance(prompt, list):
        batch_size = len(prompt)
    else:
        batch_size = prompt_embeds.shape[0]

    global_pool_conditions = (
        controlnet.config.global_pool_conditions
        if isinstance(controlnet, SparseControlNetModel)
        else controlnet.nets[0].config.global_pool_conditions
    )
    guess_mode = guess_mode or global_pool_conditions

    # 3. Encode input prompt
    text_encoder_lora_scale = (
        self.cross_attention_kwargs.get("scale", None) if self.cross_attention_kwargs is not None else None
    )
    prompt_embeds, negative_prompt_embeds = self.encode_prompt(
        prompt,
        num_videos_per_prompt,
        self.do_classifier_free_guidance,
        negative_prompt,
        prompt_embeds=prompt_embeds,
        negative_prompt_embeds=negative_prompt_embeds,
        lora_scale=text_encoder_lora_scale,
        clip_skip=self.clip_skip,
    )
    # For classifier free guidance, we need to do two forward passes.
    # Here we concatenate the unconditional and text embeddings into a single batch
    # to avoid doing two forward passes
    if self.do_classifier_free_guidance:
        prompt_embeds = ops.cat([negative_prompt_embeds, prompt_embeds])

    # 4. Prepare IP-Adapter embeddings
    if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
        image_embeds = self.prepare_ip_adapter_image_embeds(
            ip_adapter_image,
            ip_adapter_image_embeds,
            batch_size * num_videos_per_prompt,
            self.do_classifier_free_guidance,
        )

    # 5. Prepare controlnet conditioning
    conditioning_frames = self.prepare_image(conditioning_frames, width, height, controlnet.dtype)
    controlnet_cond, controlnet_cond_mask = self.prepare_sparse_control_conditioning(
        conditioning_frames, num_frames, controlnet_frame_indices, controlnet.dtype
    )

    # 6. Prepare timesteps
    self.scheduler.set_timesteps(num_inference_steps)
    timesteps = self.scheduler.timesteps

    # 7. Prepare latent variables
    num_channels_latents = self.unet.config.in_channels
    latents = self.prepare_latents(
        batch_size * num_videos_per_prompt,
        num_channels_latents,
        num_frames,
        height,
        width,
        prompt_embeds.dtype,
        generator,
        latents,
    )

    # 8. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
    extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)

    # 9. Add image embeds for IP-Adapter
    added_cond_kwargs = (
        {"image_embeds": image_embeds}
        if ip_adapter_image is not None or ip_adapter_image_embeds is not None
        else None
    )

    self._num_timesteps = len(timesteps)
    num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order

    # 10. Denoising loop
    with self.progress_bar(total=self._num_timesteps) as progress_bar:
        for i, t in enumerate(timesteps):
            # expand the latents if we are doing classifier free guidance
            latent_model_input = ops.cat([latents] * 2) if self.do_classifier_free_guidance else latents
            latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)

            if guess_mode and self.do_classifier_free_guidance:
                # Infer SparseControlNetModel only for the conditional batch.
                control_model_input = latents
                control_model_input = self.scheduler.scale_model_input(control_model_input, t)
                controlnet_prompt_embeds = prompt_embeds.chunk(2)[1]
            else:
                control_model_input = latent_model_input
                controlnet_prompt_embeds = prompt_embeds

            down_block_res_samples, mid_block_res_sample = self.controlnet(
                control_model_input,
                t,
                encoder_hidden_states=controlnet_prompt_embeds,
                controlnet_cond=controlnet_cond,
                conditioning_mask=controlnet_cond_mask,
                conditioning_scale=controlnet_conditioning_scale,
                guess_mode=guess_mode,
                return_dict=False,
            )

            # predict the noise residual
            noise_pred = self.unet(
                latent_model_input,
                t,
                encoder_hidden_states=prompt_embeds,
                cross_attention_kwargs=cross_attention_kwargs,
                added_cond_kwargs=ms.mutable(added_cond_kwargs) if added_cond_kwargs else added_cond_kwargs,
                down_block_additional_residuals=ms.mutable(down_block_res_samples),
                mid_block_additional_residual=mid_block_res_sample,
            )[0]

            # perform guidance
            if self.do_classifier_free_guidance:
                noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
                noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)

            # compute the previous noisy sample x_t -> x_t-1
            latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs)[0]

            if callback_on_step_end is not None:
                callback_kwargs = {}
                for k in callback_on_step_end_tensor_inputs:
                    callback_kwargs[k] = locals()[k]
                callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)

                latents = callback_outputs.pop("latents", latents)
                prompt_embeds = callback_outputs.pop("prompt_embeds", prompt_embeds)
                negative_prompt_embeds = callback_outputs.pop("negative_prompt_embeds", negative_prompt_embeds)

            # call the callback, if provided
            if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
                progress_bar.update()

    # 11. Post processing
    if output_type == "latent":
        video = latents
    else:
        video_tensor = self.decode_latents(latents)
        video = self.video_processor.postprocess_video(video=video_tensor, output_type=output_type)

    if not return_dict:
        return (video,)

    return AnimateDiffPipelineOutput(frames=video)

mindone.diffusers.pipelines.AnimateDiffSparseControlNetPipeline.encode_prompt(prompt, num_images_per_prompt, do_classifier_free_guidance, negative_prompt=None, prompt_embeds=None, negative_prompt_embeds=None, lora_scale=None, clip_skip=None)

Encodes the prompt into text encoder hidden states.

PARAMETER DESCRIPTION
prompt

prompt to be encoded

TYPE: `str` or `List[str]`, *optional*

num_images_per_prompt

number of images that should be generated per prompt

TYPE: `int`

do_classifier_free_guidance

whether to use classifier free guidance or not

TYPE: `bool`

negative_prompt

The prompt or prompts not to guide the image generation. If not defined, one has to pass negative_prompt_embeds instead. Ignored when not using guidance (i.e., ignored if guidance_scale is less than 1).

TYPE: `str` or `List[str]`, *optional* DEFAULT: None

prompt_embeds

Pre-generated text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, text embeddings will be generated from prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

negative_prompt_embeds

Pre-generated negative text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, negative_prompt_embeds will be generated from negative_prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

lora_scale

A LoRA scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.

TYPE: `float`, *optional* DEFAULT: None

clip_skip

Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that the output of the pre-final layer will be used for computing the prompt embeddings.

TYPE: `int`, *optional* DEFAULT: None

Source code in mindone/diffusers/pipelines/animatediff/pipeline_animatediff_sparsectrl.py 
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
def encode_prompt(
    self,
    prompt,
    num_images_per_prompt,
    do_classifier_free_guidance,
    negative_prompt=None,
    prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    lora_scale: Optional[float] = None,
    clip_skip: Optional[int] = None,
):
    r"""
    Encodes the prompt into text encoder hidden states.

    Args:
        prompt (`str` or `List[str]`, *optional*):
            prompt to be encoded
        num_images_per_prompt (`int`):
            number of images that should be generated per prompt
        do_classifier_free_guidance (`bool`):
            whether to use classifier free guidance or not
        negative_prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts not to guide the image generation. If not defined, one has to pass
            `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
            less than `1`).
        prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
            provided, text embeddings will be generated from `prompt` input argument.
        negative_prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
            weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
            argument.
        lora_scale (`float`, *optional*):
            A LoRA scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
        clip_skip (`int`, *optional*):
            Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
            the output of the pre-final layer will be used for computing the prompt embeddings.
    """
    # set lora scale so that monkey patched LoRA
    # function of text encoder can correctly access it
    if lora_scale is not None and isinstance(self, StableDiffusionLoraLoaderMixin):
        self._lora_scale = lora_scale

        # dynamically adjust the LoRA scale
        scale_lora_layers(self.text_encoder, lora_scale)

    if prompt is not None and isinstance(prompt, str):
        batch_size = 1
    elif prompt is not None and isinstance(prompt, list):
        batch_size = len(prompt)
    else:
        batch_size = prompt_embeds.shape[0]

    if prompt_embeds is None:
        # textual inversion: process multi-vector tokens if necessary
        if isinstance(self, TextualInversionLoaderMixin):
            prompt = self.maybe_convert_prompt(prompt, self.tokenizer)

        text_inputs = self.tokenizer(
            prompt,
            padding="max_length",
            max_length=self.tokenizer.model_max_length,
            truncation=True,
            return_tensors="np",
        )
        text_input_ids = text_inputs.input_ids
        untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="np").input_ids

        if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not np.array_equal(
            text_input_ids, untruncated_ids
        ):
            removed_text = self.tokenizer.batch_decode(untruncated_ids[:, self.tokenizer.model_max_length - 1 : -1])
            logger.warning(
                "The following part of your input was truncated because CLIP can only handle sequences up to"
                f" {self.tokenizer.model_max_length} tokens: {removed_text}"
            )

        if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
            attention_mask = ms.Tensor(text_inputs.attention_mask)
        else:
            attention_mask = None

        text_input_ids = ms.Tensor(text_input_ids)
        if clip_skip is None:
            prompt_embeds = self.text_encoder(text_input_ids, attention_mask=attention_mask)
            prompt_embeds = prompt_embeds[0]
        else:
            prompt_embeds = self.text_encoder(
                text_input_ids, attention_mask=attention_mask, output_hidden_states=True
            )
            # Access the `hidden_states` first, that contains a tuple of
            # all the hidden states from the encoder layers. Then index into
            # the tuple to access the hidden states from the desired layer.
            prompt_embeds = prompt_embeds[-1][-(clip_skip + 1)]
            # We also need to apply the final LayerNorm here to not mess with the
            # representations. The `last_hidden_states` that we typically use for
            # obtaining the final prompt representations passes through the LayerNorm
            # layer.
            prompt_embeds = self.text_encoder.text_model.final_layer_norm(prompt_embeds)

    if self.text_encoder is not None:
        prompt_embeds_dtype = self.text_encoder.dtype
    elif self.unet is not None:
        prompt_embeds_dtype = self.unet.dtype
    else:
        prompt_embeds_dtype = prompt_embeds.dtype

    prompt_embeds = prompt_embeds.to(dtype=prompt_embeds_dtype)

    bs_embed, seq_len, _ = prompt_embeds.shape
    # duplicate text embeddings for each generation per prompt, using mps friendly method
    prompt_embeds = prompt_embeds.tile((1, num_images_per_prompt, 1))
    prompt_embeds = prompt_embeds.view(bs_embed * num_images_per_prompt, seq_len, -1)

    # get unconditional embeddings for classifier free guidance
    if do_classifier_free_guidance and negative_prompt_embeds is None:
        uncond_tokens: List[str]
        if negative_prompt is None:
            uncond_tokens = [""] * batch_size
        elif prompt is not None and type(prompt) is not type(negative_prompt):
            raise TypeError(
                f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
                f" {type(prompt)}."
            )
        elif isinstance(negative_prompt, str):
            uncond_tokens = [negative_prompt]
        elif batch_size != len(negative_prompt):
            raise ValueError(
                f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
                f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
                " the batch size of `prompt`."
            )
        else:
            uncond_tokens = negative_prompt

        # textual inversion: process multi-vector tokens if necessary
        if isinstance(self, TextualInversionLoaderMixin):
            uncond_tokens = self.maybe_convert_prompt(uncond_tokens, self.tokenizer)

        max_length = prompt_embeds.shape[1]
        uncond_input = self.tokenizer(
            uncond_tokens,
            padding="max_length",
            max_length=max_length,
            truncation=True,
            return_tensors="np",
        )

        if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
            attention_mask = ms.Tensor(uncond_input.attention_mask)
        else:
            attention_mask = None

        negative_prompt_embeds = self.text_encoder(
            ms.Tensor(uncond_input.input_ids),
            attention_mask=attention_mask,
        )
        negative_prompt_embeds = negative_prompt_embeds[0]

    if do_classifier_free_guidance:
        # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
        seq_len = negative_prompt_embeds.shape[1]

        negative_prompt_embeds = negative_prompt_embeds.to(dtype=prompt_embeds_dtype)

        negative_prompt_embeds = negative_prompt_embeds.tile((1, num_images_per_prompt, 1))
        negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)

    if self.text_encoder is not None:
        if isinstance(self, StableDiffusionLoraLoaderMixin):
            # Retrieve the original scale by scaling back the LoRA layers
            unscale_lora_layers(self.text_encoder, lora_scale)

    return prompt_embeds, negative_prompt_embeds

mindone.diffusers.pipelines.AnimateDiffSDXLPipeline

Bases: DiffusionPipeline, StableDiffusionMixin, FromSingleFileMixin, StableDiffusionXLLoraLoaderMixin, TextualInversionLoaderMixin, IPAdapterMixin

Pipeline for text-to-video generation using Stable Diffusion XL.

This model inherits from [DiffusionPipeline]. Check the superclass documentation for the generic methods the library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)

The pipeline also inherits the following loading methods
  • [~loaders.TextualInversionLoaderMixin.load_textual_inversion] for loading textual inversion embeddings
  • [~loaders.FromSingleFileMixin.from_single_file] for loading .ckpt files
  • [~loaders.StableDiffusionXLLoraLoaderMixin.load_lora_weights] for loading LoRA weights
  • [~loaders.StableDiffusionXLLoraLoaderMixin.save_lora_weights] for saving LoRA weights
  • [~loaders.IPAdapterMixin.load_ip_adapter] for loading IP Adapters
PARAMETER DESCRIPTION
vae

Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.

TYPE: [`AutoencoderKL`]

text_encoder

Frozen text-encoder. Stable Diffusion XL uses the text portion of CLIP, specifically the clip-vit-large-patch14 variant.

TYPE: [`CLIPTextModel`]

text_encoder_2

Second frozen text-encoder. Stable Diffusion XL uses the text and pool portion of CLIP, specifically the laion/CLIP-ViT-bigG-14-laion2B-39B-b160k variant.

TYPE: [` CLIPTextModelWithProjection`]

tokenizer

Tokenizer of class CLIPTokenizer.

TYPE: `CLIPTokenizer`

tokenizer_2

Second Tokenizer of class CLIPTokenizer.

TYPE: `CLIPTokenizer`

unet

Conditional U-Net architecture to denoise the encoded image latents.

TYPE: [`UNet2DConditionModel`]

scheduler

A scheduler to be used in combination with unet to denoise the encoded image latents. Can be one of [DDIMScheduler], [LMSDiscreteScheduler], or [PNDMScheduler].

TYPE: [`SchedulerMixin`]

force_zeros_for_empty_prompt

Whether the negative prompt embeddings shall be forced to always be set to 0. Also see the config of stabilityai/stable-diffusion-xl-base-1-0.

TYPE: `bool`, *optional*, defaults to `"True"` DEFAULT: True

Source code in mindone/diffusers/pipelines/animatediff/pipeline_animatediff_sdxl.py 
 171
 172
 173
 174
 175
 176
 177
 178
 179
 180
 181
 182
 183
 184
 185
 186
 187
 188
 189
 190
 191
 192
 193
 194
 195
 196
 197
 198
 199
 200
 201
 202
 203
 204
 205
 206
 207
 208
 209
 210
 211
 212
 213
 214
 215
 216
 217
 218
 219
 220
 221
 222
 223
 224
 225
 226
 227
 228
 229
 230
 231
 232
 233
 234
 235
 236
 237
 238
 239
 240
 241
 242
 243
 244
 245
 246
 247
 248
 249
 250
 251
 252
 253
 254
 255
 256
 257
 258
 259
 260
 261
 262
 263
 264
 265
 266
 267
 268
 269
 270
 271
 272
 273
 274
 275
 276
 277
 278
 279
 280
 281
 282
 283
 284
 285
 286
 287
 288
 289
 290
 291
 292
 293
 294
 295
 296
 297
 298
 299
 300
 301
 302
 303
 304
 305
 306
 307
 308
 309
 310
 311
 312
 313
 314
 315
 316
 317
 318
 319
 320
 321
 322
 323
 324
 325
 326
 327
 328
 329
 330
 331
 332
 333
 334
 335
 336
 337
 338
 339
 340
 341
 342
 343
 344
 345
 346
 347
 348
 349
 350
 351
 352
 353
 354
 355
 356
 357
 358
 359
 360
 361
 362
 363
 364
 365
 366
 367
 368
 369
 370
 371
 372
 373
 374
 375
 376
 377
 378
 379
 380
 381
 382
 383
 384
 385
 386
 387
 388
 389
 390
 391
 392
 393
 394
 395
 396
 397
 398
 399
 400
 401
 402
 403
 404
 405
 406
 407
 408
 409
 410
 411
 412
 413
 414
 415
 416
 417
 418
 419
 420
 421
 422
 423
 424
 425
 426
 427
 428
 429
 430
 431
 432
 433
 434
 435
 436
 437
 438
 439
 440
 441
 442
 443
 444
 445
 446
 447
 448
 449
 450
 451
 452
 453
 454
 455
 456
 457
 458
 459
 460
 461
 462
 463
 464
 465
 466
 467
 468
 469
 470
 471
 472
 473
 474
 475
 476
 477
 478
 479
 480
 481
 482
 483
 484
 485
 486
 487
 488
 489
 490
 491
 492
 493
 494
 495
 496
 497
 498
 499
 500
 501
 502
 503
 504
 505
 506
 507
 508
 509
 510
 511
 512
 513
 514
 515
 516
 517
 518
 519
 520
 521
 522
 523
 524
 525
 526
 527
 528
 529
 530
 531
 532
 533
 534
 535
 536
 537
 538
 539
 540
 541
 542
 543
 544
 545
 546
 547
 548
 549
 550
 551
 552
 553
 554
 555
 556
 557
 558
 559
 560
 561
 562
 563
 564
 565
 566
 567
 568
 569
 570
 571
 572
 573
 574
 575
 576
 577
 578
 579
 580
 581
 582
 583
 584
 585
 586
 587
 588
 589
 590
 591
 592
 593
 594
 595
 596
 597
 598
 599
 600
 601
 602
 603
 604
 605
 606
 607
 608
 609
 610
 611
 612
 613
 614
 615
 616
 617
 618
 619
 620
 621
 622
 623
 624
 625
 626
 627
 628
 629
 630
 631
 632
 633
 634
 635
 636
 637
 638
 639
 640
 641
 642
 643
 644
 645
 646
 647
 648
 649
 650
 651
 652
 653
 654
 655
 656
 657
 658
 659
 660
 661
 662
 663
 664
 665
 666
 667
 668
 669
 670
 671
 672
 673
 674
 675
 676
 677
 678
 679
 680
 681
 682
 683
 684
 685
 686
 687
 688
 689
 690
 691
 692
 693
 694
 695
 696
 697
 698
 699
 700
 701
 702
 703
 704
 705
 706
 707
 708
 709
 710
 711
 712
 713
 714
 715
 716
 717
 718
 719
 720
 721
 722
 723
 724
 725
 726
 727
 728
 729
 730
 731
 732
 733
 734
 735
 736
 737
 738
 739
 740
 741
 742
 743
 744
 745
 746
 747
 748
 749
 750
 751
 752
 753
 754
 755
 756
 757
 758
 759
 760
 761
 762
 763
 764
 765
 766
 767
 768
 769
 770
 771
 772
 773
 774
 775
 776
 777
 778
 779
 780
 781
 782
 783
 784
 785
 786
 787
 788
 789
 790
 791
 792
 793
 794
 795
 796
 797
 798
 799
 800
 801
 802
 803
 804
 805
 806
 807
 808
 809
 810
 811
 812
 813
 814
 815
 816
 817
 818
 819
 820
 821
 822
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
class AnimateDiffSDXLPipeline(
    DiffusionPipeline,
    StableDiffusionMixin,
    FromSingleFileMixin,
    StableDiffusionXLLoraLoaderMixin,
    TextualInversionLoaderMixin,
    IPAdapterMixin,
):
    r"""
    Pipeline for text-to-video generation using Stable Diffusion XL.

    This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods the
    library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)

    The pipeline also inherits the following loading methods:
        - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
        - [`~loaders.FromSingleFileMixin.from_single_file`] for loading `.ckpt` files
        - [`~loaders.StableDiffusionXLLoraLoaderMixin.load_lora_weights`] for loading LoRA weights
        - [`~loaders.StableDiffusionXLLoraLoaderMixin.save_lora_weights`] for saving LoRA weights
        - [`~loaders.IPAdapterMixin.load_ip_adapter`] for loading IP Adapters

    Args:
        vae ([`AutoencoderKL`]):
            Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
        text_encoder ([`CLIPTextModel`]):
            Frozen text-encoder. Stable Diffusion XL uses the text portion of
            [CLIP](https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModel), specifically
            the [clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) variant.
        text_encoder_2 ([` CLIPTextModelWithProjection`]):
            Second frozen text-encoder. Stable Diffusion XL uses the text and pool portion of
            [CLIP](https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModelWithProjection),
            specifically the
            [laion/CLIP-ViT-bigG-14-laion2B-39B-b160k](https://huggingface.co/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k)
            variant.
        tokenizer (`CLIPTokenizer`):
            Tokenizer of class
            [CLIPTokenizer](https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer).
        tokenizer_2 (`CLIPTokenizer`):
            Second Tokenizer of class
            [CLIPTokenizer](https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer).
        unet ([`UNet2DConditionModel`]):
            Conditional U-Net architecture to denoise the encoded image latents.
        scheduler ([`SchedulerMixin`]):
            A scheduler to be used in combination with `unet` to denoise the encoded image latents. Can be one of
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        force_zeros_for_empty_prompt (`bool`, *optional*, defaults to `"True"`):
            Whether the negative prompt embeddings shall be forced to always be set to 0. Also see the config of
            `stabilityai/stable-diffusion-xl-base-1-0`.
    """

    model_cpu_offload_seq = "text_encoder->text_encoder_2->image_encoder->unet->vae"
    _optional_components = [
        "tokenizer",
        "tokenizer_2",
        "text_encoder",
        "text_encoder_2",
        "image_encoder",
        "feature_extractor",
    ]
    _callback_tensor_inputs = [
        "latents",
        "prompt_embeds",
        "negative_prompt_embeds",
        "add_text_embeds",
        "add_time_ids",
        "negative_pooled_prompt_embeds",
        "negative_add_time_ids",
    ]

    def __init__(
        self,
        vae: AutoencoderKL,
        text_encoder: CLIPTextModel,
        text_encoder_2: CLIPTextModelWithProjection,
        tokenizer: CLIPTokenizer,
        tokenizer_2: CLIPTokenizer,
        unet: Union[UNet2DConditionModel, UNetMotionModel],
        motion_adapter: MotionAdapter,
        scheduler: Union[
            DDIMScheduler,
            PNDMScheduler,
            LMSDiscreteScheduler,
            EulerDiscreteScheduler,
            EulerAncestralDiscreteScheduler,
            DPMSolverMultistepScheduler,
        ],
        image_encoder: CLIPVisionModelWithProjection = None,
        feature_extractor: CLIPImageProcessor = None,
        force_zeros_for_empty_prompt: bool = True,
    ):
        super().__init__()

        if isinstance(unet, UNet2DConditionModel):
            unet = UNetMotionModel.from_unet2d(unet, motion_adapter)

        self.register_modules(
            vae=vae,
            text_encoder=text_encoder,
            text_encoder_2=text_encoder_2,
            tokenizer=tokenizer,
            tokenizer_2=tokenizer_2,
            unet=unet,
            motion_adapter=motion_adapter,
            scheduler=scheduler,
            image_encoder=image_encoder,
            feature_extractor=feature_extractor,
        )
        self.register_to_config(force_zeros_for_empty_prompt=force_zeros_for_empty_prompt)
        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
        self.video_processor = VideoProcessor(vae_scale_factor=self.vae_scale_factor)

        self.default_sample_size = self.unet.config.sample_size

    # Copied from diffusers.pipelines.stable_diffusion_xl.pipeline_stable_diffusion_xl.StableDiffusionXLPipeline.encode_prompt with num_images_per_prompt->num_videos_per_prompt  # noqa E501
    def encode_prompt(
        self,
        prompt: str,
        prompt_2: Optional[str] = None,
        num_videos_per_prompt: int = 1,
        do_classifier_free_guidance: bool = True,
        negative_prompt: Optional[str] = None,
        negative_prompt_2: Optional[str] = None,
        prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        pooled_prompt_embeds: Optional[ms.Tensor] = None,
        negative_pooled_prompt_embeds: Optional[ms.Tensor] = None,
        lora_scale: Optional[float] = None,
        clip_skip: Optional[int] = None,
    ):
        r"""
        Encodes the prompt into text encoder hidden states.

        Args:
            prompt (`str` or `List[str]`, *optional*):
                prompt to be encoded
            prompt_2 (`str` or `List[str]`, *optional*):
                The prompt or prompts to be sent to the `tokenizer_2` and `text_encoder_2`. If not defined, `prompt` is
                used in both text-encoders
            num_videos_per_prompt (`int`):
                number of images that should be generated per prompt
            do_classifier_free_guidance (`bool`):
                whether to use classifier free guidance or not
            negative_prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts not to guide the image generation. If not defined, one has to pass
                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
                less than `1`).
            negative_prompt_2 (`str` or `List[str]`, *optional*):
                The prompt or prompts not to guide the image generation to be sent to `tokenizer_2` and
                `text_encoder_2`. If not defined, `negative_prompt` is used in both text-encoders
            prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                provided, text embeddings will be generated from `prompt` input argument.
            negative_prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                argument.
            pooled_prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
                If not provided, pooled text embeddings will be generated from `prompt` input argument.
            negative_pooled_prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_prompt`
                input argument.
            lora_scale (`float`, *optional*):
                A lora scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
            clip_skip (`int`, *optional*):
                Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
                the output of the pre-final layer will be used for computing the prompt embeddings.
        """

        # set lora scale so that monkey patched LoRA
        # function of text encoder can correctly access it
        if lora_scale is not None and isinstance(self, StableDiffusionXLLoraLoaderMixin):
            self._lora_scale = lora_scale

            # dynamically adjust the LoRA scale
            if self.text_encoder is not None:
                scale_lora_layers(self.text_encoder, lora_scale)

            if self.text_encoder_2 is not None:
                scale_lora_layers(self.text_encoder_2, lora_scale)

        prompt = [prompt] if isinstance(prompt, str) else prompt

        if prompt is not None:
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        # Define tokenizers and text encoders
        tokenizers = [self.tokenizer, self.tokenizer_2] if self.tokenizer is not None else [self.tokenizer_2]
        text_encoders = (
            [self.text_encoder, self.text_encoder_2] if self.text_encoder is not None else [self.text_encoder_2]
        )

        if prompt_embeds is None:
            prompt_2 = prompt_2 or prompt
            prompt_2 = [prompt_2] if isinstance(prompt_2, str) else prompt_2

            # textual inversion: process multi-vector tokens if necessary
            prompt_embeds_list = []
            prompts = [prompt, prompt_2]
            for prompt, tokenizer, text_encoder in zip(prompts, tokenizers, text_encoders):
                if isinstance(self, TextualInversionLoaderMixin):
                    prompt = self.maybe_convert_prompt(prompt, tokenizer)

                text_inputs = tokenizer(
                    prompt,
                    padding="max_length",
                    max_length=tokenizer.model_max_length,
                    truncation=True,
                    return_tensors="np",
                )

                text_input_ids = text_inputs.input_ids
                untruncated_ids = tokenizer(prompt, padding="longest", return_tensors="np").input_ids

                if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not np.array_equal(
                    text_input_ids, untruncated_ids
                ):
                    removed_text = tokenizer.batch_decode(untruncated_ids[:, tokenizer.model_max_length - 1 : -1])
                    logger.warning(
                        "The following part of your input was truncated because CLIP can only handle sequences up to"
                        f" {tokenizer.model_max_length} tokens: {removed_text}"
                    )

                prompt_embeds = text_encoder(ms.tensor(text_input_ids), output_hidden_states=True)

                # We are only ALWAYS interested in the pooled output of the final text encoder
                pooled_prompt_embeds = prompt_embeds[0]
                if clip_skip is None:
                    prompt_embeds = prompt_embeds[2][-2]
                else:
                    # "2" because SDXL always indexes from the penultimate layer.
                    prompt_embeds = prompt_embeds[2][-(clip_skip + 2)]

                prompt_embeds_list.append(prompt_embeds)

            prompt_embeds = ops.concat(prompt_embeds_list, axis=-1)

        # get unconditional embeddings for classifier free guidance
        zero_out_negative_prompt = negative_prompt is None and self.config.force_zeros_for_empty_prompt
        if do_classifier_free_guidance and negative_prompt_embeds is None and zero_out_negative_prompt:
            negative_prompt_embeds = ops.zeros_like(prompt_embeds)
            negative_pooled_prompt_embeds = ops.zeros_like(pooled_prompt_embeds)
        elif do_classifier_free_guidance and negative_prompt_embeds is None:
            negative_prompt = negative_prompt or ""
            negative_prompt_2 = negative_prompt_2 or negative_prompt

            # normalize str to list
            negative_prompt = batch_size * [negative_prompt] if isinstance(negative_prompt, str) else negative_prompt
            negative_prompt_2 = (
                batch_size * [negative_prompt_2] if isinstance(negative_prompt_2, str) else negative_prompt_2
            )

            uncond_tokens: List[str]
            if prompt is not None and type(prompt) is not type(negative_prompt):
                raise TypeError(
                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
                    f" {type(prompt)}."
                )
            elif batch_size != len(negative_prompt):
                raise ValueError(
                    f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
                    f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
                    " the batch size of `prompt`."
                )
            else:
                uncond_tokens = [negative_prompt, negative_prompt_2]

            negative_prompt_embeds_list = []
            for negative_prompt, tokenizer, text_encoder in zip(uncond_tokens, tokenizers, text_encoders):
                if isinstance(self, TextualInversionLoaderMixin):
                    negative_prompt = self.maybe_convert_prompt(negative_prompt, tokenizer)

                max_length = prompt_embeds.shape[1]
                uncond_input = tokenizer(
                    negative_prompt,
                    padding="max_length",
                    max_length=max_length,
                    truncation=True,
                    return_tensors="np",
                )

                negative_prompt_embeds = text_encoder(
                    ms.Tensor.from_numpy(uncond_input.input_ids),
                    output_hidden_states=True,
                )
                # We are only ALWAYS interested in the pooled output of the final text encoder
                negative_pooled_prompt_embeds = negative_prompt_embeds[0]
                negative_prompt_embeds = negative_prompt_embeds[2][-2]

                negative_prompt_embeds_list.append(negative_prompt_embeds)

            negative_prompt_embeds = ops.concat(negative_prompt_embeds_list, axis=-1)

        if self.text_encoder_2 is not None:
            prompt_embeds = prompt_embeds.to(dtype=self.text_encoder_2.dtype)
        else:
            prompt_embeds = prompt_embeds.to(dtype=self.unet.dtype)

        bs_embed, seq_len, _ = prompt_embeds.shape
        # duplicate text embeddings for each generation per prompt, using mps friendly method
        prompt_embeds = prompt_embeds.tile((1, num_videos_per_prompt, 1))
        prompt_embeds = prompt_embeds.view(bs_embed * num_videos_per_prompt, seq_len, -1)

        if do_classifier_free_guidance:
            # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
            seq_len = negative_prompt_embeds.shape[1]

            if self.text_encoder_2 is not None:
                negative_prompt_embeds = negative_prompt_embeds.to(dtype=self.text_encoder_2.dtype)
            else:
                negative_prompt_embeds = negative_prompt_embeds.to(dtype=self.unet.dtype)

            negative_prompt_embeds = negative_prompt_embeds.tile((1, num_videos_per_prompt, 1))
            negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_videos_per_prompt, seq_len, -1)

        pooled_prompt_embeds = pooled_prompt_embeds.tile((1, num_videos_per_prompt)).view(
            bs_embed * num_videos_per_prompt, -1
        )
        if do_classifier_free_guidance:
            negative_pooled_prompt_embeds = negative_pooled_prompt_embeds.tile((1, num_videos_per_prompt)).view(
                bs_embed * num_videos_per_prompt, -1
            )

        if self.text_encoder is not None:
            if isinstance(self, StableDiffusionXLLoraLoaderMixin):
                # Retrieve the original scale by scaling back the LoRA layers
                unscale_lora_layers(self.text_encoder, lora_scale)

        if self.text_encoder_2 is not None:
            if isinstance(self, StableDiffusionXLLoraLoaderMixin):
                # Retrieve the original scale by scaling back the LoRA layers
                unscale_lora_layers(self.text_encoder_2, lora_scale)

        return prompt_embeds, negative_prompt_embeds, pooled_prompt_embeds, negative_pooled_prompt_embeds

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_image
    def encode_image(self, image, num_images_per_prompt, output_hidden_states=None):
        dtype = next(self.image_encoder.get_parameters()).dtype

        if not isinstance(image, ms.Tensor):
            image = self.feature_extractor(image, return_tensors="np").pixel_values
            image = ms.Tensor(image)

        image = image.to(dtype=dtype)
        if output_hidden_states:
            image_enc_hidden_states = self.image_encoder(image, output_hidden_states=True)[2][-2]
            image_enc_hidden_states = image_enc_hidden_states.repeat_interleave(num_images_per_prompt, dim=0)
            uncond_image_enc_hidden_states = self.image_encoder(ops.zeros_like(image), output_hidden_states=True)[2][-2]
            uncond_image_enc_hidden_states = uncond_image_enc_hidden_states.repeat_interleave(
                num_images_per_prompt, dim=0
            )
            return image_enc_hidden_states, uncond_image_enc_hidden_states
        else:
            image_embeds = self.image_encoder(image)[0]
            image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
            uncond_image_embeds = ops.zeros_like(image_embeds)

            return image_embeds, uncond_image_embeds

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_ip_adapter_image_embeds
    def prepare_ip_adapter_image_embeds(
        self, ip_adapter_image, ip_adapter_image_embeds, num_images_per_prompt, do_classifier_free_guidance
    ):
        if ip_adapter_image_embeds is None:
            if not isinstance(ip_adapter_image, list):
                ip_adapter_image = [ip_adapter_image]

            if len(ip_adapter_image) != len(self.unet.encoder_hid_proj.image_projection_layers):
                raise ValueError(
                    f"`ip_adapter_image` must have same length as the number of IP Adapters. Got {len(ip_adapter_image)} images and {len(self.unet.encoder_hid_proj.image_projection_layers)} IP Adapters."  # noqa: E501
                )

            image_embeds = []
            for single_ip_adapter_image, image_proj_layer in zip(
                ip_adapter_image, self.unet.encoder_hid_proj.image_projection_layers
            ):
                output_hidden_state = not isinstance(image_proj_layer, ImageProjection)
                single_image_embeds, single_negative_image_embeds = self.encode_image(
                    single_ip_adapter_image, 1, output_hidden_state
                )
                single_image_embeds = ops.stack([single_image_embeds] * num_images_per_prompt, axis=0)
                single_negative_image_embeds = ops.stack([single_negative_image_embeds] * num_images_per_prompt, axis=0)

                if do_classifier_free_guidance:
                    single_image_embeds = ops.cat([single_negative_image_embeds, single_image_embeds])

                image_embeds.append(single_image_embeds)
        else:
            repeat_dims = [1]
            image_embeds = []
            for single_image_embeds in ip_adapter_image_embeds:
                if do_classifier_free_guidance:
                    single_negative_image_embeds, single_image_embeds = single_image_embeds.chunk(2)
                    single_image_embeds = single_image_embeds.tile(
                        (num_images_per_prompt, *(repeat_dims * len(single_image_embeds.shape[1:])))
                    )
                    single_negative_image_embeds = single_negative_image_embeds.tile(
                        (num_images_per_prompt, *(repeat_dims * len(single_negative_image_embeds.shape[1:])))
                    )
                    single_image_embeds = ops.cat([single_negative_image_embeds, single_image_embeds])
                else:
                    single_image_embeds = single_image_embeds.tile(
                        (num_images_per_prompt, *(repeat_dims * len(single_image_embeds.shape[1:])))
                    )
                image_embeds.append(single_image_embeds)

        return image_embeds

    # Copied from diffusers.pipelines.text_to_video_synthesis/pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
    def decode_latents(self, latents):
        latents = 1 / self.vae.config.scaling_factor * latents

        batch_size, channels, num_frames, height, width = latents.shape
        latents = latents.permute(0, 2, 1, 3, 4).reshape(batch_size * num_frames, channels, height, width)

        image = self.vae.decode(latents)[0]
        video = image[None, :].reshape((batch_size, num_frames, -1) + image.shape[2:]).permute(0, 2, 1, 3, 4)
        # we always cast to float32 as this does not cause significant overhead and is compatible with bfloat16
        video = video.float()
        return video

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
    def prepare_extra_step_kwargs(self, generator, eta):
        # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
        # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
        # and should be between [0, 1]

        accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
        extra_step_kwargs = {}
        if accepts_eta:
            extra_step_kwargs["eta"] = eta

        # check if the scheduler accepts generator
        accepts_generator = "generator" in set(inspect.signature(self.scheduler.step).parameters.keys())
        if accepts_generator:
            extra_step_kwargs["generator"] = generator
        return extra_step_kwargs

    def check_inputs(
        self,
        prompt,
        prompt_2,
        height,
        width,
        negative_prompt=None,
        negative_prompt_2=None,
        prompt_embeds=None,
        negative_prompt_embeds=None,
        pooled_prompt_embeds=None,
        negative_pooled_prompt_embeds=None,
        callback_on_step_end_tensor_inputs=None,
    ):
        if height % 8 != 0 or width % 8 != 0:
            raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")

        if callback_on_step_end_tensor_inputs is not None and not all(
            k in self._callback_tensor_inputs for k in callback_on_step_end_tensor_inputs
        ):
            raise ValueError(
                f"`callback_on_step_end_tensor_inputs` has to be in {self._callback_tensor_inputs}, but found {[k for k in callback_on_step_end_tensor_inputs if k not in self._callback_tensor_inputs]}"  # noqa E501
            )

        if prompt is not None and prompt_embeds is not None:
            raise ValueError(
                f"Cannot forward both `prompt`: {prompt} and `prompt_embeds`: {prompt_embeds}. Please make sure to"
                " only forward one of the two."
            )
        elif prompt_2 is not None and prompt_embeds is not None:
            raise ValueError(
                f"Cannot forward both `prompt_2`: {prompt_2} and `prompt_embeds`: {prompt_embeds}. Please make sure to"
                " only forward one of the two."
            )
        elif prompt is None and prompt_embeds is None:
            raise ValueError(
                "Provide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined."
            )
        elif prompt is not None and (not isinstance(prompt, str) and not isinstance(prompt, list)):
            raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")
        elif prompt_2 is not None and (not isinstance(prompt_2, str) and not isinstance(prompt_2, list)):
            raise ValueError(f"`prompt_2` has to be of type `str` or `list` but is {type(prompt_2)}")

        if negative_prompt is not None and negative_prompt_embeds is not None:
            raise ValueError(
                f"Cannot forward both `negative_prompt`: {negative_prompt} and `negative_prompt_embeds`:"
                f" {negative_prompt_embeds}. Please make sure to only forward one of the two."
            )
        elif negative_prompt_2 is not None and negative_prompt_embeds is not None:
            raise ValueError(
                f"Cannot forward both `negative_prompt_2`: {negative_prompt_2} and `negative_prompt_embeds`:"
                f" {negative_prompt_embeds}. Please make sure to only forward one of the two."
            )

        if prompt_embeds is not None and negative_prompt_embeds is not None:
            if prompt_embeds.shape != negative_prompt_embeds.shape:
                raise ValueError(
                    "`prompt_embeds` and `negative_prompt_embeds` must have the same shape when passed directly, but"
                    f" got: `prompt_embeds` {prompt_embeds.shape} != `negative_prompt_embeds`"
                    f" {negative_prompt_embeds.shape}."
                )

        if prompt_embeds is not None and pooled_prompt_embeds is None:
            raise ValueError(
                "If `prompt_embeds` are provided, `pooled_prompt_embeds` also have to be passed. Make sure to generate `pooled_prompt_embeds` from the same text encoder that was used to generate `prompt_embeds`."  # noqa E501
            )

        if negative_prompt_embeds is not None and negative_pooled_prompt_embeds is None:
            raise ValueError(
                "If `negative_prompt_embeds` are provided, `negative_pooled_prompt_embeds` also have to be passed. Make sure to generate `negative_pooled_prompt_embeds` from the same text encoder that was used to generate `negative_prompt_embeds`."  # noqa E501
            )

    # Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.prepare_latents
    def prepare_latents(
        self, batch_size, num_channels_latents, num_frames, height, width, dtype, generator, latents=None
    ):
        shape = (
            batch_size,
            num_channels_latents,
            num_frames,
            height // self.vae_scale_factor,
            width // self.vae_scale_factor,
        )
        if isinstance(generator, list) and len(generator) != batch_size:
            raise ValueError(
                f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
                f" size of {batch_size}. Make sure the batch size matches the length of the generators."
            )

        if latents is None:
            latents = randn_tensor(shape, generator=generator, dtype=dtype)

        # scale the initial noise by the standard deviation required by the scheduler
        latents = (latents * self.scheduler.init_noise_sigma).to(dtype)
        return latents

    def _get_add_time_ids(
        self, original_size, crops_coords_top_left, target_size, dtype, text_encoder_projection_dim=None
    ):
        add_time_ids = list(original_size + crops_coords_top_left + target_size)

        passed_add_embed_dim = (
            self.unet.config.addition_time_embed_dim * len(add_time_ids) + text_encoder_projection_dim
        )
        expected_add_embed_dim = self.unet.add_embedding.linear_1.in_channels

        if expected_add_embed_dim != passed_add_embed_dim:
            raise ValueError(
                f"Model expects an added time embedding vector of length {expected_add_embed_dim}, but a vector of {passed_add_embed_dim} was created. The model has an incorrect config. Please check `unet.config.time_embedding_type` and `text_encoder_2.config.projection_dim`."  # noqa E501
            )

        add_time_ids = ms.Tensor([add_time_ids], dtype=dtype)
        return add_time_ids

    def upcast_vae(self):
        self.vae.to(dtype=ms.float32)

    # Copied from diffusers.pipelines.latent_consistency_models.pipeline_latent_consistency_text2img.LatentConsistencyModelPipeline.get_guidance_scale_embedding
    def get_guidance_scale_embedding(
        self, w: ms.Tensor, embedding_dim: int = 512, dtype: ms.Type = ms.float32
    ) -> ms.Tensor:
        """
        See https://github.com/google-research/vdm/blob/dc27b98a554f65cdc654b800da5aa1846545d41b/model_vdm.py#L298

        Args:
            w (`ms.Tensor`):
                Generate embedding vectors with a specified guidance scale to subsequently enrich timestep embeddings.
            embedding_dim (`int`, *optional*, defaults to 512):
                Dimension of the embeddings to generate.
            dtype (`mindspore.dtype`, *optional*, defaults to `mindspore.float32`):
                Data type of the generated embeddings.

        Returns:
            `ms.Tensor`: Embedding vectors with shape `(len(w), embedding_dim)`.
        """
        assert len(w.shape) == 1
        w = w * 1000.0

        half_dim = embedding_dim // 2
        emb = ops.log(ms.Tensor(10000.0)) / (half_dim - 1)
        emb = ops.exp(ops.arange(half_dim, dtype=dtype) * -emb)
        emb = w.to(dtype)[:, None] * emb[None, :]
        emb = ops.cat([ops.sin(emb), ops.cos(emb)], axis=1)
        if embedding_dim % 2 == 1:  # zero pad
            emb = ms.mint.nn.functional.pad(emb, (0, 1))
        assert emb.shape == (w.shape[0], embedding_dim)
        return emb

    @property
    def guidance_scale(self):
        return self._guidance_scale

    @property
    def guidance_rescale(self):
        return self._guidance_rescale

    @property
    def clip_skip(self):
        return self._clip_skip

    # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
    # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
    # corresponds to doing no classifier free guidance.
    @property
    def do_classifier_free_guidance(self):
        return self._guidance_scale > 1 and self.unet.config.time_cond_proj_dim is None

    @property
    def cross_attention_kwargs(self):
        return self._cross_attention_kwargs

    @property
    def denoising_end(self):
        return self._denoising_end

    @property
    def num_timesteps(self):
        return self._num_timesteps

    @property
    def interrupt(self):
        return self._interrupt

    def __call__(
        self,
        prompt: Union[str, List[str]] = None,
        prompt_2: Optional[Union[str, List[str]]] = None,
        num_frames: int = 16,
        height: Optional[int] = None,
        width: Optional[int] = None,
        num_inference_steps: int = 50,
        timesteps: List[int] = None,
        sigmas: List[float] = None,
        denoising_end: Optional[float] = None,
        guidance_scale: float = 5.0,
        negative_prompt: Optional[Union[str, List[str]]] = None,
        negative_prompt_2: Optional[Union[str, List[str]]] = None,
        num_videos_per_prompt: Optional[int] = 1,
        eta: float = 0.0,
        generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
        latents: Optional[ms.Tensor] = None,
        prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        pooled_prompt_embeds: Optional[ms.Tensor] = None,
        negative_pooled_prompt_embeds: Optional[ms.Tensor] = None,
        ip_adapter_image: Optional[PipelineImageInput] = None,
        ip_adapter_image_embeds: Optional[List[ms.Tensor]] = None,
        output_type: Optional[str] = "pil",
        return_dict: bool = False,
        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
        guidance_rescale: float = 0.0,
        original_size: Optional[Tuple[int, int]] = None,
        crops_coords_top_left: Tuple[int, int] = (0, 0),
        target_size: Optional[Tuple[int, int]] = None,
        negative_original_size: Optional[Tuple[int, int]] = None,
        negative_crops_coords_top_left: Tuple[int, int] = (0, 0),
        negative_target_size: Optional[Tuple[int, int]] = None,
        clip_skip: Optional[int] = None,
        callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
    ):
        r"""
        Function invoked when calling the pipeline for generation.

        Args:
            prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts to guide the video generation. If not defined, one has to pass `prompt_embeds`.
                instead.
            prompt_2 (`str` or `List[str]`, *optional*):
                The prompt or prompts to be sent to the `tokenizer_2` and `text_encoder_2`. If not defined, `prompt` is
                used in both text-encoders
            num_frames:
                The number of video frames that are generated. Defaults to 16 frames which at 8 frames per seconds
                amounts to 2 seconds of video.
            height (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
                The height in pixels of the generated video. This is set to 1024 by default for the best results.
                Anything below 512 pixels won't work well for
                [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
                and checkpoints that are not specifically fine-tuned on low resolutions.
            width (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
                The width in pixels of the generated video. This is set to 1024 by default for the best results.
                Anything below 512 pixels won't work well for
                [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
                and checkpoints that are not specifically fine-tuned on low resolutions.
            num_inference_steps (`int`, *optional*, defaults to 50):
                The number of denoising steps. More denoising steps usually lead to a higher quality video at the
                expense of slower inference.
            timesteps (`List[int]`, *optional*):
                Custom timesteps to use for the denoising process with schedulers which support a `timesteps` argument
                in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
                passed will be used. Must be in descending order.
            sigmas (`List[float]`, *optional*):
                Custom sigmas to use for the denoising process with schedulers which support a `sigmas` argument in
                their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is passed
                will be used.
            denoising_end (`float`, *optional*):
                When specified, determines the fraction (between 0.0 and 1.0) of the total denoising process to be
                completed before it is intentionally prematurely terminated. As a result, the returned sample will
                still retain a substantial amount of noise as determined by the discrete timesteps selected by the
                scheduler. The denoising_end parameter should ideally be utilized when this pipeline forms a part of a
                "Mixture of Denoisers" multi-pipeline setup, as elaborated in [**Refining the Image
                Output**](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/stable_diffusion_xl#refining-the-image-output)
            guidance_scale (`float`, *optional*, defaults to 5.0):
                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
                `guidance_scale` is defined as `w` of equation 2. of [Imagen
                Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
                1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
                usually at the expense of lower video quality.
            negative_prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts not to guide the video generation. If not defined, one has to pass
                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
                less than `1`).
            negative_prompt_2 (`str` or `List[str]`, *optional*):
                The prompt or prompts not to guide the video generation to be sent to `tokenizer_2` and
                `text_encoder_2`. If not defined, `negative_prompt` is used in both text-encoders
            num_videos_per_prompt (`int`, *optional*, defaults to 1):
                The number of videos to generate per prompt.
            eta (`float`, *optional*, defaults to 0.0):
                Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to
                [`schedulers.DDIMScheduler`], will be ignored for others.
            generator (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
                One or a list of [numpy generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
                to make generation deterministic.
            latents (`ms.Tensor`, *optional*):
                Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for video
                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                tensor will ge generated by sampling using the supplied random `generator`.
            prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                provided, text embeddings will be generated from `prompt` input argument.
            negative_prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                argument.
            pooled_prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
                If not provided, pooled text embeddings will be generated from `prompt` input argument.
            negative_pooled_prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_prompt`
                input argument.
            ip_adapter_image: (`PipelineImageInput`, *optional*):
                Optional image input to work with IP Adapters.
            ip_adapter_image_embeds (`List[ms.Tensor]`, *optional*):
                Pre-generated image embeddings for IP-Adapter. If not provided, embeddings are computed from the
                `ip_adapter_image` input argument.
            output_type (`str`, *optional*, defaults to `"pil"`):
                The output format of the generated video. Choose between
                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
            return_dict (`bool`, *optional*, defaults to `False`):
                Whether or not to return a [`~pipelines.stable_diffusion_xl.AnimateDiffPipelineOutput`] instead of a
                plain tuple.
            cross_attention_kwargs (`dict`, *optional*):
                A kwargs dictionary that if specified is passed along to the `AttentionProcessor` as defined under
                `self.processor` in
                [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
            guidance_rescale (`float`, *optional*, defaults to 0.0):
                Guidance rescale factor proposed by [Common Diffusion Noise Schedules and Sample Steps are
                Flawed](https://arxiv.org/pdf/2305.08891.pdf) `guidance_scale` is defined as `φ` in equation 16. of
                [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://arxiv.org/pdf/2305.08891.pdf).
                Guidance rescale factor should fix overexposure when using zero terminal SNR.
            original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                If `original_size` is not the same as `target_size` the image will appear to be down- or upsampled.
                `original_size` defaults to `(height, width)` if not specified. Part of SDXL's micro-conditioning as
                explained in section 2.2 of
                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
            crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
                `crops_coords_top_left` can be used to generate an image that appears to be "cropped" from the position
                `crops_coords_top_left` downwards. Favorable, well-centered images are usually achieved by setting
                `crops_coords_top_left` to (0, 0). Part of SDXL's micro-conditioning as explained in section 2.2 of
                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
            target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                For most cases, `target_size` should be set to the desired height and width of the generated image. If
                not specified it will default to `(height, width)`. Part of SDXL's micro-conditioning as explained in
                section 2.2 of [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
            negative_original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                To negatively condition the generation process based on a specific image resolution. Part of SDXL's
                micro-conditioning as explained in section 2.2 of
                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952). For more
                information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.
            negative_crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
                To negatively condition the generation process based on a specific crop coordinates. Part of SDXL's
                micro-conditioning as explained in section 2.2 of
                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952). For more
                information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.
            negative_target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                To negatively condition the generation process based on a target image resolution. It should be as same
                as the `target_size` for most cases. Part of SDXL's micro-conditioning as explained in section 2.2 of
                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952). For more
                information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.
            callback_on_step_end (`Callable`, *optional*):
                A function that calls at the end of each denoising steps during the inference. The function is called
                with the following arguments: `callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int,
                callback_kwargs: Dict)`. `callback_kwargs` will include a list of all tensors as specified by
                `callback_on_step_end_tensor_inputs`.
            callback_on_step_end_tensor_inputs (`List`, *optional*):
                The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
                will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
                `._callback_tensor_inputs` attribute of your pipeline class.

        Examples:

        Returns:
            [`~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput`] or `tuple`:
                If `return_dict` is `True`, [`~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput`] is
                returned, otherwise a `tuple` is returned where the first element is a list with the generated frames.
        """

        # 0. Default height and width to unet
        height = height or self.default_sample_size * self.vae_scale_factor
        width = width or self.default_sample_size * self.vae_scale_factor

        num_videos_per_prompt = 1

        original_size = original_size or (height, width)
        target_size = target_size or (height, width)

        # 1. Check inputs. Raise error if not correct
        self.check_inputs(
            prompt,
            prompt_2,
            height,
            width,
            negative_prompt,
            negative_prompt_2,
            prompt_embeds,
            negative_prompt_embeds,
            pooled_prompt_embeds,
            negative_pooled_prompt_embeds,
            callback_on_step_end_tensor_inputs,
        )

        self._guidance_scale = guidance_scale
        self._guidance_rescale = guidance_rescale
        self._clip_skip = clip_skip
        self._cross_attention_kwargs = cross_attention_kwargs
        self._denoising_end = denoising_end
        self._interrupt = False

        # 2. Define call parameters
        if prompt is not None and isinstance(prompt, str):
            batch_size = 1
        elif prompt is not None and isinstance(prompt, list):
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        # 3. Encode input prompt
        lora_scale = self.cross_attention_kwargs.get("scale", None) if self.cross_attention_kwargs is not None else None

        (
            prompt_embeds,
            negative_prompt_embeds,
            pooled_prompt_embeds,
            negative_pooled_prompt_embeds,
        ) = self.encode_prompt(
            prompt=prompt,
            prompt_2=prompt_2,
            num_videos_per_prompt=num_videos_per_prompt,
            do_classifier_free_guidance=self.do_classifier_free_guidance,
            negative_prompt=negative_prompt,
            negative_prompt_2=negative_prompt_2,
            prompt_embeds=prompt_embeds,
            negative_prompt_embeds=negative_prompt_embeds,
            pooled_prompt_embeds=pooled_prompt_embeds,
            negative_pooled_prompt_embeds=negative_pooled_prompt_embeds,
            lora_scale=lora_scale,
            clip_skip=self.clip_skip,
        )

        # 4. Prepare timesteps
        timesteps, num_inference_steps = retrieve_timesteps(self.scheduler, num_inference_steps, timesteps, sigmas)

        # 5. Prepare latent variables
        num_channels_latents = self.unet.config.in_channels
        latents = self.prepare_latents(
            batch_size * num_videos_per_prompt,
            num_channels_latents,
            num_frames,
            height,
            width,
            prompt_embeds.dtype,
            generator,
            latents,
        )

        # 6. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
        extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)

        # 7. Prepare added time ids & embeddings
        add_text_embeds = pooled_prompt_embeds
        if self.text_encoder_2 is None:
            text_encoder_projection_dim = int(pooled_prompt_embeds.shape[-1])
        else:
            text_encoder_projection_dim = self.text_encoder_2.config.projection_dim

        add_time_ids = self._get_add_time_ids(
            original_size,
            crops_coords_top_left,
            target_size,
            dtype=prompt_embeds.dtype,
            text_encoder_projection_dim=text_encoder_projection_dim,
        )
        if negative_original_size is not None and negative_target_size is not None:
            negative_add_time_ids = self._get_add_time_ids(
                negative_original_size,
                negative_crops_coords_top_left,
                negative_target_size,
                dtype=prompt_embeds.dtype,
                text_encoder_projection_dim=text_encoder_projection_dim,
            )
        else:
            negative_add_time_ids = add_time_ids

        if self.do_classifier_free_guidance:
            prompt_embeds = ops.cat([negative_prompt_embeds, prompt_embeds], axis=0)
            add_text_embeds = ops.cat([negative_pooled_prompt_embeds, add_text_embeds], axis=0)
            add_time_ids = ops.cat([negative_add_time_ids, add_time_ids], axis=0)

        add_time_ids = add_time_ids.tile((batch_size * num_videos_per_prompt, 1))

        if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
            image_embeds = self.prepare_ip_adapter_image_embeds(
                ip_adapter_image,
                ip_adapter_image_embeds,
                batch_size * num_videos_per_prompt,
                self.do_classifier_free_guidance,
            )

        # 7.1 Apply denoising_end
        if (
            self.denoising_end is not None
            and isinstance(self.denoising_end, float)
            and self.denoising_end > 0
            and self.denoising_end < 1
        ):
            discrete_timestep_cutoff = int(
                round(
                    self.scheduler.config.num_train_timesteps
                    - (self.denoising_end * self.scheduler.config.num_train_timesteps)
                )
            )
            num_inference_steps = len(list(filter(lambda ts: ts >= discrete_timestep_cutoff, timesteps)))
            timesteps = timesteps[:num_inference_steps]

        # 8. Optionally get Guidance Scale Embedding
        timestep_cond = None
        if self.unet.config.time_cond_proj_dim is not None:
            guidance_scale_tensor = ms.Tensor(self.guidance_scale - 1).tile((batch_size * num_videos_per_prompt))
            timestep_cond = self.get_guidance_scale_embedding(
                guidance_scale_tensor, embedding_dim=self.unet.config.time_cond_proj_dim
            ).to(dtype=latents.dtype)

        self._num_timesteps = len(timesteps)

        # 9. Denoising loop
        with self.progress_bar(total=self._num_timesteps) as progress_bar:
            for i, t in enumerate(timesteps):
                if self.interrupt:
                    continue

                # expand the latents if we are doing classifier free guidance
                latent_model_input = ops.cat([latents] * 2) if self.do_classifier_free_guidance else latents

                latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)

                # predict the noise residual
                added_cond_kwargs = {"text_embeds": add_text_embeds, "time_ids": add_time_ids}
                if ip_adapter_image is not None or ip_adapter_image_embeds:
                    added_cond_kwargs["image_embeds"] = image_embeds

                noise_pred = self.unet(
                    latent_model_input,
                    t,
                    encoder_hidden_states=prompt_embeds,
                    timestep_cond=timestep_cond,
                    cross_attention_kwargs=self.cross_attention_kwargs,
                    added_cond_kwargs=ms.mutable(added_cond_kwargs),
                    return_dict=False,
                )[0]

                # perform guidance
                if self.do_classifier_free_guidance:
                    noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
                    noise_pred = noise_pred_uncond + self.guidance_scale * (noise_pred_text - noise_pred_uncond)

                if self.do_classifier_free_guidance and self.guidance_rescale > 0.0:
                    # Based on 3.4. in https://arxiv.org/pdf/2305.08891.pdf
                    noise_pred = rescale_noise_cfg(noise_pred, noise_pred_text, guidance_rescale=self.guidance_rescale)

                # compute the previous noisy sample x_t -> x_t-1
                latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]

                if callback_on_step_end is not None:
                    callback_kwargs = {}
                    for k in callback_on_step_end_tensor_inputs:
                        callback_kwargs[k] = locals()[k]
                    callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)

                    latents = callback_outputs.pop("latents", latents)
                    prompt_embeds = callback_outputs.pop("prompt_embeds", prompt_embeds)
                    negative_prompt_embeds = callback_outputs.pop("negative_prompt_embeds", negative_prompt_embeds)
                    add_text_embeds = callback_outputs.pop("add_text_embeds", add_text_embeds)
                    negative_pooled_prompt_embeds = callback_outputs.pop(
                        "negative_pooled_prompt_embeds", negative_pooled_prompt_embeds
                    )
                    add_time_ids = callback_outputs.pop("add_time_ids", add_time_ids)
                    negative_add_time_ids = callback_outputs.pop("negative_add_time_ids", negative_add_time_ids)

                progress_bar.update()

        # make sure the VAE is in float32 mode, as it overflows in float16
        needs_upcasting = self.vae.dtype == ms.float16 and self.vae.config.force_upcast

        if needs_upcasting:
            self.upcast_vae()
            latents = latents.to(next(iter(self.vae.post_quant_conv.get_parameters())).dtype)

        # 10. Post processing
        if output_type == "latent":
            video = latents
        else:
            video_tensor = self.decode_latents(latents)
            video = self.video_processor.postprocess_video(video=video_tensor, output_type=output_type)

        # cast back to fp16 if needed
        if needs_upcasting:
            self.vae.to(dtype=ms.float16)

        if not return_dict:
            return (video,)

        return AnimateDiffPipelineOutput(frames=video)

mindone.diffusers.pipelines.AnimateDiffSDXLPipeline.__call__(prompt=None, prompt_2=None, num_frames=16, height=None, width=None, num_inference_steps=50, timesteps=None, sigmas=None, denoising_end=None, guidance_scale=5.0, negative_prompt=None, negative_prompt_2=None, num_videos_per_prompt=1, eta=0.0, generator=None, latents=None, prompt_embeds=None, negative_prompt_embeds=None, pooled_prompt_embeds=None, negative_pooled_prompt_embeds=None, ip_adapter_image=None, ip_adapter_image_embeds=None, output_type='pil', return_dict=False, cross_attention_kwargs=None, guidance_rescale=0.0, original_size=None, crops_coords_top_left=(0, 0), target_size=None, negative_original_size=None, negative_crops_coords_top_left=(0, 0), negative_target_size=None, clip_skip=None, callback_on_step_end=None, callback_on_step_end_tensor_inputs=['latents'])

Function invoked when calling the pipeline for generation.

PARAMETER DESCRIPTION
prompt

The prompt or prompts to guide the video generation. If not defined, one has to pass prompt_embeds. instead.

TYPE: `str` or `List[str]`, *optional* DEFAULT: None

prompt_2

The prompt or prompts to be sent to the tokenizer_2 and text_encoder_2. If not defined, prompt is used in both text-encoders

TYPE: `str` or `List[str]`, *optional* DEFAULT: None

num_frames

The number of video frames that are generated. Defaults to 16 frames which at 8 frames per seconds amounts to 2 seconds of video.

TYPE: int DEFAULT: 16

height

The height in pixels of the generated video. This is set to 1024 by default for the best results. Anything below 512 pixels won't work well for stabilityai/stable-diffusion-xl-base-1.0 and checkpoints that are not specifically fine-tuned on low resolutions.

TYPE: `int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor DEFAULT: None

width

The width in pixels of the generated video. This is set to 1024 by default for the best results. Anything below 512 pixels won't work well for stabilityai/stable-diffusion-xl-base-1.0 and checkpoints that are not specifically fine-tuned on low resolutions.

TYPE: `int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor DEFAULT: None

num_inference_steps

The number of denoising steps. More denoising steps usually lead to a higher quality video at the expense of slower inference.

TYPE: `int`, *optional*, defaults to 50 DEFAULT: 50

timesteps

Custom timesteps to use for the denoising process with schedulers which support a timesteps argument in their set_timesteps method. If not defined, the default behavior when num_inference_steps is passed will be used. Must be in descending order.

TYPE: `List[int]`, *optional* DEFAULT: None

sigmas

Custom sigmas to use for the denoising process with schedulers which support a sigmas argument in their set_timesteps method. If not defined, the default behavior when num_inference_steps is passed will be used.

TYPE: `List[float]`, *optional* DEFAULT: None

denoising_end

When specified, determines the fraction (between 0.0 and 1.0) of the total denoising process to be completed before it is intentionally prematurely terminated. As a result, the returned sample will still retain a substantial amount of noise as determined by the discrete timesteps selected by the scheduler. The denoising_end parameter should ideally be utilized when this pipeline forms a part of a "Mixture of Denoisers" multi-pipeline setup, as elaborated in Refining the Image Output

TYPE: `float`, *optional* DEFAULT: None

guidance_scale

Guidance scale as defined in Classifier-Free Diffusion Guidance. guidance_scale is defined as w of equation 2. of Imagen Paper. Guidance scale is enabled by setting guidance_scale > 1. Higher guidance scale encourages to generate images that are closely linked to the text prompt, usually at the expense of lower video quality.

TYPE: `float`, *optional*, defaults to 5.0 DEFAULT: 5.0

negative_prompt

The prompt or prompts not to guide the video generation. If not defined, one has to pass negative_prompt_embeds instead. Ignored when not using guidance (i.e., ignored if guidance_scale is less than 1).

TYPE: `str` or `List[str]`, *optional* DEFAULT: None

negative_prompt_2

The prompt or prompts not to guide the video generation to be sent to tokenizer_2 and text_encoder_2. If not defined, negative_prompt is used in both text-encoders

TYPE: `str` or `List[str]`, *optional* DEFAULT: None

num_videos_per_prompt

The number of videos to generate per prompt.

TYPE: `int`, *optional*, defaults to 1 DEFAULT: 1

eta

Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to [schedulers.DDIMScheduler], will be ignored for others.

TYPE: `float`, *optional*, defaults to 0.0 DEFAULT: 0.0

generator

One or a list of numpy generator(s) to make generation deterministic.

TYPE: `np.random.Generator` or `List[np.random.Generator]`, *optional* DEFAULT: None

latents

Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for video generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor will ge generated by sampling using the supplied random generator.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

prompt_embeds

Pre-generated text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, text embeddings will be generated from prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

negative_prompt_embeds

Pre-generated negative text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, negative_prompt_embeds will be generated from negative_prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

pooled_prompt_embeds

Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, pooled text embeddings will be generated from prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

negative_pooled_prompt_embeds

Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, pooled negative_prompt_embeds will be generated from negative_prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

ip_adapter_image

(PipelineImageInput, optional): Optional image input to work with IP Adapters.

TYPE: Optional[PipelineImageInput] DEFAULT: None

ip_adapter_image_embeds

Pre-generated image embeddings for IP-Adapter. If not provided, embeddings are computed from the ip_adapter_image input argument.

TYPE: `List[ms.Tensor]`, *optional* DEFAULT: None

output_type

The output format of the generated video. Choose between PIL: PIL.Image.Image or np.array.

TYPE: `str`, *optional*, defaults to `"pil"` DEFAULT: 'pil'

return_dict

Whether or not to return a [~pipelines.stable_diffusion_xl.AnimateDiffPipelineOutput] instead of a plain tuple.

TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False

cross_attention_kwargs

A kwargs dictionary that if specified is passed along to the AttentionProcessor as defined under self.processor in diffusers.models.attention_processor.

TYPE: `dict`, *optional* DEFAULT: None

guidance_rescale

Guidance rescale factor proposed by Common Diffusion Noise Schedules and Sample Steps are Flawed guidance_scale is defined as φ in equation 16. of Common Diffusion Noise Schedules and Sample Steps are Flawed. Guidance rescale factor should fix overexposure when using zero terminal SNR.

TYPE: `float`, *optional*, defaults to 0.0 DEFAULT: 0.0

original_size

If original_size is not the same as target_size the image will appear to be down- or upsampled. original_size defaults to (height, width) if not specified. Part of SDXL's micro-conditioning as explained in section 2.2 of https://huggingface.co/papers/2307.01952.

TYPE: `Tuple[int]`, *optional*, defaults to (1024, 1024 DEFAULT: None

crops_coords_top_left

crops_coords_top_left can be used to generate an image that appears to be "cropped" from the position crops_coords_top_left downwards. Favorable, well-centered images are usually achieved by setting crops_coords_top_left to (0, 0). Part of SDXL's micro-conditioning as explained in section 2.2 of https://huggingface.co/papers/2307.01952.

TYPE: `Tuple[int]`, *optional*, defaults to (0, 0 DEFAULT: (0, 0)

target_size

For most cases, target_size should be set to the desired height and width of the generated image. If not specified it will default to (height, width). Part of SDXL's micro-conditioning as explained in section 2.2 of https://huggingface.co/papers/2307.01952.

TYPE: `Tuple[int]`, *optional*, defaults to (1024, 1024 DEFAULT: None

negative_original_size

To negatively condition the generation process based on a specific image resolution. Part of SDXL's micro-conditioning as explained in section 2.2 of https://huggingface.co/papers/2307.01952. For more information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.

TYPE: `Tuple[int]`, *optional*, defaults to (1024, 1024 DEFAULT: None

negative_crops_coords_top_left

To negatively condition the generation process based on a specific crop coordinates. Part of SDXL's micro-conditioning as explained in section 2.2 of https://huggingface.co/papers/2307.01952. For more information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.

TYPE: `Tuple[int]`, *optional*, defaults to (0, 0 DEFAULT: (0, 0)

negative_target_size

To negatively condition the generation process based on a target image resolution. It should be as same as the target_size for most cases. Part of SDXL's micro-conditioning as explained in section 2.2 of https://huggingface.co/papers/2307.01952. For more information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.

TYPE: `Tuple[int]`, *optional*, defaults to (1024, 1024 DEFAULT: None

callback_on_step_end

A function that calls at the end of each denoising steps during the inference. The function is called with the following arguments: callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict). callback_kwargs will include a list of all tensors as specified by callback_on_step_end_tensor_inputs.

TYPE: `Callable`, *optional* DEFAULT: None

callback_on_step_end_tensor_inputs

The list of tensor inputs for the callback_on_step_end function. The tensors specified in the list will be passed as callback_kwargs argument. You will only be able to include variables listed in the ._callback_tensor_inputs attribute of your pipeline class.

TYPE: `List`, *optional* DEFAULT: ['latents']

RETURNS DESCRIPTION

[~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput] or tuple: If return_dict is True, [~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput] is returned, otherwise a tuple is returned where the first element is a list with the generated frames.
Source code in mindone/diffusers/pipelines/animatediff/pipeline_animatediff_sdxl.py 
 796
 797
 798
 799
 800
 801
 802
 803
 804
 805
 806
 807
 808
 809
 810
 811
 812
 813
 814
 815
 816
 817
 818
 819
 820
 821
 822
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
def __call__(
    self,
    prompt: Union[str, List[str]] = None,
    prompt_2: Optional[Union[str, List[str]]] = None,
    num_frames: int = 16,
    height: Optional[int] = None,
    width: Optional[int] = None,
    num_inference_steps: int = 50,
    timesteps: List[int] = None,
    sigmas: List[float] = None,
    denoising_end: Optional[float] = None,
    guidance_scale: float = 5.0,
    negative_prompt: Optional[Union[str, List[str]]] = None,
    negative_prompt_2: Optional[Union[str, List[str]]] = None,
    num_videos_per_prompt: Optional[int] = 1,
    eta: float = 0.0,
    generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
    latents: Optional[ms.Tensor] = None,
    prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    pooled_prompt_embeds: Optional[ms.Tensor] = None,
    negative_pooled_prompt_embeds: Optional[ms.Tensor] = None,
    ip_adapter_image: Optional[PipelineImageInput] = None,
    ip_adapter_image_embeds: Optional[List[ms.Tensor]] = None,
    output_type: Optional[str] = "pil",
    return_dict: bool = False,
    cross_attention_kwargs: Optional[Dict[str, Any]] = None,
    guidance_rescale: float = 0.0,
    original_size: Optional[Tuple[int, int]] = None,
    crops_coords_top_left: Tuple[int, int] = (0, 0),
    target_size: Optional[Tuple[int, int]] = None,
    negative_original_size: Optional[Tuple[int, int]] = None,
    negative_crops_coords_top_left: Tuple[int, int] = (0, 0),
    negative_target_size: Optional[Tuple[int, int]] = None,
    clip_skip: Optional[int] = None,
    callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
    callback_on_step_end_tensor_inputs: List[str] = ["latents"],
):
    r"""
    Function invoked when calling the pipeline for generation.

    Args:
        prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts to guide the video generation. If not defined, one has to pass `prompt_embeds`.
            instead.
        prompt_2 (`str` or `List[str]`, *optional*):
            The prompt or prompts to be sent to the `tokenizer_2` and `text_encoder_2`. If not defined, `prompt` is
            used in both text-encoders
        num_frames:
            The number of video frames that are generated. Defaults to 16 frames which at 8 frames per seconds
            amounts to 2 seconds of video.
        height (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
            The height in pixels of the generated video. This is set to 1024 by default for the best results.
            Anything below 512 pixels won't work well for
            [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
            and checkpoints that are not specifically fine-tuned on low resolutions.
        width (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
            The width in pixels of the generated video. This is set to 1024 by default for the best results.
            Anything below 512 pixels won't work well for
            [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
            and checkpoints that are not specifically fine-tuned on low resolutions.
        num_inference_steps (`int`, *optional*, defaults to 50):
            The number of denoising steps. More denoising steps usually lead to a higher quality video at the
            expense of slower inference.
        timesteps (`List[int]`, *optional*):
            Custom timesteps to use for the denoising process with schedulers which support a `timesteps` argument
            in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
            passed will be used. Must be in descending order.
        sigmas (`List[float]`, *optional*):
            Custom sigmas to use for the denoising process with schedulers which support a `sigmas` argument in
            their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is passed
            will be used.
        denoising_end (`float`, *optional*):
            When specified, determines the fraction (between 0.0 and 1.0) of the total denoising process to be
            completed before it is intentionally prematurely terminated. As a result, the returned sample will
            still retain a substantial amount of noise as determined by the discrete timesteps selected by the
            scheduler. The denoising_end parameter should ideally be utilized when this pipeline forms a part of a
            "Mixture of Denoisers" multi-pipeline setup, as elaborated in [**Refining the Image
            Output**](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/stable_diffusion_xl#refining-the-image-output)
        guidance_scale (`float`, *optional*, defaults to 5.0):
            Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
            `guidance_scale` is defined as `w` of equation 2. of [Imagen
            Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
            1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
            usually at the expense of lower video quality.
        negative_prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts not to guide the video generation. If not defined, one has to pass
            `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
            less than `1`).
        negative_prompt_2 (`str` or `List[str]`, *optional*):
            The prompt or prompts not to guide the video generation to be sent to `tokenizer_2` and
            `text_encoder_2`. If not defined, `negative_prompt` is used in both text-encoders
        num_videos_per_prompt (`int`, *optional*, defaults to 1):
            The number of videos to generate per prompt.
        eta (`float`, *optional*, defaults to 0.0):
            Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to
            [`schedulers.DDIMScheduler`], will be ignored for others.
        generator (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
            One or a list of [numpy generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
            to make generation deterministic.
        latents (`ms.Tensor`, *optional*):
            Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for video
            generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
            tensor will ge generated by sampling using the supplied random `generator`.
        prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
            provided, text embeddings will be generated from `prompt` input argument.
        negative_prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
            weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
            argument.
        pooled_prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
            If not provided, pooled text embeddings will be generated from `prompt` input argument.
        negative_pooled_prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
            weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_prompt`
            input argument.
        ip_adapter_image: (`PipelineImageInput`, *optional*):
            Optional image input to work with IP Adapters.
        ip_adapter_image_embeds (`List[ms.Tensor]`, *optional*):
            Pre-generated image embeddings for IP-Adapter. If not provided, embeddings are computed from the
            `ip_adapter_image` input argument.
        output_type (`str`, *optional*, defaults to `"pil"`):
            The output format of the generated video. Choose between
            [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
        return_dict (`bool`, *optional*, defaults to `False`):
            Whether or not to return a [`~pipelines.stable_diffusion_xl.AnimateDiffPipelineOutput`] instead of a
            plain tuple.
        cross_attention_kwargs (`dict`, *optional*):
            A kwargs dictionary that if specified is passed along to the `AttentionProcessor` as defined under
            `self.processor` in
            [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
        guidance_rescale (`float`, *optional*, defaults to 0.0):
            Guidance rescale factor proposed by [Common Diffusion Noise Schedules and Sample Steps are
            Flawed](https://arxiv.org/pdf/2305.08891.pdf) `guidance_scale` is defined as `φ` in equation 16. of
            [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://arxiv.org/pdf/2305.08891.pdf).
            Guidance rescale factor should fix overexposure when using zero terminal SNR.
        original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
            If `original_size` is not the same as `target_size` the image will appear to be down- or upsampled.
            `original_size` defaults to `(height, width)` if not specified. Part of SDXL's micro-conditioning as
            explained in section 2.2 of
            [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
        crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
            `crops_coords_top_left` can be used to generate an image that appears to be "cropped" from the position
            `crops_coords_top_left` downwards. Favorable, well-centered images are usually achieved by setting
            `crops_coords_top_left` to (0, 0). Part of SDXL's micro-conditioning as explained in section 2.2 of
            [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
        target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
            For most cases, `target_size` should be set to the desired height and width of the generated image. If
            not specified it will default to `(height, width)`. Part of SDXL's micro-conditioning as explained in
            section 2.2 of [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
        negative_original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
            To negatively condition the generation process based on a specific image resolution. Part of SDXL's
            micro-conditioning as explained in section 2.2 of
            [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952). For more
            information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.
        negative_crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
            To negatively condition the generation process based on a specific crop coordinates. Part of SDXL's
            micro-conditioning as explained in section 2.2 of
            [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952). For more
            information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.
        negative_target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
            To negatively condition the generation process based on a target image resolution. It should be as same
            as the `target_size` for most cases. Part of SDXL's micro-conditioning as explained in section 2.2 of
            [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952). For more
            information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.
        callback_on_step_end (`Callable`, *optional*):
            A function that calls at the end of each denoising steps during the inference. The function is called
            with the following arguments: `callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int,
            callback_kwargs: Dict)`. `callback_kwargs` will include a list of all tensors as specified by
            `callback_on_step_end_tensor_inputs`.
        callback_on_step_end_tensor_inputs (`List`, *optional*):
            The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
            will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
            `._callback_tensor_inputs` attribute of your pipeline class.

    Examples:

    Returns:
        [`~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput`] or `tuple`:
            If `return_dict` is `True`, [`~pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput`] is
            returned, otherwise a `tuple` is returned where the first element is a list with the generated frames.
    """

    # 0. Default height and width to unet
    height = height or self.default_sample_size * self.vae_scale_factor
    width = width or self.default_sample_size * self.vae_scale_factor

    num_videos_per_prompt = 1

    original_size = original_size or (height, width)
    target_size = target_size or (height, width)

    # 1. Check inputs. Raise error if not correct
    self.check_inputs(
        prompt,
        prompt_2,
        height,
        width,
        negative_prompt,
        negative_prompt_2,
        prompt_embeds,
        negative_prompt_embeds,
        pooled_prompt_embeds,
        negative_pooled_prompt_embeds,
        callback_on_step_end_tensor_inputs,
    )

    self._guidance_scale = guidance_scale
    self._guidance_rescale = guidance_rescale
    self._clip_skip = clip_skip
    self._cross_attention_kwargs = cross_attention_kwargs
    self._denoising_end = denoising_end
    self._interrupt = False

    # 2. Define call parameters
    if prompt is not None and isinstance(prompt, str):
        batch_size = 1
    elif prompt is not None and isinstance(prompt, list):
        batch_size = len(prompt)
    else:
        batch_size = prompt_embeds.shape[0]

    # 3. Encode input prompt
    lora_scale = self.cross_attention_kwargs.get("scale", None) if self.cross_attention_kwargs is not None else None

    (
        prompt_embeds,
        negative_prompt_embeds,
        pooled_prompt_embeds,
        negative_pooled_prompt_embeds,
    ) = self.encode_prompt(
        prompt=prompt,
        prompt_2=prompt_2,
        num_videos_per_prompt=num_videos_per_prompt,
        do_classifier_free_guidance=self.do_classifier_free_guidance,
        negative_prompt=negative_prompt,
        negative_prompt_2=negative_prompt_2,
        prompt_embeds=prompt_embeds,
        negative_prompt_embeds=negative_prompt_embeds,
        pooled_prompt_embeds=pooled_prompt_embeds,
        negative_pooled_prompt_embeds=negative_pooled_prompt_embeds,
        lora_scale=lora_scale,
        clip_skip=self.clip_skip,
    )

    # 4. Prepare timesteps
    timesteps, num_inference_steps = retrieve_timesteps(self.scheduler, num_inference_steps, timesteps, sigmas)

    # 5. Prepare latent variables
    num_channels_latents = self.unet.config.in_channels
    latents = self.prepare_latents(
        batch_size * num_videos_per_prompt,
        num_channels_latents,
        num_frames,
        height,
        width,
        prompt_embeds.dtype,
        generator,
        latents,
    )

    # 6. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
    extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)

    # 7. Prepare added time ids & embeddings
    add_text_embeds = pooled_prompt_embeds
    if self.text_encoder_2 is None:
        text_encoder_projection_dim = int(pooled_prompt_embeds.shape[-1])
    else:
        text_encoder_projection_dim = self.text_encoder_2.config.projection_dim

    add_time_ids = self._get_add_time_ids(
        original_size,
        crops_coords_top_left,
        target_size,
        dtype=prompt_embeds.dtype,
        text_encoder_projection_dim=text_encoder_projection_dim,
    )
    if negative_original_size is not None and negative_target_size is not None:
        negative_add_time_ids = self._get_add_time_ids(
            negative_original_size,
            negative_crops_coords_top_left,
            negative_target_size,
            dtype=prompt_embeds.dtype,
            text_encoder_projection_dim=text_encoder_projection_dim,
        )
    else:
        negative_add_time_ids = add_time_ids

    if self.do_classifier_free_guidance:
        prompt_embeds = ops.cat([negative_prompt_embeds, prompt_embeds], axis=0)
        add_text_embeds = ops.cat([negative_pooled_prompt_embeds, add_text_embeds], axis=0)
        add_time_ids = ops.cat([negative_add_time_ids, add_time_ids], axis=0)

    add_time_ids = add_time_ids.tile((batch_size * num_videos_per_prompt, 1))

    if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
        image_embeds = self.prepare_ip_adapter_image_embeds(
            ip_adapter_image,
            ip_adapter_image_embeds,
            batch_size * num_videos_per_prompt,
            self.do_classifier_free_guidance,
        )

    # 7.1 Apply denoising_end
    if (
        self.denoising_end is not None
        and isinstance(self.denoising_end, float)
        and self.denoising_end > 0
        and self.denoising_end < 1
    ):
        discrete_timestep_cutoff = int(
            round(
                self.scheduler.config.num_train_timesteps
                - (self.denoising_end * self.scheduler.config.num_train_timesteps)
            )
        )
        num_inference_steps = len(list(filter(lambda ts: ts >= discrete_timestep_cutoff, timesteps)))
        timesteps = timesteps[:num_inference_steps]

    # 8. Optionally get Guidance Scale Embedding
    timestep_cond = None
    if self.unet.config.time_cond_proj_dim is not None:
        guidance_scale_tensor = ms.Tensor(self.guidance_scale - 1).tile((batch_size * num_videos_per_prompt))
        timestep_cond = self.get_guidance_scale_embedding(
            guidance_scale_tensor, embedding_dim=self.unet.config.time_cond_proj_dim
        ).to(dtype=latents.dtype)

    self._num_timesteps = len(timesteps)

    # 9. Denoising loop
    with self.progress_bar(total=self._num_timesteps) as progress_bar:
        for i, t in enumerate(timesteps):
            if self.interrupt:
                continue

            # expand the latents if we are doing classifier free guidance
            latent_model_input = ops.cat([latents] * 2) if self.do_classifier_free_guidance else latents

            latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)

            # predict the noise residual
            added_cond_kwargs = {"text_embeds": add_text_embeds, "time_ids": add_time_ids}
            if ip_adapter_image is not None or ip_adapter_image_embeds:
                added_cond_kwargs["image_embeds"] = image_embeds

            noise_pred = self.unet(
                latent_model_input,
                t,
                encoder_hidden_states=prompt_embeds,
                timestep_cond=timestep_cond,
                cross_attention_kwargs=self.cross_attention_kwargs,
                added_cond_kwargs=ms.mutable(added_cond_kwargs),
                return_dict=False,
            )[0]

            # perform guidance
            if self.do_classifier_free_guidance:
                noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
                noise_pred = noise_pred_uncond + self.guidance_scale * (noise_pred_text - noise_pred_uncond)

            if self.do_classifier_free_guidance and self.guidance_rescale > 0.0:
                # Based on 3.4. in https://arxiv.org/pdf/2305.08891.pdf
                noise_pred = rescale_noise_cfg(noise_pred, noise_pred_text, guidance_rescale=self.guidance_rescale)

            # compute the previous noisy sample x_t -> x_t-1
            latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]

            if callback_on_step_end is not None:
                callback_kwargs = {}
                for k in callback_on_step_end_tensor_inputs:
                    callback_kwargs[k] = locals()[k]
                callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)

                latents = callback_outputs.pop("latents", latents)
                prompt_embeds = callback_outputs.pop("prompt_embeds", prompt_embeds)
                negative_prompt_embeds = callback_outputs.pop("negative_prompt_embeds", negative_prompt_embeds)
                add_text_embeds = callback_outputs.pop("add_text_embeds", add_text_embeds)
                negative_pooled_prompt_embeds = callback_outputs.pop(
                    "negative_pooled_prompt_embeds", negative_pooled_prompt_embeds
                )
                add_time_ids = callback_outputs.pop("add_time_ids", add_time_ids)
                negative_add_time_ids = callback_outputs.pop("negative_add_time_ids", negative_add_time_ids)

            progress_bar.update()

    # make sure the VAE is in float32 mode, as it overflows in float16
    needs_upcasting = self.vae.dtype == ms.float16 and self.vae.config.force_upcast

    if needs_upcasting:
        self.upcast_vae()
        latents = latents.to(next(iter(self.vae.post_quant_conv.get_parameters())).dtype)

    # 10. Post processing
    if output_type == "latent":
        video = latents
    else:
        video_tensor = self.decode_latents(latents)
        video = self.video_processor.postprocess_video(video=video_tensor, output_type=output_type)

    # cast back to fp16 if needed
    if needs_upcasting:
        self.vae.to(dtype=ms.float16)

    if not return_dict:
        return (video,)

    return AnimateDiffPipelineOutput(frames=video)

mindone.diffusers.pipelines.AnimateDiffSDXLPipeline.encode_prompt(prompt, prompt_2=None, num_videos_per_prompt=1, do_classifier_free_guidance=True, negative_prompt=None, negative_prompt_2=None, prompt_embeds=None, negative_prompt_embeds=None, pooled_prompt_embeds=None, negative_pooled_prompt_embeds=None, lora_scale=None, clip_skip=None)

Encodes the prompt into text encoder hidden states.

PARAMETER DESCRIPTION
prompt

prompt to be encoded

TYPE: `str` or `List[str]`, *optional*

prompt_2

The prompt or prompts to be sent to the tokenizer_2 and text_encoder_2. If not defined, prompt is used in both text-encoders

TYPE: `str` or `List[str]`, *optional* DEFAULT: None

num_videos_per_prompt

number of images that should be generated per prompt

TYPE: `int` DEFAULT: 1

do_classifier_free_guidance

whether to use classifier free guidance or not

TYPE: `bool` DEFAULT: True

negative_prompt

The prompt or prompts not to guide the image generation. If not defined, one has to pass negative_prompt_embeds instead. Ignored when not using guidance (i.e., ignored if guidance_scale is less than 1).

TYPE: `str` or `List[str]`, *optional* DEFAULT: None

negative_prompt_2

The prompt or prompts not to guide the image generation to be sent to tokenizer_2 and text_encoder_2. If not defined, negative_prompt is used in both text-encoders

TYPE: `str` or `List[str]`, *optional* DEFAULT: None

prompt_embeds

Pre-generated text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, text embeddings will be generated from prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

negative_prompt_embeds

Pre-generated negative text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, negative_prompt_embeds will be generated from negative_prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

pooled_prompt_embeds

Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, pooled text embeddings will be generated from prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

negative_pooled_prompt_embeds

Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, pooled negative_prompt_embeds will be generated from negative_prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

lora_scale

A lora scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.

TYPE: `float`, *optional* DEFAULT: None

clip_skip

Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that the output of the pre-final layer will be used for computing the prompt embeddings.

TYPE: `int`, *optional* DEFAULT: None

Source code in mindone/diffusers/pipelines/animatediff/pipeline_animatediff_sdxl.py 
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
def encode_prompt(
    self,
    prompt: str,
    prompt_2: Optional[str] = None,
    num_videos_per_prompt: int = 1,
    do_classifier_free_guidance: bool = True,
    negative_prompt: Optional[str] = None,
    negative_prompt_2: Optional[str] = None,
    prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    pooled_prompt_embeds: Optional[ms.Tensor] = None,
    negative_pooled_prompt_embeds: Optional[ms.Tensor] = None,
    lora_scale: Optional[float] = None,
    clip_skip: Optional[int] = None,
):
    r"""
    Encodes the prompt into text encoder hidden states.

    Args:
        prompt (`str` or `List[str]`, *optional*):
            prompt to be encoded
        prompt_2 (`str` or `List[str]`, *optional*):
            The prompt or prompts to be sent to the `tokenizer_2` and `text_encoder_2`. If not defined, `prompt` is
            used in both text-encoders
        num_videos_per_prompt (`int`):
            number of images that should be generated per prompt
        do_classifier_free_guidance (`bool`):
            whether to use classifier free guidance or not
        negative_prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts not to guide the image generation. If not defined, one has to pass
            `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
            less than `1`).
        negative_prompt_2 (`str` or `List[str]`, *optional*):
            The prompt or prompts not to guide the image generation to be sent to `tokenizer_2` and
            `text_encoder_2`. If not defined, `negative_prompt` is used in both text-encoders
        prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
            provided, text embeddings will be generated from `prompt` input argument.
        negative_prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
            weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
            argument.
        pooled_prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
            If not provided, pooled text embeddings will be generated from `prompt` input argument.
        negative_pooled_prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
            weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_prompt`
            input argument.
        lora_scale (`float`, *optional*):
            A lora scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
        clip_skip (`int`, *optional*):
            Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
            the output of the pre-final layer will be used for computing the prompt embeddings.
    """

    # set lora scale so that monkey patched LoRA
    # function of text encoder can correctly access it
    if lora_scale is not None and isinstance(self, StableDiffusionXLLoraLoaderMixin):
        self._lora_scale = lora_scale

        # dynamically adjust the LoRA scale
        if self.text_encoder is not None:
            scale_lora_layers(self.text_encoder, lora_scale)

        if self.text_encoder_2 is not None:
            scale_lora_layers(self.text_encoder_2, lora_scale)

    prompt = [prompt] if isinstance(prompt, str) else prompt

    if prompt is not None:
        batch_size = len(prompt)
    else:
        batch_size = prompt_embeds.shape[0]

    # Define tokenizers and text encoders
    tokenizers = [self.tokenizer, self.tokenizer_2] if self.tokenizer is not None else [self.tokenizer_2]
    text_encoders = (
        [self.text_encoder, self.text_encoder_2] if self.text_encoder is not None else [self.text_encoder_2]
    )

    if prompt_embeds is None:
        prompt_2 = prompt_2 or prompt
        prompt_2 = [prompt_2] if isinstance(prompt_2, str) else prompt_2

        # textual inversion: process multi-vector tokens if necessary
        prompt_embeds_list = []
        prompts = [prompt, prompt_2]
        for prompt, tokenizer, text_encoder in zip(prompts, tokenizers, text_encoders):
            if isinstance(self, TextualInversionLoaderMixin):
                prompt = self.maybe_convert_prompt(prompt, tokenizer)

            text_inputs = tokenizer(
                prompt,
                padding="max_length",
                max_length=tokenizer.model_max_length,
                truncation=True,
                return_tensors="np",
            )

            text_input_ids = text_inputs.input_ids
            untruncated_ids = tokenizer(prompt, padding="longest", return_tensors="np").input_ids

            if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not np.array_equal(
                text_input_ids, untruncated_ids
            ):
                removed_text = tokenizer.batch_decode(untruncated_ids[:, tokenizer.model_max_length - 1 : -1])
                logger.warning(
                    "The following part of your input was truncated because CLIP can only handle sequences up to"
                    f" {tokenizer.model_max_length} tokens: {removed_text}"
                )

            prompt_embeds = text_encoder(ms.tensor(text_input_ids), output_hidden_states=True)

            # We are only ALWAYS interested in the pooled output of the final text encoder
            pooled_prompt_embeds = prompt_embeds[0]
            if clip_skip is None:
                prompt_embeds = prompt_embeds[2][-2]
            else:
                # "2" because SDXL always indexes from the penultimate layer.
                prompt_embeds = prompt_embeds[2][-(clip_skip + 2)]

            prompt_embeds_list.append(prompt_embeds)

        prompt_embeds = ops.concat(prompt_embeds_list, axis=-1)

    # get unconditional embeddings for classifier free guidance
    zero_out_negative_prompt = negative_prompt is None and self.config.force_zeros_for_empty_prompt
    if do_classifier_free_guidance and negative_prompt_embeds is None and zero_out_negative_prompt:
        negative_prompt_embeds = ops.zeros_like(prompt_embeds)
        negative_pooled_prompt_embeds = ops.zeros_like(pooled_prompt_embeds)
    elif do_classifier_free_guidance and negative_prompt_embeds is None:
        negative_prompt = negative_prompt or ""
        negative_prompt_2 = negative_prompt_2 or negative_prompt

        # normalize str to list
        negative_prompt = batch_size * [negative_prompt] if isinstance(negative_prompt, str) else negative_prompt
        negative_prompt_2 = (
            batch_size * [negative_prompt_2] if isinstance(negative_prompt_2, str) else negative_prompt_2
        )

        uncond_tokens: List[str]
        if prompt is not None and type(prompt) is not type(negative_prompt):
            raise TypeError(
                f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
                f" {type(prompt)}."
            )
        elif batch_size != len(negative_prompt):
            raise ValueError(
                f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
                f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
                " the batch size of `prompt`."
            )
        else:
            uncond_tokens = [negative_prompt, negative_prompt_2]

        negative_prompt_embeds_list = []
        for negative_prompt, tokenizer, text_encoder in zip(uncond_tokens, tokenizers, text_encoders):
            if isinstance(self, TextualInversionLoaderMixin):
                negative_prompt = self.maybe_convert_prompt(negative_prompt, tokenizer)

            max_length = prompt_embeds.shape[1]
            uncond_input = tokenizer(
                negative_prompt,
                padding="max_length",
                max_length=max_length,
                truncation=True,
                return_tensors="np",
            )

            negative_prompt_embeds = text_encoder(
                ms.Tensor.from_numpy(uncond_input.input_ids),
                output_hidden_states=True,
            )
            # We are only ALWAYS interested in the pooled output of the final text encoder
            negative_pooled_prompt_embeds = negative_prompt_embeds[0]
            negative_prompt_embeds = negative_prompt_embeds[2][-2]

            negative_prompt_embeds_list.append(negative_prompt_embeds)

        negative_prompt_embeds = ops.concat(negative_prompt_embeds_list, axis=-1)

    if self.text_encoder_2 is not None:
        prompt_embeds = prompt_embeds.to(dtype=self.text_encoder_2.dtype)
    else:
        prompt_embeds = prompt_embeds.to(dtype=self.unet.dtype)

    bs_embed, seq_len, _ = prompt_embeds.shape
    # duplicate text embeddings for each generation per prompt, using mps friendly method
    prompt_embeds = prompt_embeds.tile((1, num_videos_per_prompt, 1))
    prompt_embeds = prompt_embeds.view(bs_embed * num_videos_per_prompt, seq_len, -1)

    if do_classifier_free_guidance:
        # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
        seq_len = negative_prompt_embeds.shape[1]

        if self.text_encoder_2 is not None:
            negative_prompt_embeds = negative_prompt_embeds.to(dtype=self.text_encoder_2.dtype)
        else:
            negative_prompt_embeds = negative_prompt_embeds.to(dtype=self.unet.dtype)

        negative_prompt_embeds = negative_prompt_embeds.tile((1, num_videos_per_prompt, 1))
        negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_videos_per_prompt, seq_len, -1)

    pooled_prompt_embeds = pooled_prompt_embeds.tile((1, num_videos_per_prompt)).view(
        bs_embed * num_videos_per_prompt, -1
    )
    if do_classifier_free_guidance:
        negative_pooled_prompt_embeds = negative_pooled_prompt_embeds.tile((1, num_videos_per_prompt)).view(
            bs_embed * num_videos_per_prompt, -1
        )

    if self.text_encoder is not None:
        if isinstance(self, StableDiffusionXLLoraLoaderMixin):
            # Retrieve the original scale by scaling back the LoRA layers
            unscale_lora_layers(self.text_encoder, lora_scale)

    if self.text_encoder_2 is not None:
        if isinstance(self, StableDiffusionXLLoraLoaderMixin):
            # Retrieve the original scale by scaling back the LoRA layers
            unscale_lora_layers(self.text_encoder_2, lora_scale)

    return prompt_embeds, negative_prompt_embeds, pooled_prompt_embeds, negative_pooled_prompt_embeds

mindone.diffusers.pipelines.AnimateDiffSDXLPipeline.get_guidance_scale_embedding(w, embedding_dim=512, dtype=ms.float32)

See https://github.com/google-research/vdm/blob/dc27b98a554f65cdc654b800da5aa1846545d41b/model_vdm.py#L298

PARAMETER DESCRIPTION
w

Generate embedding vectors with a specified guidance scale to subsequently enrich timestep embeddings.

TYPE: `ms.Tensor`

embedding_dim

Dimension of the embeddings to generate.

TYPE: `int`, *optional*, defaults to 512 DEFAULT: 512

dtype

Data type of the generated embeddings.

TYPE: `mindspore.dtype`, *optional*, defaults to `mindspore.float32` DEFAULT: float32

RETURNS DESCRIPTION
Tensor

ms.Tensor: Embedding vectors with shape (len(w), embedding_dim).
Source code in mindone/diffusers/pipelines/animatediff/pipeline_animatediff_sdxl.py 
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
def get_guidance_scale_embedding(
    self, w: ms.Tensor, embedding_dim: int = 512, dtype: ms.Type = ms.float32
) -> ms.Tensor:
    """
    See https://github.com/google-research/vdm/blob/dc27b98a554f65cdc654b800da5aa1846545d41b/model_vdm.py#L298

    Args:
        w (`ms.Tensor`):
            Generate embedding vectors with a specified guidance scale to subsequently enrich timestep embeddings.
        embedding_dim (`int`, *optional*, defaults to 512):
            Dimension of the embeddings to generate.
        dtype (`mindspore.dtype`, *optional*, defaults to `mindspore.float32`):
            Data type of the generated embeddings.

    Returns:
        `ms.Tensor`: Embedding vectors with shape `(len(w), embedding_dim)`.
    """
    assert len(w.shape) == 1
    w = w * 1000.0

    half_dim = embedding_dim // 2
    emb = ops.log(ms.Tensor(10000.0)) / (half_dim - 1)
    emb = ops.exp(ops.arange(half_dim, dtype=dtype) * -emb)
    emb = w.to(dtype)[:, None] * emb[None, :]
    emb = ops.cat([ops.sin(emb), ops.cos(emb)], axis=1)
    if embedding_dim % 2 == 1:  # zero pad
        emb = ms.mint.nn.functional.pad(emb, (0, 1))
    assert emb.shape == (w.shape[0], embedding_dim)
    return emb

mindone.diffusers.pipelines.AnimateDiffVideoToVideoPipeline

Bases: DiffusionPipeline, StableDiffusionMixin, TextualInversionLoaderMixin, IPAdapterMixin, LoraLoaderMixin

Pipeline for video-to-video generation.

This model inherits from [DiffusionPipeline]. Check the superclass documentation for the generic methods implemented for all pipelines (downloading, saving, running on a particular device, etc.).

The pipeline also inherits the following loading methods
  • [~loaders.TextualInversionLoaderMixin.load_textual_inversion] for loading textual inversion embeddings
  • [~loaders.LoraLoaderMixin.load_lora_weights] for loading LoRA weights
  • [~loaders.LoraLoaderMixin.save_lora_weights] for saving LoRA weights
  • [~loaders.IPAdapterMixin.load_ip_adapter] for loading IP Adapters
PARAMETER DESCRIPTION
vae

Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.

TYPE: [`AutoencoderKL`]

text_encoder

Frozen text-encoder (clip-vit-large-patch14).

TYPE: [`CLIPTextModel`]

tokenizer

A [~transformers.CLIPTokenizer] to tokenize text.

TYPE: `CLIPTokenizer`

unet

A [UNet2DConditionModel] used to create a UNetMotionModel to denoise the encoded video latents.

TYPE: [`UNet2DConditionModel`]

motion_adapter

A [MotionAdapter] to be used in combination with unet to denoise the encoded video latents.

TYPE: [`MotionAdapter`]

scheduler

A scheduler to be used in combination with unet to denoise the encoded image latents. Can be one of [DDIMScheduler], [LMSDiscreteScheduler], or [PNDMScheduler].

TYPE: [`SchedulerMixin`]

Source code in mindone/diffusers/pipelines/animatediff/pipeline_animatediff_video2video.py 
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
class AnimateDiffVideoToVideoPipeline(
    DiffusionPipeline,
    StableDiffusionMixin,
    TextualInversionLoaderMixin,
    IPAdapterMixin,
    LoraLoaderMixin,
):
    r"""
    Pipeline for video-to-video generation.

    This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods
    implemented for all pipelines (downloading, saving, running on a particular device, etc.).

    The pipeline also inherits the following loading methods:
        - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
        - [`~loaders.LoraLoaderMixin.load_lora_weights`] for loading LoRA weights
        - [`~loaders.LoraLoaderMixin.save_lora_weights`] for saving LoRA weights
        - [`~loaders.IPAdapterMixin.load_ip_adapter`] for loading IP Adapters

    Args:
        vae ([`AutoencoderKL`]):
            Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
        text_encoder ([`CLIPTextModel`]):
            Frozen text-encoder ([clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14)).
        tokenizer (`CLIPTokenizer`):
            A [`~transformers.CLIPTokenizer`] to tokenize text.
        unet ([`UNet2DConditionModel`]):
            A [`UNet2DConditionModel`] used to create a UNetMotionModel to denoise the encoded video latents.
        motion_adapter ([`MotionAdapter`]):
            A [`MotionAdapter`] to be used in combination with `unet` to denoise the encoded video latents.
        scheduler ([`SchedulerMixin`]):
            A scheduler to be used in combination with `unet` to denoise the encoded image latents. Can be one of
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
    """

    model_cpu_offload_seq = "text_encoder->image_encoder->unet->vae"
    _optional_components = ["feature_extractor", "image_encoder", "motion_adapter"]
    _callback_tensor_inputs = ["latents", "prompt_embeds", "negative_prompt_embeds"]

    def __init__(
        self,
        vae: AutoencoderKL,
        text_encoder: CLIPTextModel,
        tokenizer: CLIPTokenizer,
        unet: UNet2DConditionModel,
        motion_adapter: MotionAdapter,
        scheduler: Union[
            DDIMScheduler,
            PNDMScheduler,
            LMSDiscreteScheduler,
            EulerDiscreteScheduler,
            EulerAncestralDiscreteScheduler,
            DPMSolverMultistepScheduler,
        ],
        feature_extractor: CLIPImageProcessor = None,
        image_encoder: CLIPVisionModelWithProjection = None,
    ):
        super().__init__()
        if isinstance(unet, UNet2DConditionModel):
            unet = UNetMotionModel.from_unet2d(unet, motion_adapter)

        self.register_modules(
            vae=vae,
            text_encoder=text_encoder,
            tokenizer=tokenizer,
            unet=unet,
            motion_adapter=motion_adapter,
            scheduler=scheduler,
            feature_extractor=feature_extractor,
            image_encoder=image_encoder,
        )
        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
        self.video_processor = VideoProcessor(vae_scale_factor=self.vae_scale_factor)

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_prompt with num_images_per_prompt -> num_videos_per_prompt  # noqa: E501
    def encode_prompt(
        self,
        prompt,
        num_images_per_prompt,
        do_classifier_free_guidance,
        negative_prompt=None,
        prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        lora_scale: Optional[float] = None,
        clip_skip: Optional[int] = None,
    ):
        r"""
        Encodes the prompt into text encoder hidden states.

        Args:
            prompt (`str` or `List[str]`, *optional*):
                prompt to be encoded
            num_images_per_prompt (`int`):
                number of images that should be generated per prompt
            do_classifier_free_guidance (`bool`):
                whether to use classifier free guidance or not
            negative_prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts not to guide the image generation. If not defined, one has to pass
                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
                less than `1`).
            prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                provided, text embeddings will be generated from `prompt` input argument.
            negative_prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                argument.
            lora_scale (`float`, *optional*):
                A LoRA scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
            clip_skip (`int`, *optional*):
                Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
                the output of the pre-final layer will be used for computing the prompt embeddings.
        """
        # set lora scale so that monkey patched LoRA
        # function of text encoder can correctly access it
        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
            self._lora_scale = lora_scale

            # dynamically adjust the LoRA scale
            scale_lora_layers(self.text_encoder, lora_scale)

        if prompt is not None and isinstance(prompt, str):
            batch_size = 1
        elif prompt is not None and isinstance(prompt, list):
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        if prompt_embeds is None:
            # textual inversion: process multi-vector tokens if necessary
            if isinstance(self, TextualInversionLoaderMixin):
                prompt = self.maybe_convert_prompt(prompt, self.tokenizer)

            text_inputs = self.tokenizer(
                prompt,
                padding="max_length",
                max_length=self.tokenizer.model_max_length,
                truncation=True,
                return_tensors="np",
            )
            text_input_ids = text_inputs.input_ids
            untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="np").input_ids

            if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not np.array_equal(
                text_input_ids, untruncated_ids
            ):
                removed_text = self.tokenizer.batch_decode(untruncated_ids[:, self.tokenizer.model_max_length - 1 : -1])
                logger.warning(
                    "The following part of your input was truncated because CLIP can only handle sequences up to"
                    f" {self.tokenizer.model_max_length} tokens: {removed_text}"
                )

            if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
                attention_mask = ms.Tensor(text_inputs.attention_mask)
            else:
                attention_mask = None

            if clip_skip is None:
                prompt_embeds = self.text_encoder(ms.Tensor(text_input_ids), attention_mask=attention_mask)
                prompt_embeds = prompt_embeds[0]
            else:
                prompt_embeds = self.text_encoder(
                    ms.Tensor(text_input_ids), attention_mask=attention_mask, output_hidden_states=True
                )
                # Access the `hidden_states` first, that contains a tuple of
                # all the hidden states from the encoder layers. Then index into
                # the tuple to access the hidden states from the desired layer.
                prompt_embeds = prompt_embeds[-1][-(clip_skip + 1)]
                # We also need to apply the final LayerNorm here to not mess with the
                # representations. The `last_hidden_states` that we typically use for
                # obtaining the final prompt representations passes through the LayerNorm
                # layer.
                prompt_embeds = self.text_encoder.text_model.final_layer_norm(prompt_embeds)

        if self.text_encoder is not None:
            prompt_embeds_dtype = self.text_encoder.dtype
        elif self.unet is not None:
            prompt_embeds_dtype = self.unet.dtype
        else:
            prompt_embeds_dtype = prompt_embeds.dtype

        prompt_embeds = prompt_embeds.to(dtype=prompt_embeds_dtype)

        bs_embed, seq_len, _ = prompt_embeds.shape
        # duplicate text embeddings for each generation per prompt, using mps friendly method
        prompt_embeds = prompt_embeds.tile((1, num_images_per_prompt, 1))
        prompt_embeds = prompt_embeds.view(bs_embed * num_images_per_prompt, seq_len, -1)

        # get unconditional embeddings for classifier free guidance
        if do_classifier_free_guidance and negative_prompt_embeds is None:
            uncond_tokens: List[str]
            if negative_prompt is None:
                uncond_tokens = [""] * batch_size
            elif prompt is not None and type(prompt) is not type(negative_prompt):
                raise TypeError(
                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
                    f" {type(prompt)}."
                )
            elif isinstance(negative_prompt, str):
                uncond_tokens = [negative_prompt]
            elif batch_size != len(negative_prompt):
                raise ValueError(
                    f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
                    f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
                    " the batch size of `prompt`."
                )
            else:
                uncond_tokens = negative_prompt

            # textual inversion: process multi-vector tokens if necessary
            if isinstance(self, TextualInversionLoaderMixin):
                uncond_tokens = self.maybe_convert_prompt(uncond_tokens, self.tokenizer)

            max_length = prompt_embeds.shape[1]
            uncond_input = self.tokenizer(
                uncond_tokens,
                padding="max_length",
                max_length=max_length,
                truncation=True,
                return_tensors="np",
            )

            if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
                attention_mask = ms.Tensor(uncond_input.attention_mask)
            else:
                attention_mask = None

            negative_prompt_embeds = self.text_encoder(
                ms.Tensor(uncond_input.input_ids),
                attention_mask=attention_mask,
            )
            negative_prompt_embeds = negative_prompt_embeds[0]

        if do_classifier_free_guidance:
            # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
            seq_len = negative_prompt_embeds.shape[1]

            negative_prompt_embeds = negative_prompt_embeds.to(dtype=prompt_embeds_dtype)

            negative_prompt_embeds = negative_prompt_embeds.tile((1, num_images_per_prompt, 1))
            negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)

        if self.text_encoder is not None:
            if isinstance(self, LoraLoaderMixin):
                # Retrieve the original scale by scaling back the LoRA layers
                unscale_lora_layers(self.text_encoder, lora_scale)

        return prompt_embeds, negative_prompt_embeds

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_image
    def encode_image(self, image, num_images_per_prompt, output_hidden_states=None):
        dtype = next(self.image_encoder.get_parameters()).dtype

        if not isinstance(image, ms.Tensor):
            image = self.feature_extractor(image, return_tensors="np").pixel_values
            image = ms.Tensor(image)

        image = image.to(dtype=dtype)
        if output_hidden_states:
            image_enc_hidden_states = self.image_encoder(image, output_hidden_states=True)[2][-2]
            image_enc_hidden_states = image_enc_hidden_states.repeat_interleave(num_images_per_prompt, dim=0)
            uncond_image_enc_hidden_states = self.image_encoder(ops.zeros_like(image), output_hidden_states=True)[2][-2]
            uncond_image_enc_hidden_states = uncond_image_enc_hidden_states.repeat_interleave(
                num_images_per_prompt, dim=0
            )
            return image_enc_hidden_states, uncond_image_enc_hidden_states
        else:
            image_embeds = self.image_encoder(image)[0]
            image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
            uncond_image_embeds = ops.zeros_like(image_embeds)

            return image_embeds, uncond_image_embeds

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_ip_adapter_image_embeds
    def prepare_ip_adapter_image_embeds(
        self, ip_adapter_image, ip_adapter_image_embeds, num_images_per_prompt, do_classifier_free_guidance
    ):
        if ip_adapter_image_embeds is None:
            if not isinstance(ip_adapter_image, list):
                ip_adapter_image = [ip_adapter_image]

            if len(ip_adapter_image) != len(self.unet.encoder_hid_proj.image_projection_layers):
                raise ValueError(
                    f"`ip_adapter_image` must have same length as the number of IP Adapters. Got {len(ip_adapter_image)} images and {len(self.unet.encoder_hid_proj.image_projection_layers)} IP Adapters."  # noqa: E501
                )

            image_embeds = []
            for single_ip_adapter_image, image_proj_layer in zip(
                ip_adapter_image, self.unet.encoder_hid_proj.image_projection_layers
            ):
                output_hidden_state = not isinstance(image_proj_layer, ImageProjection)
                single_image_embeds, single_negative_image_embeds = self.encode_image(
                    single_ip_adapter_image, 1, output_hidden_state
                )
                single_image_embeds = ops.stack([single_image_embeds] * num_images_per_prompt, axis=0)
                single_negative_image_embeds = ops.stack([single_negative_image_embeds] * num_images_per_prompt, axis=0)

                if do_classifier_free_guidance:
                    single_image_embeds = ops.cat([single_negative_image_embeds, single_image_embeds])

                image_embeds.append(single_image_embeds)
        else:
            repeat_dims = [1]
            image_embeds = []
            for single_image_embeds in ip_adapter_image_embeds:
                if do_classifier_free_guidance:
                    single_negative_image_embeds, single_image_embeds = single_image_embeds.chunk(2)
                    single_image_embeds = single_image_embeds.tile(
                        (num_images_per_prompt, *(repeat_dims * len(single_image_embeds.shape[1:])))
                    )
                    single_negative_image_embeds = single_negative_image_embeds.tile(
                        (num_images_per_prompt, *(repeat_dims * len(single_negative_image_embeds.shape[1:])))
                    )
                    single_image_embeds = ops.cat([single_negative_image_embeds, single_image_embeds])
                else:
                    single_image_embeds = single_image_embeds.tile(
                        (num_images_per_prompt, *(repeat_dims * len(single_image_embeds.shape[1:])))
                    )
                image_embeds.append(single_image_embeds)

        return image_embeds

    # Copied from diffusers.pipelines.text_to_video_synthesis/pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
    def decode_latents(self, latents):
        latents = 1 / self.vae.config.scaling_factor * latents

        batch_size, channels, num_frames, height, width = latents.shape
        latents = latents.permute(0, 2, 1, 3, 4).reshape(batch_size * num_frames, channels, height, width)

        image = self.vae.decode(latents)[0]
        video = image[None, :].reshape((batch_size, num_frames, -1) + image.shape[2:]).permute(0, 2, 1, 3, 4)
        # we always cast to float32 as this does not cause significant overhead and is compatible with bfloat16
        video = video.float()
        return video

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
    def prepare_extra_step_kwargs(self, generator, eta):
        # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
        # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
        # and should be between [0, 1]

        accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
        extra_step_kwargs = {}
        if accepts_eta:
            extra_step_kwargs["eta"] = eta

        # check if the scheduler accepts generator
        accepts_generator = "generator" in set(inspect.signature(self.scheduler.step).parameters.keys())
        if accepts_generator:
            extra_step_kwargs["generator"] = generator
        return extra_step_kwargs

    def check_inputs(
        self,
        prompt,
        strength,
        height,
        width,
        video=None,
        latents=None,
        negative_prompt=None,
        prompt_embeds=None,
        negative_prompt_embeds=None,
        ip_adapter_image=None,
        ip_adapter_image_embeds=None,
        callback_on_step_end_tensor_inputs=None,
    ):
        if strength < 0 or strength > 1:
            raise ValueError(f"The value of strength should in [0.0, 1.0] but is {strength}")

        if height % 8 != 0 or width % 8 != 0:
            raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")

        if callback_on_step_end_tensor_inputs is not None and not all(
            k in self._callback_tensor_inputs for k in callback_on_step_end_tensor_inputs
        ):
            raise ValueError(
                f"`callback_on_step_end_tensor_inputs` has to be in {self._callback_tensor_inputs}, but found {[k for k in callback_on_step_end_tensor_inputs if k not in self._callback_tensor_inputs]}"  # noqa: E501
            )

        if prompt is not None and prompt_embeds is not None:
            raise ValueError(
                f"Cannot forward both `prompt`: {prompt} and `prompt_embeds`: {prompt_embeds}. Please make sure to"
                " only forward one of the two."
            )
        elif prompt is None and prompt_embeds is None:
            raise ValueError(
                "Provide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined."
            )
        elif prompt is not None and (not isinstance(prompt, str) and not isinstance(prompt, list)):
            raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")

        if negative_prompt is not None and negative_prompt_embeds is not None:
            raise ValueError(
                f"Cannot forward both `negative_prompt`: {negative_prompt} and `negative_prompt_embeds`:"
                f" {negative_prompt_embeds}. Please make sure to only forward one of the two."
            )

        if prompt_embeds is not None and negative_prompt_embeds is not None:
            if prompt_embeds.shape != negative_prompt_embeds.shape:
                raise ValueError(
                    "`prompt_embeds` and `negative_prompt_embeds` must have the same shape when passed directly, but"
                    f" got: `prompt_embeds` {prompt_embeds.shape} != `negative_prompt_embeds`"
                    f" {negative_prompt_embeds.shape}."
                )

        if video is not None and latents is not None:
            raise ValueError("Only one of `video` or `latents` should be provided")

        if ip_adapter_image is not None and ip_adapter_image_embeds is not None:
            raise ValueError(
                "Provide either `ip_adapter_image` or `ip_adapter_image_embeds`. Cannot leave both `ip_adapter_image` and `ip_adapter_image_embeds` defined."
            )

        if ip_adapter_image_embeds is not None:
            if not isinstance(ip_adapter_image_embeds, list):
                raise ValueError(
                    f"`ip_adapter_image_embeds` has to be of type `list` but is {type(ip_adapter_image_embeds)}"
                )
            elif ip_adapter_image_embeds[0].ndim not in [3, 4]:
                raise ValueError(
                    f"`ip_adapter_image_embeds` has to be a list of 3D or 4D tensors but is {ip_adapter_image_embeds[0].ndim}D"
                )

    def get_timesteps(self, num_inference_steps, timesteps, strength):
        # get the original timestep using init_timestep
        init_timestep = min(int(num_inference_steps * strength), num_inference_steps)

        t_start = max(num_inference_steps - init_timestep, 0)
        timesteps = timesteps[t_start * self.scheduler.order :]

        return timesteps, num_inference_steps - t_start

    def prepare_latents(
        self,
        video,
        height,
        width,
        num_channels_latents,
        batch_size,
        timestep,
        dtype,
        generator,
        latents=None,
    ):
        if latents is None:
            num_frames = video.shape[1]
        else:
            num_frames = latents.shape[2]

        shape = (
            batch_size,
            num_channels_latents,
            num_frames,
            height // self.vae_scale_factor,
            width // self.vae_scale_factor,
        )

        if isinstance(generator, list) and len(generator) != batch_size:
            raise ValueError(
                f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
                f" size of {batch_size}. Make sure the batch size matches the length of the generators."
            )

        if latents is None:
            # make sure the VAE is in float32 mode, as it overflows in float16
            if self.vae.config.force_upcast:
                video = video.float()
                self.vae.to(dtype=ms.float32)

            if isinstance(generator, list):
                if len(generator) != batch_size:
                    raise ValueError(
                        f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
                        f" size of {batch_size}. Make sure the batch size matches the length of the generators."
                    )

                init_latents = [
                    retrieve_latents(self.vae, self.vae.encode(video[i])[0], generator).unsqueeze(0)
                    for i in range(batch_size)
                ]
            else:
                init_latents = [
                    retrieve_latents(self.vae, self.vae.encode(vid)[0], generator).unsqueeze(0) for vid in video
                ]

            init_latents = ops.cat(init_latents, axis=0)

            # restore vae to original dtype
            if self.vae.config.force_upcast:
                self.vae.to(dtype)

            init_latents = init_latents.to(dtype)
            init_latents = self.vae.config.scaling_factor * init_latents

            if batch_size > init_latents.shape[0] and batch_size % init_latents.shape[0] == 0:
                # expand init_latents for batch_size
                error_message = (
                    f"You have passed {batch_size} text prompts (`prompt`), but only {init_latents.shape[0]} initial"
                    " images (`image`). Please make sure to update your script to pass as many initial images as text prompts"
                )
                raise ValueError(error_message)
            elif batch_size > init_latents.shape[0] and batch_size % init_latents.shape[0] != 0:
                raise ValueError(
                    f"Cannot duplicate `image` of batch size {init_latents.shape[0]} to {batch_size} text prompts."
                )
            else:
                init_latents = ops.cat([init_latents], axis=0)

            noise = randn_tensor(init_latents.shape, generator=generator, dtype=dtype)
            latents = self.scheduler.add_noise(init_latents, noise, timestep).permute(0, 2, 1, 3, 4)
        else:
            if shape != latents.shape:
                # [B, C, F, H, W]
                raise ValueError(f"`latents` expected to have {shape=}, but found {latents.shape=}")
            latents = latents.to(dtype=dtype)

        return latents

    @property
    def guidance_scale(self):
        return self._guidance_scale

    @property
    def clip_skip(self):
        return self._clip_skip

    # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
    # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
    # corresponds to doing no classifier free guidance.
    @property
    def do_classifier_free_guidance(self):
        return self._guidance_scale > 1

    @property
    def cross_attention_kwargs(self):
        return self._cross_attention_kwargs

    @property
    def num_timesteps(self):
        return self._num_timesteps

    def __call__(
        self,
        video: List[List[PipelineImageInput]] = None,
        prompt: Optional[Union[str, List[str]]] = None,
        height: Optional[int] = None,
        width: Optional[int] = None,
        num_inference_steps: int = 50,
        timesteps: Optional[List[int]] = None,
        sigmas: Optional[List[float]] = None,
        guidance_scale: float = 7.5,
        strength: float = 0.8,
        negative_prompt: Optional[Union[str, List[str]]] = None,
        num_videos_per_prompt: Optional[int] = 1,
        eta: float = 0.0,
        generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
        latents: Optional[ms.Tensor] = None,
        prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        ip_adapter_image: Optional[PipelineImageInput] = None,
        ip_adapter_image_embeds: Optional[List[ms.Tensor]] = None,
        output_type: Optional[str] = "pil",
        return_dict: bool = False,
        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
        clip_skip: Optional[int] = None,
        callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
    ):
        r"""
        The call function to the pipeline for generation.

        Args:
            video (`List[PipelineImageInput]`):
                The input video to condition the generation on. Must be a list of images/frames of the video.
            prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`.
            height (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
                The height in pixels of the generated video.
            width (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
                The width in pixels of the generated video.
            num_inference_steps (`int`, *optional*, defaults to 50):
                The number of denoising steps. More denoising steps usually lead to a higher quality videos at the
                expense of slower inference.
            timesteps (`List[int]`, *optional*):
                Custom timesteps to use for the denoising process with schedulers which support a `timesteps` argument
                in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
                passed will be used. Must be in descending order.
            sigmas (`List[float]`, *optional*):
                Custom sigmas to use for the denoising process with schedulers which support a `sigmas` argument in
                their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is passed
                will be used.
            strength (`float`, *optional*, defaults to 0.8):
                Higher strength leads to more differences between original video and generated video.
            guidance_scale (`float`, *optional*, defaults to 7.5):
                A higher guidance scale value encourages the model to generate images closely linked to the text
                `prompt` at the expense of lower image quality. Guidance scale is enabled when `guidance_scale > 1`.
            negative_prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts to guide what to not include in image generation. If not defined, you need to
                pass `negative_prompt_embeds` instead. Ignored when not using guidance (`guidance_scale < 1`).
            eta (`float`, *optional*, defaults to 0.0):
                Corresponds to parameter eta (η) from the [DDIM](https://arxiv.org/abs/2010.02502) paper. Only applies
                to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
            generator (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
                A [`np.random.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
                generation deterministic.
            latents (`ms.Tensor`, *optional*):
                Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for video
                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                tensor is generated by sampling using the supplied random `generator`. Latents should be of shape
                `(batch_size, num_channel, num_frames, height, width)`.
            prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
                provided, text embeddings are generated from the `prompt` input argument.
            negative_prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
                not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
            ip_adapter_image: (`PipelineImageInput`, *optional*):
                Optional image input to work with IP Adapters.
            ip_adapter_image_embeds (`List[torch.Tensor]`, *optional*):
                Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
                IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should
                contain the negative image embedding if `do_classifier_free_guidance` is set to `True`. If not
                provided, embeddings are computed from the `ip_adapter_image` input argument.
            output_type (`str`, *optional*, defaults to `"pil"`):
                The output format of the generated video. Choose between `ms.Tensor`, `PIL.Image` or
                `np.array`.
            return_dict (`bool`, *optional*, defaults to `False`):
                Whether or not to return a [`AnimateDiffPipelineOutput`] instead of a plain tuple.
            cross_attention_kwargs (`dict`, *optional*):
                A kwargs dictionary that if specified is passed along to the [`AttentionProcessor`] as defined in
                [`self.processor`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
            clip_skip (`int`, *optional*):
                Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
                the output of the pre-final layer will be used for computing the prompt embeddings.
            callback_on_step_end (`Callable`, *optional*):
                A function that calls at the end of each denoising steps during the inference. The function is called
                with the following arguments: `callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int,
                callback_kwargs: Dict)`. `callback_kwargs` will include a list of all tensors as specified by
                `callback_on_step_end_tensor_inputs`.
            callback_on_step_end_tensor_inputs (`List`, *optional*):
                The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
                will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
                `._callback_tensor_inputs` attribute of your pipeline class.

        Examples:

        Returns:
            [`pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput`] or `tuple`:
                If `return_dict` is `True`, [`pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput`] is
                returned, otherwise a `tuple` is returned where the first element is a list with the generated frames.
        """

        # 0. Default height and width to unet
        height = height or self.unet.config.sample_size * self.vae_scale_factor
        width = width or self.unet.config.sample_size * self.vae_scale_factor

        num_videos_per_prompt = 1

        # 1. Check inputs. Raise error if not correct
        self.check_inputs(
            prompt=prompt,
            strength=strength,
            height=height,
            width=width,
            negative_prompt=negative_prompt,
            prompt_embeds=prompt_embeds,
            negative_prompt_embeds=negative_prompt_embeds,
            video=video,
            latents=latents,
            ip_adapter_image=ip_adapter_image,
            ip_adapter_image_embeds=ip_adapter_image_embeds,
            callback_on_step_end_tensor_inputs=callback_on_step_end_tensor_inputs,
        )

        self._guidance_scale = guidance_scale
        self._clip_skip = clip_skip
        self._cross_attention_kwargs = cross_attention_kwargs

        # 2. Define call parameters
        if prompt is not None and isinstance(prompt, str):
            batch_size = 1
        elif prompt is not None and isinstance(prompt, list):
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        # 3. Encode input prompt
        text_encoder_lora_scale = (
            self.cross_attention_kwargs.get("scale", None) if self.cross_attention_kwargs is not None else None
        )
        prompt_embeds, negative_prompt_embeds = self.encode_prompt(
            prompt,
            num_videos_per_prompt,
            self.do_classifier_free_guidance,
            negative_prompt,
            prompt_embeds=prompt_embeds,
            negative_prompt_embeds=negative_prompt_embeds,
            lora_scale=text_encoder_lora_scale,
            clip_skip=self.clip_skip,
        )

        # For classifier free guidance, we need to do two forward passes.
        # Here we concatenate the unconditional and text embeddings into a single batch
        # to avoid doing two forward passes
        if self.do_classifier_free_guidance:
            prompt_embeds = ops.cat([negative_prompt_embeds, prompt_embeds])

        if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
            image_embeds = self.prepare_ip_adapter_image_embeds(
                ip_adapter_image,
                ip_adapter_image_embeds,
                batch_size * num_videos_per_prompt,
                self.do_classifier_free_guidance,
            )

        # 4. Prepare timesteps
        timesteps, num_inference_steps = retrieve_timesteps(self.scheduler, num_inference_steps, timesteps, sigmas)
        timesteps, num_inference_steps = self.get_timesteps(num_inference_steps, timesteps, strength)
        latent_timestep = timesteps[:1].tile((batch_size * num_videos_per_prompt,))

        # 5. Prepare latent variables
        if latents is None:
            video = self.video_processor.preprocess_video(video, height=height, width=width)
            # Move the number of frames before the number of channels.
            video = video.permute(0, 2, 1, 3, 4)
            video = video.to(prompt_embeds.dtype)
        num_channels_latents = self.unet.config.in_channels
        latents = self.prepare_latents(
            video=video,
            height=height,
            width=width,
            num_channels_latents=num_channels_latents,
            batch_size=batch_size * num_videos_per_prompt,
            timestep=latent_timestep,
            dtype=prompt_embeds.dtype,
            generator=generator,
            latents=latents,
        )

        # 6. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
        extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)

        # 7. Add image embeds for IP-Adapter
        added_cond_kwargs = (
            {"image_embeds": image_embeds}
            if ip_adapter_image is not None or ip_adapter_image_embeds is not None
            else None
        )

        # self.free_init_enabled relies on `FreeInitMixin` that involves FFT implemented by the framework,
        # which is currently incomplete within the MindSpore. Therefore, we have disabled this functionality.
        # if self.free_init_enabled: ...

        self._num_timesteps = len(timesteps)
        num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order

        # 8. Denoising loop
        with self.progress_bar(total=self._num_timesteps) as progress_bar:
            for i, t in enumerate(timesteps):
                # expand the latents if we are doing classifier free guidance
                latent_model_input = ops.cat([latents] * 2) if self.do_classifier_free_guidance else latents
                # TODO: method of scheduler should not change the dtype of input.
                #  Remove the casting after cuiyushi confirm that.
                tmp_dtype = latent_model_input.dtype
                latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
                latent_model_input = latent_model_input.to(tmp_dtype)

                # predict the noise residual
                noise_pred = self.unet(
                    latent_model_input,
                    t,
                    encoder_hidden_states=prompt_embeds,
                    cross_attention_kwargs=self.cross_attention_kwargs,
                    added_cond_kwargs=ms.mutable(added_cond_kwargs) if added_cond_kwargs else added_cond_kwargs,
                )[0]

                # perform guidance
                if self.do_classifier_free_guidance:
                    noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
                    noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)

                # compute the previous noisy sample x_t -> x_t-1
                # TODO: method of scheduler should not change the dtype of input.
                #  Remove the casting after cuiyushi confirm that.
                tmp_dtype = latents.dtype
                latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]
                latents = latents.to(tmp_dtype)

                if callback_on_step_end is not None:
                    callback_kwargs = {}
                    for k in callback_on_step_end_tensor_inputs:
                        callback_kwargs[k] = locals()[k]
                    callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)

                    latents = callback_outputs.pop("latents", latents)
                    prompt_embeds = callback_outputs.pop("prompt_embeds", prompt_embeds)
                    negative_prompt_embeds = callback_outputs.pop("negative_prompt_embeds", negative_prompt_embeds)

                # call the callback, if provided
                if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
                    progress_bar.update()

        # 9. Post-processing
        if output_type == "latent":
            video = latents
        else:
            video_tensor = self.decode_latents(latents)
            video = self.video_processor.postprocess_video(video=video_tensor, output_type=output_type)

        if not return_dict:
            return (video,)

        return AnimateDiffPipelineOutput(frames=video)

mindone.diffusers.pipelines.AnimateDiffVideoToVideoPipeline.__call__(video=None, prompt=None, height=None, width=None, num_inference_steps=50, timesteps=None, sigmas=None, guidance_scale=7.5, strength=0.8, negative_prompt=None, num_videos_per_prompt=1, eta=0.0, generator=None, latents=None, prompt_embeds=None, negative_prompt_embeds=None, ip_adapter_image=None, ip_adapter_image_embeds=None, output_type='pil', return_dict=False, cross_attention_kwargs=None, clip_skip=None, callback_on_step_end=None, callback_on_step_end_tensor_inputs=['latents'])

The call function to the pipeline for generation.

PARAMETER DESCRIPTION
video

The input video to condition the generation on. Must be a list of images/frames of the video.

TYPE: `List[PipelineImageInput]` DEFAULT: None

prompt

The prompt or prompts to guide image generation. If not defined, you need to pass prompt_embeds.

TYPE: `str` or `List[str]`, *optional* DEFAULT: None

height

The height in pixels of the generated video.

TYPE: `int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor` DEFAULT: None

width

The width in pixels of the generated video.

TYPE: `int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor` DEFAULT: None

num_inference_steps

The number of denoising steps. More denoising steps usually lead to a higher quality videos at the expense of slower inference.

TYPE: `int`, *optional*, defaults to 50 DEFAULT: 50

timesteps

Custom timesteps to use for the denoising process with schedulers which support a timesteps argument in their set_timesteps method. If not defined, the default behavior when num_inference_steps is passed will be used. Must be in descending order.

TYPE: `List[int]`, *optional* DEFAULT: None

sigmas

Custom sigmas to use for the denoising process with schedulers which support a sigmas argument in their set_timesteps method. If not defined, the default behavior when num_inference_steps is passed will be used.

TYPE: `List[float]`, *optional* DEFAULT: None

strength

Higher strength leads to more differences between original video and generated video.

TYPE: `float`, *optional*, defaults to 0.8 DEFAULT: 0.8

guidance_scale

A higher guidance scale value encourages the model to generate images closely linked to the text prompt at the expense of lower image quality. Guidance scale is enabled when guidance_scale > 1.

TYPE: `float`, *optional*, defaults to 7.5 DEFAULT: 7.5

negative_prompt

The prompt or prompts to guide what to not include in image generation. If not defined, you need to pass negative_prompt_embeds instead. Ignored when not using guidance (guidance_scale < 1).

TYPE: `str` or `List[str]`, *optional* DEFAULT: None

eta

Corresponds to parameter eta (η) from the DDIM paper. Only applies to the [~schedulers.DDIMScheduler], and is ignored in other schedulers.

TYPE: `float`, *optional*, defaults to 0.0 DEFAULT: 0.0

generator

A np.random.Generator to make generation deterministic.

TYPE: `np.random.Generator` or `List[np.random.Generator]`, *optional* DEFAULT: None

latents

Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for video generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor is generated by sampling using the supplied random generator. Latents should be of shape (batch_size, num_channel, num_frames, height, width).

TYPE: `ms.Tensor`, *optional* DEFAULT: None

prompt_embeds

Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not provided, text embeddings are generated from the prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

negative_prompt_embeds

Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not provided, negative_prompt_embeds are generated from the negative_prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

ip_adapter_image

(PipelineImageInput, optional): Optional image input to work with IP Adapters.

TYPE: Optional[PipelineImageInput] DEFAULT: None

ip_adapter_image_embeds

Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of IP-adapters. Each element should be a tensor of shape (batch_size, num_images, emb_dim). It should contain the negative image embedding if do_classifier_free_guidance is set to True. If not provided, embeddings are computed from the ip_adapter_image input argument.

TYPE: `List[torch.Tensor]`, *optional* DEFAULT: None

output_type

The output format of the generated video. Choose between ms.Tensor, PIL.Image or np.array.

TYPE: `str`, *optional*, defaults to `"pil"` DEFAULT: 'pil'

return_dict

Whether or not to return a [AnimateDiffPipelineOutput] instead of a plain tuple.

TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False

cross_attention_kwargs

A kwargs dictionary that if specified is passed along to the [AttentionProcessor] as defined in self.processor.

TYPE: `dict`, *optional* DEFAULT: None

clip_skip

Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that the output of the pre-final layer will be used for computing the prompt embeddings.

TYPE: `int`, *optional* DEFAULT: None

callback_on_step_end

A function that calls at the end of each denoising steps during the inference. The function is called with the following arguments: callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict). callback_kwargs will include a list of all tensors as specified by callback_on_step_end_tensor_inputs.

TYPE: `Callable`, *optional* DEFAULT: None

callback_on_step_end_tensor_inputs

The list of tensor inputs for the callback_on_step_end function. The tensors specified in the list will be passed as callback_kwargs argument. You will only be able to include variables listed in the ._callback_tensor_inputs attribute of your pipeline class.

TYPE: `List`, *optional* DEFAULT: ['latents']

RETURNS DESCRIPTION

[pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput] or tuple: If return_dict is True, [pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput] is returned, otherwise a tuple is returned where the first element is a list with the generated frames.
Source code in mindone/diffusers/pipelines/animatediff/pipeline_animatediff_video2video.py 
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
def __call__(
    self,
    video: List[List[PipelineImageInput]] = None,
    prompt: Optional[Union[str, List[str]]] = None,
    height: Optional[int] = None,
    width: Optional[int] = None,
    num_inference_steps: int = 50,
    timesteps: Optional[List[int]] = None,
    sigmas: Optional[List[float]] = None,
    guidance_scale: float = 7.5,
    strength: float = 0.8,
    negative_prompt: Optional[Union[str, List[str]]] = None,
    num_videos_per_prompt: Optional[int] = 1,
    eta: float = 0.0,
    generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
    latents: Optional[ms.Tensor] = None,
    prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    ip_adapter_image: Optional[PipelineImageInput] = None,
    ip_adapter_image_embeds: Optional[List[ms.Tensor]] = None,
    output_type: Optional[str] = "pil",
    return_dict: bool = False,
    cross_attention_kwargs: Optional[Dict[str, Any]] = None,
    clip_skip: Optional[int] = None,
    callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
    callback_on_step_end_tensor_inputs: List[str] = ["latents"],
):
    r"""
    The call function to the pipeline for generation.

    Args:
        video (`List[PipelineImageInput]`):
            The input video to condition the generation on. Must be a list of images/frames of the video.
        prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`.
        height (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
            The height in pixels of the generated video.
        width (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
            The width in pixels of the generated video.
        num_inference_steps (`int`, *optional*, defaults to 50):
            The number of denoising steps. More denoising steps usually lead to a higher quality videos at the
            expense of slower inference.
        timesteps (`List[int]`, *optional*):
            Custom timesteps to use for the denoising process with schedulers which support a `timesteps` argument
            in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
            passed will be used. Must be in descending order.
        sigmas (`List[float]`, *optional*):
            Custom sigmas to use for the denoising process with schedulers which support a `sigmas` argument in
            their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is passed
            will be used.
        strength (`float`, *optional*, defaults to 0.8):
            Higher strength leads to more differences between original video and generated video.
        guidance_scale (`float`, *optional*, defaults to 7.5):
            A higher guidance scale value encourages the model to generate images closely linked to the text
            `prompt` at the expense of lower image quality. Guidance scale is enabled when `guidance_scale > 1`.
        negative_prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts to guide what to not include in image generation. If not defined, you need to
            pass `negative_prompt_embeds` instead. Ignored when not using guidance (`guidance_scale < 1`).
        eta (`float`, *optional*, defaults to 0.0):
            Corresponds to parameter eta (η) from the [DDIM](https://arxiv.org/abs/2010.02502) paper. Only applies
            to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
        generator (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
            A [`np.random.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
            generation deterministic.
        latents (`ms.Tensor`, *optional*):
            Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for video
            generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
            tensor is generated by sampling using the supplied random `generator`. Latents should be of shape
            `(batch_size, num_channel, num_frames, height, width)`.
        prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
            provided, text embeddings are generated from the `prompt` input argument.
        negative_prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
            not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
        ip_adapter_image: (`PipelineImageInput`, *optional*):
            Optional image input to work with IP Adapters.
        ip_adapter_image_embeds (`List[torch.Tensor]`, *optional*):
            Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
            IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should
            contain the negative image embedding if `do_classifier_free_guidance` is set to `True`. If not
            provided, embeddings are computed from the `ip_adapter_image` input argument.
        output_type (`str`, *optional*, defaults to `"pil"`):
            The output format of the generated video. Choose between `ms.Tensor`, `PIL.Image` or
            `np.array`.
        return_dict (`bool`, *optional*, defaults to `False`):
            Whether or not to return a [`AnimateDiffPipelineOutput`] instead of a plain tuple.
        cross_attention_kwargs (`dict`, *optional*):
            A kwargs dictionary that if specified is passed along to the [`AttentionProcessor`] as defined in
            [`self.processor`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
        clip_skip (`int`, *optional*):
            Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
            the output of the pre-final layer will be used for computing the prompt embeddings.
        callback_on_step_end (`Callable`, *optional*):
            A function that calls at the end of each denoising steps during the inference. The function is called
            with the following arguments: `callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int,
            callback_kwargs: Dict)`. `callback_kwargs` will include a list of all tensors as specified by
            `callback_on_step_end_tensor_inputs`.
        callback_on_step_end_tensor_inputs (`List`, *optional*):
            The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
            will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
            `._callback_tensor_inputs` attribute of your pipeline class.

    Examples:

    Returns:
        [`pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput`] or `tuple`:
            If `return_dict` is `True`, [`pipelines.animatediff.pipeline_output.AnimateDiffPipelineOutput`] is
            returned, otherwise a `tuple` is returned where the first element is a list with the generated frames.
    """

    # 0. Default height and width to unet
    height = height or self.unet.config.sample_size * self.vae_scale_factor
    width = width or self.unet.config.sample_size * self.vae_scale_factor

    num_videos_per_prompt = 1

    # 1. Check inputs. Raise error if not correct
    self.check_inputs(
        prompt=prompt,
        strength=strength,
        height=height,
        width=width,
        negative_prompt=negative_prompt,
        prompt_embeds=prompt_embeds,
        negative_prompt_embeds=negative_prompt_embeds,
        video=video,
        latents=latents,
        ip_adapter_image=ip_adapter_image,
        ip_adapter_image_embeds=ip_adapter_image_embeds,
        callback_on_step_end_tensor_inputs=callback_on_step_end_tensor_inputs,
    )

    self._guidance_scale = guidance_scale
    self._clip_skip = clip_skip
    self._cross_attention_kwargs = cross_attention_kwargs

    # 2. Define call parameters
    if prompt is not None and isinstance(prompt, str):
        batch_size = 1
    elif prompt is not None and isinstance(prompt, list):
        batch_size = len(prompt)
    else:
        batch_size = prompt_embeds.shape[0]

    # 3. Encode input prompt
    text_encoder_lora_scale = (
        self.cross_attention_kwargs.get("scale", None) if self.cross_attention_kwargs is not None else None
    )
    prompt_embeds, negative_prompt_embeds = self.encode_prompt(
        prompt,
        num_videos_per_prompt,
        self.do_classifier_free_guidance,
        negative_prompt,
        prompt_embeds=prompt_embeds,
        negative_prompt_embeds=negative_prompt_embeds,
        lora_scale=text_encoder_lora_scale,
        clip_skip=self.clip_skip,
    )

    # For classifier free guidance, we need to do two forward passes.
    # Here we concatenate the unconditional and text embeddings into a single batch
    # to avoid doing two forward passes
    if self.do_classifier_free_guidance:
        prompt_embeds = ops.cat([negative_prompt_embeds, prompt_embeds])

    if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
        image_embeds = self.prepare_ip_adapter_image_embeds(
            ip_adapter_image,
            ip_adapter_image_embeds,
            batch_size * num_videos_per_prompt,
            self.do_classifier_free_guidance,
        )

    # 4. Prepare timesteps
    timesteps, num_inference_steps = retrieve_timesteps(self.scheduler, num_inference_steps, timesteps, sigmas)
    timesteps, num_inference_steps = self.get_timesteps(num_inference_steps, timesteps, strength)
    latent_timestep = timesteps[:1].tile((batch_size * num_videos_per_prompt,))

    # 5. Prepare latent variables
    if latents is None:
        video = self.video_processor.preprocess_video(video, height=height, width=width)
        # Move the number of frames before the number of channels.
        video = video.permute(0, 2, 1, 3, 4)
        video = video.to(prompt_embeds.dtype)
    num_channels_latents = self.unet.config.in_channels
    latents = self.prepare_latents(
        video=video,
        height=height,
        width=width,
        num_channels_latents=num_channels_latents,
        batch_size=batch_size * num_videos_per_prompt,
        timestep=latent_timestep,
        dtype=prompt_embeds.dtype,
        generator=generator,
        latents=latents,
    )

    # 6. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
    extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)

    # 7. Add image embeds for IP-Adapter
    added_cond_kwargs = (
        {"image_embeds": image_embeds}
        if ip_adapter_image is not None or ip_adapter_image_embeds is not None
        else None
    )

    # self.free_init_enabled relies on `FreeInitMixin` that involves FFT implemented by the framework,
    # which is currently incomplete within the MindSpore. Therefore, we have disabled this functionality.
    # if self.free_init_enabled: ...

    self._num_timesteps = len(timesteps)
    num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order

    # 8. Denoising loop
    with self.progress_bar(total=self._num_timesteps) as progress_bar:
        for i, t in enumerate(timesteps):
            # expand the latents if we are doing classifier free guidance
            latent_model_input = ops.cat([latents] * 2) if self.do_classifier_free_guidance else latents
            # TODO: method of scheduler should not change the dtype of input.
            #  Remove the casting after cuiyushi confirm that.
            tmp_dtype = latent_model_input.dtype
            latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
            latent_model_input = latent_model_input.to(tmp_dtype)

            # predict the noise residual
            noise_pred = self.unet(
                latent_model_input,
                t,
                encoder_hidden_states=prompt_embeds,
                cross_attention_kwargs=self.cross_attention_kwargs,
                added_cond_kwargs=ms.mutable(added_cond_kwargs) if added_cond_kwargs else added_cond_kwargs,
            )[0]

            # perform guidance
            if self.do_classifier_free_guidance:
                noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
                noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)

            # compute the previous noisy sample x_t -> x_t-1
            # TODO: method of scheduler should not change the dtype of input.
            #  Remove the casting after cuiyushi confirm that.
            tmp_dtype = latents.dtype
            latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]
            latents = latents.to(tmp_dtype)

            if callback_on_step_end is not None:
                callback_kwargs = {}
                for k in callback_on_step_end_tensor_inputs:
                    callback_kwargs[k] = locals()[k]
                callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)

                latents = callback_outputs.pop("latents", latents)
                prompt_embeds = callback_outputs.pop("prompt_embeds", prompt_embeds)
                negative_prompt_embeds = callback_outputs.pop("negative_prompt_embeds", negative_prompt_embeds)

            # call the callback, if provided
            if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
                progress_bar.update()

    # 9. Post-processing
    if output_type == "latent":
        video = latents
    else:
        video_tensor = self.decode_latents(latents)
        video = self.video_processor.postprocess_video(video=video_tensor, output_type=output_type)

    if not return_dict:
        return (video,)

    return AnimateDiffPipelineOutput(frames=video)

mindone.diffusers.pipelines.AnimateDiffVideoToVideoPipeline.encode_prompt(prompt, num_images_per_prompt, do_classifier_free_guidance, negative_prompt=None, prompt_embeds=None, negative_prompt_embeds=None, lora_scale=None, clip_skip=None)

Encodes the prompt into text encoder hidden states.

PARAMETER DESCRIPTION
prompt

prompt to be encoded

TYPE: `str` or `List[str]`, *optional*

num_images_per_prompt

number of images that should be generated per prompt

TYPE: `int`

do_classifier_free_guidance

whether to use classifier free guidance or not

TYPE: `bool`

negative_prompt

The prompt or prompts not to guide the image generation. If not defined, one has to pass negative_prompt_embeds instead. Ignored when not using guidance (i.e., ignored if guidance_scale is less than 1).

TYPE: `str` or `List[str]`, *optional* DEFAULT: None

prompt_embeds

Pre-generated text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, text embeddings will be generated from prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

negative_prompt_embeds

Pre-generated negative text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, negative_prompt_embeds will be generated from negative_prompt input argument.

TYPE: `ms.Tensor`, *optional* DEFAULT: None

lora_scale

A LoRA scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.

TYPE: `float`, *optional* DEFAULT: None

clip_skip

Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that the output of the pre-final layer will be used for computing the prompt embeddings.

TYPE: `int`, *optional* DEFAULT: None

Source code in mindone/diffusers/pipelines/animatediff/pipeline_animatediff_video2video.py 
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
def encode_prompt(
    self,
    prompt,
    num_images_per_prompt,
    do_classifier_free_guidance,
    negative_prompt=None,
    prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    lora_scale: Optional[float] = None,
    clip_skip: Optional[int] = None,
):
    r"""
    Encodes the prompt into text encoder hidden states.

    Args:
        prompt (`str` or `List[str]`, *optional*):
            prompt to be encoded
        num_images_per_prompt (`int`):
            number of images that should be generated per prompt
        do_classifier_free_guidance (`bool`):
            whether to use classifier free guidance or not
        negative_prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts not to guide the image generation. If not defined, one has to pass
            `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
            less than `1`).
        prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
            provided, text embeddings will be generated from `prompt` input argument.
        negative_prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
            weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
            argument.
        lora_scale (`float`, *optional*):
            A LoRA scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
        clip_skip (`int`, *optional*):
            Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
            the output of the pre-final layer will be used for computing the prompt embeddings.
    """
    # set lora scale so that monkey patched LoRA
    # function of text encoder can correctly access it
    if lora_scale is not None and isinstance(self, LoraLoaderMixin):
        self._lora_scale = lora_scale

        # dynamically adjust the LoRA scale
        scale_lora_layers(self.text_encoder, lora_scale)

    if prompt is not None and isinstance(prompt, str):
        batch_size = 1
    elif prompt is not None and isinstance(prompt, list):
        batch_size = len(prompt)
    else:
        batch_size = prompt_embeds.shape[0]

    if prompt_embeds is None:
        # textual inversion: process multi-vector tokens if necessary
        if isinstance(self, TextualInversionLoaderMixin):
            prompt = self.maybe_convert_prompt(prompt, self.tokenizer)

        text_inputs = self.tokenizer(
            prompt,
            padding="max_length",
            max_length=self.tokenizer.model_max_length,
            truncation=True,
            return_tensors="np",
        )
        text_input_ids = text_inputs.input_ids
        untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="np").input_ids

        if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not np.array_equal(
            text_input_ids, untruncated_ids
        ):
            removed_text = self.tokenizer.batch_decode(untruncated_ids[:, self.tokenizer.model_max_length - 1 : -1])
            logger.warning(
                "The following part of your input was truncated because CLIP can only handle sequences up to"
                f" {self.tokenizer.model_max_length} tokens: {removed_text}"
            )

        if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
            attention_mask = ms.Tensor(text_inputs.attention_mask)
        else:
            attention_mask = None

        if clip_skip is None:
            prompt_embeds = self.text_encoder(ms.Tensor(text_input_ids), attention_mask=attention_mask)
            prompt_embeds = prompt_embeds[0]
        else:
            prompt_embeds = self.text_encoder(
                ms.Tensor(text_input_ids), attention_mask=attention_mask, output_hidden_states=True
            )
            # Access the `hidden_states` first, that contains a tuple of
            # all the hidden states from the encoder layers. Then index into
            # the tuple to access the hidden states from the desired layer.
            prompt_embeds = prompt_embeds[-1][-(clip_skip + 1)]
            # We also need to apply the final LayerNorm here to not mess with the
            # representations. The `last_hidden_states` that we typically use for
            # obtaining the final prompt representations passes through the LayerNorm
            # layer.
            prompt_embeds = self.text_encoder.text_model.final_layer_norm(prompt_embeds)

    if self.text_encoder is not None:
        prompt_embeds_dtype = self.text_encoder.dtype
    elif self.unet is not None:
        prompt_embeds_dtype = self.unet.dtype
    else:
        prompt_embeds_dtype = prompt_embeds.dtype

    prompt_embeds = prompt_embeds.to(dtype=prompt_embeds_dtype)

    bs_embed, seq_len, _ = prompt_embeds.shape
    # duplicate text embeddings for each generation per prompt, using mps friendly method
    prompt_embeds = prompt_embeds.tile((1, num_images_per_prompt, 1))
    prompt_embeds = prompt_embeds.view(bs_embed * num_images_per_prompt, seq_len, -1)

    # get unconditional embeddings for classifier free guidance
    if do_classifier_free_guidance and negative_prompt_embeds is None:
        uncond_tokens: List[str]
        if negative_prompt is None:
            uncond_tokens = [""] * batch_size
        elif prompt is not None and type(prompt) is not type(negative_prompt):
            raise TypeError(
                f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
                f" {type(prompt)}."
            )
        elif isinstance(negative_prompt, str):
            uncond_tokens = [negative_prompt]
        elif batch_size != len(negative_prompt):
            raise ValueError(
                f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
                f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
                " the batch size of `prompt`."
            )
        else:
            uncond_tokens = negative_prompt

        # textual inversion: process multi-vector tokens if necessary
        if isinstance(self, TextualInversionLoaderMixin):
            uncond_tokens = self.maybe_convert_prompt(uncond_tokens, self.tokenizer)

        max_length = prompt_embeds.shape[1]
        uncond_input = self.tokenizer(
            uncond_tokens,
            padding="max_length",
            max_length=max_length,
            truncation=True,
            return_tensors="np",
        )

        if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
            attention_mask = ms.Tensor(uncond_input.attention_mask)
        else:
            attention_mask = None

        negative_prompt_embeds = self.text_encoder(
            ms.Tensor(uncond_input.input_ids),
            attention_mask=attention_mask,
        )
        negative_prompt_embeds = negative_prompt_embeds[0]

    if do_classifier_free_guidance:
        # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
        seq_len = negative_prompt_embeds.shape[1]

        negative_prompt_embeds = negative_prompt_embeds.to(dtype=prompt_embeds_dtype)

        negative_prompt_embeds = negative_prompt_embeds.tile((1, num_images_per_prompt, 1))
        negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)

    if self.text_encoder is not None:
        if isinstance(self, LoraLoaderMixin):
            # Retrieve the original scale by scaling back the LoRA layers
            unscale_lora_layers(self.text_encoder, lora_scale)

    return prompt_embeds, negative_prompt_embeds

mindone.diffusers.pipelines.animatediff.AnimateDiffPipelineOutput dataclass

Bases: BaseOutput

Output class for AnimateDiff pipelines.

Args: frames (mindspore.Tensor, np.ndarray, or List[List[PIL.Image.Image]]): List of video outputs - It can be a nested list of length batch_size, with each sub-list containing denoised PIL image sequences of length num_frames. It can also be a NumPy array or Torch tensor of shape (batch_size, num_frames, channels, height, width)

Source code in mindone/diffusers/pipelines/animatediff/pipeline_output.py 
12
13
14
15
16
17
18
19
20
21
22
23
24
@dataclass
class AnimateDiffPipelineOutput(BaseOutput):
    r"""
     Output class for AnimateDiff pipelines.

     Args:
        frames (`mindspore.Tensor`, `np.ndarray`, or List[List[PIL.Image.Image]]):
            List of video outputs - It can be a nested list of length `batch_size,` with each sub-list containing denoised
     PIL image sequences of length `num_frames.` It can also be a NumPy array or Torch tensor of shape
    `(batch_size, num_frames, channels, height, width)`
    """

    frames: Union[ms.Tensor, np.ndarray, List[List[PIL.Image.Image]]]