Wan

Wan 2.1 by the Alibaba Wan Team.

Generating Videos with Wan 2.1

We will first need to install some addtional dependencies.

pip install -u ftfy imageio-ffmpeg imageio

Text to Video Generation

The following example requires 11GB VRAM to run and uses the smaller Wan-AI/Wan2.1-T2V-1.3B-Diffusers model. You can switch it out for the larger Wan2.1-I2V-14B-720P-Diffusers or Wan-AI/Wan2.1-I2V-14B-480P-Diffusers if you have at least 35GB VRAM available.

from mindone.diffusers import WanPipeline
from mindone.diffusers.utils import export_to_video
import mindspore as ms

# Available models: Wan-AI/Wan2.1-I2V-14B-720P-Diffusers or Wan-AI/Wan2.1-I2V-14B-480P-Diffusers
model_id = "Wan-AI/Wan2.1-T2V-1.3B-Diffusers"

pipe = WanPipeline.from_pretrained(model_id, mindspore_dtype=ms.bfloat16)

prompt = "A cat and a dog baking a cake together in a kitchen. The cat is carefully measuring flour, while the dog is stirring the batter with a wooden spoon. The kitchen is cozy, with sunlight streaming through the window."
negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards"
num_frames = 33

frames = pipe(prompt=prompt, negative_prompt=negative_prompt, num_frames=num_frames)[0][0]
export_to_video(frames, "wan-t2v.mp4", fps=16)

Tip

You can improve the quality of the generated video by running the decoding step in full precision.

from mindone.diffusers import WanPipeline, AutoencoderKLWan
from mindone.diffusers.utils import export_to_video
import mindspore as ms

model_id = "Wan-AI/Wan2.1-T2V-1.3B-Diffusers"

vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", mindspore_dtype=ms.float32)
pipe = WanPipeline.from_pretrained(model_id, vae=vae, mindspore_dtype=ms.bfloat16)

prompt = "A cat and a dog baking a cake together in a kitchen. The cat is carefully measuring flour, while the dog is stirring the batter with a wooden spoon. The kitchen is cozy, with sunlight streaming through the window."
negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards"
num_frames = 33

frames = pipe(prompt=prompt, num_frames=num_frames)[0][0]
export_to_video(frames, "wan-t2v.mp4", fps=16)

Image to Video Generation

The Image to Video pipeline requires loading the AutoencoderKLWan and the CLIPVisionModel components in full precision. The following example will need at least 35GB of VRAM to run.

import mindspore as ms
import numpy as np
from mindone.diffusers import AutoencoderKLWan, WanImageToVideoPipeline
from mindone.diffusers.utils import export_to_video, load_image
from mindone.transformers import CLIPVisionModel

# Available models: Wan-AI/Wan2.1-I2V-14B-480P-Diffusers, Wan-AI/Wan2.1-I2V-14B-720P-Diffusers
model_id = "Wan-AI/Wan2.1-I2V-14B-480P-Diffusers"
image_encoder = CLIPVisionModel.from_pretrained(
    model_id, subfolder="image_encoder", mindspore_dtype=ms.float32
)
vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", mindspore_dtype=ms.float32)
pipe = WanImageToVideoPipeline.from_pretrained(
    model_id, vae=vae, image_encoder=image_encoder, mindspore_dtype=ms.bfloat16
)

image = load_image(
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"
)

max_area = 480 * 832
aspect_ratio = image.height / image.width
mod_value = pipe.vae_scale_factor_spatial * pipe.transformer.config.patch_size[1]
height = round(np.sqrt(max_area * aspect_ratio)) // mod_value * mod_value
width = round(np.sqrt(max_area / aspect_ratio)) // mod_value * mod_value
image = image.resize((width, height))

prompt = (
    "An astronaut hatching from an egg, on the surface of the moon, the darkness and depth of space realised in "
    "the background. High quality, ultrarealistic detail and breath-taking movie-like camera shot."
)
negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards"

num_frames = 33

output = pipe(
    image=image,
    prompt=prompt,
    negative_prompt=negative_prompt,
    height=height,
    width=width,
    num_frames=num_frames,
    guidance_scale=5.0,
)[0][0]
export_to_video(output, "wan-i2v.mp4", fps=16)

Video to Video Generation

import mindspore as ms
from mindone.diffusers.utils import load_video, export_to_video
from mindone.diffusers import AutoencoderKLWan, WanVideoToVideoPipeline, UniPCMultistepScheduler

# Available models: Wan-AI/Wan2.1-T2V-14B-Diffusers, Wan-AI/Wan2.1-T2V-1.3B-Diffusers
model_id = "Wan-AI/Wan2.1-T2V-1.3B-Diffusers"
vae = AutoencoderKLWan.from_pretrained(
    model_id, subfolder="vae", mindspore_dtype=ms.float32
)
pipe = WanVideoToVideoPipeline.from_pretrained(
    model_id, vae=vae, mindspore_dtype=ms.bfloat16
)
flow_shift = 3.0  # 5.0 for 720P, 3.0 for 480P
pipe.scheduler = UniPCMultistepScheduler.from_config(
    pipe.scheduler.config, flow_shift=flow_shift
)

prompt = "A robot standing on a mountain top. The sun is setting in the background"
negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards"
video = load_video(
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/hiker.mp4"
)
output = pipe(
    video=video,
    prompt=prompt,
    negative_prompt=negative_prompt,
    height=480,
    width=512,
    guidance_scale=7.0,
    strength=0.7,
)[0][0]

export_to_video(output, "wan-v2v.mp4", fps=16)

Using Single File Loading with Wan 2.1

The WanTransformer3DModel and AutoencoderKLWan models support loading checkpoints in their original format via the from_single_file loading method.

import mindspore as ms
from mindone.diffusers import WanPipeline, WanTransformer3DModel

ckpt_path = "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/diffusion_models/wan2.1_t2v_1.3B_bf16.safetensors"
transformer = WanTransformer3DModel.from_single_file(ckpt_path, mindspore_dtype=ms.bfloat16)

pipe = WanPipeline.from_pretrained("Wan-AI/Wan2.1-T2V-1.3B-Diffusers", transformer=transformer)

Recommendations for Inference

• Keep AutencoderKLWan in torch.float32 for better decoding quality.
• num_frames should satisfy the following constraint: (num_frames - 1) % 4 == 0
• For smaller resolution videos, try lower values of shift (between 2.0 to 5.0) in the Scheduler. For larger resolution videos, try higher values (between 7.0 and 12.0). The default value is 3.0 for Wan.

mindone.diffusers.WanPipeline

Bases: DiffusionPipeline, WanLoraLoaderMixin

Pipeline for text-to-video generation using Wan.

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.).

PARAMETER	DESCRIPTION
tokenizer	Tokenizer from T5, specifically the google/umt5-xxl variant. TYPE: [`T5Tokenizer`]
text_encoder	T5, specifically the google/umt5-xxl variant. TYPE: [`T5EncoderModel`]
transformer	Conditional Transformer to denoise the input latents. TYPE: [`WanTransformer3DModel`]
scheduler	A scheduler to be used in combination with transformer to denoise the encoded image latents. TYPE: [`UniPCMultistepScheduler`]
vae	Variational Auto-Encoder (VAE) Model to encode and decode videos to and from latent representations. TYPE: [`AutoencoderKLWan`]

Source code in mindone/diffusers/pipelines/wan/pipeline_wan.py

class WanPipeline(DiffusionPipeline, WanLoraLoaderMixin):
    r"""
    Pipeline for text-to-video generation using Wan.

    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.).

    Args:
        tokenizer ([`T5Tokenizer`]):
            Tokenizer from [T5](https://huggingface.co/docs/transformers/en/model_doc/t5#transformers.T5Tokenizer),
            specifically the [google/umt5-xxl](https://huggingface.co/google/umt5-xxl) variant.
        text_encoder ([`T5EncoderModel`]):
            [T5](https://huggingface.co/docs/transformers/en/model_doc/t5#transformers.T5EncoderModel), specifically
            the [google/umt5-xxl](https://huggingface.co/google/umt5-xxl) variant.
        transformer ([`WanTransformer3DModel`]):
            Conditional Transformer to denoise the input latents.
        scheduler ([`UniPCMultistepScheduler`]):
            A scheduler to be used in combination with `transformer` to denoise the encoded image latents.
        vae ([`AutoencoderKLWan`]):
            Variational Auto-Encoder (VAE) Model to encode and decode videos to and from latent representations.
    """

    model_cpu_offload_seq = "text_encoder->transformer->vae"
    _callback_tensor_inputs = ["latents", "prompt_embeds", "negative_prompt_embeds"]

    def __init__(
        self,
        tokenizer: AutoTokenizer,
        text_encoder: UMT5EncoderModel,
        transformer: WanTransformer3DModel,
        vae: AutoencoderKLWan,
        scheduler: FlowMatchEulerDiscreteScheduler,
    ):
        super().__init__()

        self.register_modules(
            vae=vae,
            text_encoder=text_encoder,
            tokenizer=tokenizer,
            transformer=transformer,
            scheduler=scheduler,
        )

        self.vae_scale_factor_temporal = 2 ** sum(self.vae.temperal_downsample) if getattr(self, "vae", None) else 4
        self.vae_scale_factor_spatial = 2 ** len(self.vae.temperal_downsample) if getattr(self, "vae", None) else 8
        self.video_processor = VideoProcessor(vae_scale_factor=self.vae_scale_factor_spatial)

    def _get_t5_prompt_embeds(
        self,
        prompt: Union[str, List[str]] = None,
        num_videos_per_prompt: int = 1,
        max_sequence_length: int = 226,
        dtype: Optional[ms.Type] = None,
    ):
        dtype = dtype or self.text_encoder.dtype

        prompt = [prompt] if isinstance(prompt, str) else prompt
        prompt = [prompt_clean(u) for u in prompt]
        batch_size = len(prompt)

        text_inputs = self.tokenizer(
            prompt,
            padding="max_length",
            max_length=max_sequence_length,
            truncation=True,
            add_special_tokens=True,
            return_attention_mask=True,
            return_tensors="np",
        )
        text_input_ids, mask = ms.tensor(text_inputs.input_ids), ms.tensor(text_inputs.attention_mask)
        seq_lens = mask.gt(0).sum(dim=1).long()

        prompt_embeds = self.text_encoder(text_input_ids, mask)[0]
        prompt_embeds = prompt_embeds.to(dtype=dtype)
        prompt_embeds = [u[:v] for u, v in zip(prompt_embeds, seq_lens)]
        prompt_embeds = mint.stack(
            [mint.cat([u, u.new_zeros((max_sequence_length - u.shape[0], u.shape[1]))]) for u in prompt_embeds], dim=0
        )

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

        return prompt_embeds

    def encode_prompt(
        self,
        prompt: Union[str, List[str]],
        negative_prompt: Optional[Union[str, List[str]]] = None,
        do_classifier_free_guidance: bool = True,
        num_videos_per_prompt: int = 1,
        prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        max_sequence_length: int = 226,
        dtype: Optional[ms.Type] = None,
    ):
        r"""
        Encodes the prompt into text encoder hidden states.

        Args:
            prompt (`str` or `List[str]`, *optional*):
                prompt to be encoded
            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`).
            do_classifier_free_guidance (`bool`, *optional*, defaults to `True`):
                Whether to use classifier free guidance or not.
            num_videos_per_prompt (`int`, *optional*, defaults to 1):
                Number of videos that should be generated per prompt.
            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.
            dtype: (`ms.Type`, *optional*):
                mindspore dtype
        """
        prompt = [prompt] if isinstance(prompt, str) else prompt
        if prompt is not None:
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        if prompt_embeds is None:
            prompt_embeds = self._get_t5_prompt_embeds(
                prompt=prompt,
                num_videos_per_prompt=num_videos_per_prompt,
                max_sequence_length=max_sequence_length,
                dtype=dtype,
            )

        if do_classifier_free_guidance and negative_prompt_embeds is None:
            negative_prompt = negative_prompt or ""
            negative_prompt = batch_size * [negative_prompt] if isinstance(negative_prompt, str) else negative_prompt

            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`."
                )

            negative_prompt_embeds = self._get_t5_prompt_embeds(
                prompt=negative_prompt,
                num_videos_per_prompt=num_videos_per_prompt,
                max_sequence_length=max_sequence_length,
                dtype=dtype,
            )

        return prompt_embeds, negative_prompt_embeds

    def check_inputs(
        self,
        prompt,
        negative_prompt,
        height,
        width,
        prompt_embeds=None,
        negative_prompt_embeds=None,
        callback_on_step_end_tensor_inputs=None,
    ):
        if height % 16 != 0 or width % 16 != 0:
            raise ValueError(f"`height` and `width` have to be divisible by 16 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 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`: {negative_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 negative_prompt is not None and (
            not isinstance(negative_prompt, str) and not isinstance(negative_prompt, list)
        ):
            raise ValueError(f"`negative_prompt` has to be of type `str` or `list` but is {type(negative_prompt)}")

    def prepare_latents(
        self,
        batch_size: int,
        num_channels_latents: int = 16,
        height: int = 480,
        width: int = 832,
        num_frames: int = 81,
        dtype: Optional[ms.Type] = None,
        generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
        latents: Optional[ms.Tensor] = None,
    ) -> ms.Tensor:
        if latents is not None:
            return latents.to(dtype=dtype)

        num_latent_frames = (num_frames - 1) // self.vae_scale_factor_temporal + 1
        shape = (
            batch_size,
            num_channels_latents,
            num_latent_frames,
            int(height) // self.vae_scale_factor_spatial,
            int(width) // self.vae_scale_factor_spatial,
        )
        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."
            )

        latents = randn_tensor(shape, generator=generator, dtype=dtype)
        return latents

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

    @property
    def do_classifier_free_guidance(self):
        return self._guidance_scale > 1.0

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

    @property
    def current_timestep(self):
        return self._current_timestep

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

    @property
    def attention_kwargs(self):
        return self._attention_kwargs

    def __call__(
        self,
        prompt: Union[str, List[str]] = None,
        negative_prompt: Union[str, List[str]] = None,
        height: int = 480,
        width: int = 832,
        num_frames: int = 81,
        num_inference_steps: int = 50,
        guidance_scale: float = 5.0,
        num_videos_per_prompt: Optional[int] = 1,
        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,
        output_type: Optional[str] = "np",
        return_dict: bool = False,
        attention_kwargs: Optional[Dict[str, Any]] = None,
        callback_on_step_end: Optional[
            Union[Callable[[int, int, Dict], None], PipelineCallback, MultiPipelineCallbacks]
        ] = None,
        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
        max_sequence_length: int = 512,
    ):
        r"""
        The call function to the pipeline for generation.

        Args:
            prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts to guide the image generation. If not defined, pass `prompt_embeds` instead.
            negative_prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts to avoid during image generation. If not defined, pass `negative_prompt_embeds`
                instead. Ignored when not using guidance (`guidance_scale` < `1`).
            height (`int`, defaults to `480`):
                The height in pixels of the generated image.
            width (`int`, defaults to `832`):
                The width in pixels of the generated image.
            num_frames (`int`, defaults to `81`):
                The number of frames in the generated video.
            num_inference_steps (`int`, defaults to `50`):
                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                expense of slower inference.
            guidance_scale (`float`, defaults to `5.0`):
                Guidance scale as defined in [Classifier-Free Diffusion
                Guidance](https://huggingface.co/papers/2207.12598). `guidance_scale` is defined as `w` of equation 2.
                of [Imagen Paper](https://huggingface.co/papers/2205.11487). 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 image quality.
            num_videos_per_prompt (`int`, *optional*, defaults to 1):
                The number of images to generate per prompt.
            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 image
                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`.
            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.
            output_type (`str`, *optional*, defaults to `"np"`):
                The output format of the generated image. Choose between `PIL.Image` or `np.array`.
            return_dict (`bool`, *optional*, defaults to `False`):
                Whether or not to return a [`WanPipelineOutput`] instead of a plain tuple.
            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).
            callback_on_step_end (`Callable`, `PipelineCallback`, `MultiPipelineCallbacks`, *optional*):
                A function or a subclass of `PipelineCallback` or `MultiPipelineCallbacks` that is called at the end of
                each denoising step during the inference. 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.
            max_sequence_length (`int`, defaults to `512`):
                The maximum sequence length of the text encoder. If the prompt is longer than this, it will be
                truncated. If the prompt is shorter, it will be padded to this length.

        Examples:

        Returns:
            [`~WanPipelineOutput`] or `tuple`:
                If `return_dict` is `True`, [`WanPipelineOutput`] is returned, otherwise a `tuple` is returned where
                the first element is a list with the generated images and the second element is a list of `bool`s
                indicating whether the corresponding generated image contains "not-safe-for-work" (nsfw) content.
        """

        if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)):
            callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs

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

        if num_frames % self.vae_scale_factor_temporal != 1:
            logger.warning(
                f"`num_frames - 1` has to be divisible by {self.vae_scale_factor_temporal}. Rounding to the nearest number."
            )
            num_frames = num_frames // self.vae_scale_factor_temporal * self.vae_scale_factor_temporal + 1
        num_frames = max(num_frames, 1)

        self._guidance_scale = guidance_scale
        self._attention_kwargs = attention_kwargs
        self._current_timestep = None
        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
        prompt_embeds, negative_prompt_embeds = self.encode_prompt(
            prompt=prompt,
            negative_prompt=negative_prompt,
            do_classifier_free_guidance=self.do_classifier_free_guidance,
            num_videos_per_prompt=num_videos_per_prompt,
            prompt_embeds=prompt_embeds,
            negative_prompt_embeds=negative_prompt_embeds,
            max_sequence_length=max_sequence_length,
        )

        transformer_dtype = self.transformer.dtype
        prompt_embeds = prompt_embeds.to(transformer_dtype)
        if negative_prompt_embeds is not None:
            negative_prompt_embeds = negative_prompt_embeds.to(transformer_dtype)

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

        # 5. Prepare latent variables
        num_channels_latents = self.transformer.config.in_channels
        latents = self.prepare_latents(
            batch_size * num_videos_per_prompt,
            num_channels_latents,
            height,
            width,
            num_frames,
            ms.float32,
            generator,
            latents,
        )

        # 6. Denoising loop
        num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
        self._num_timesteps = len(timesteps)

        with self.progress_bar(total=num_inference_steps) as progress_bar:
            for i, t in enumerate(timesteps):
                if self.interrupt:
                    continue

                self._current_timestep = t
                latent_model_input = latents.to(transformer_dtype)
                timestep = t.broadcast_to((latents.shape[0],))

                noise_pred = self.transformer(
                    hidden_states=latent_model_input,
                    timestep=timestep,
                    encoder_hidden_states=prompt_embeds,
                    attention_kwargs=attention_kwargs,
                    return_dict=False,
                )[0]

                if self.do_classifier_free_guidance:
                    noise_uncond = self.transformer(
                        hidden_states=latent_model_input,
                        timestep=timestep,
                        encoder_hidden_states=negative_prompt_embeds,
                        attention_kwargs=attention_kwargs,
                        return_dict=False,
                    )[0]
                    noise_pred = noise_uncond + guidance_scale * (noise_pred - noise_uncond)

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

                # 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()

        self._current_timestep = None

        if not output_type == "latent":
            latents = latents.to(self.vae.dtype)
            latents_mean = (
                ms.tensor(self.vae.config.latents_mean).view(1, self.vae.config.z_dim, 1, 1, 1).to(latents.dtype)
            )
            latents_std = 1.0 / ms.tensor(self.vae.config.latents_std).view(1, self.vae.config.z_dim, 1, 1, 1).to(
                latents.dtype
            )
            latents = latents / latents_std + latents_mean
            # TODO: we use pynative mode here since cache in vae.decode which not supported in graph mode
            with pynative_context():
                video = self.vae.decode(latents, return_dict=False)[0]
            video = self.video_processor.postprocess_video(video, output_type=output_type)
        else:
            video = latents

        if not return_dict:
            return (video,)

        return WanPipelineOutput(frames=video)

mindone.diffusers.WanPipeline.__call__(prompt=None, negative_prompt=None, height=480, width=832, num_frames=81, num_inference_steps=50, guidance_scale=5.0, num_videos_per_prompt=1, generator=None, latents=None, prompt_embeds=None, negative_prompt_embeds=None, output_type='np', return_dict=False, attention_kwargs=None, callback_on_step_end=None, callback_on_step_end_tensor_inputs=['latents'], max_sequence_length=512)

The call function to the pipeline for generation.

PARAMETER	DESCRIPTION
prompt	The prompt or prompts to guide the image generation. If not defined, pass prompt_embeds instead. TYPE: `str` or `List[str]`, *optional* DEFAULT: None
negative_prompt	The prompt or prompts to avoid during image generation. If not defined, pass negative_prompt_embeds instead. Ignored when not using guidance (guidance_scale < 1). TYPE: `str` or `List[str]`, *optional* DEFAULT: None
height	The height in pixels of the generated image. TYPE: `int`, defaults to `480` DEFAULT: 480
width	The width in pixels of the generated image. TYPE: `int`, defaults to `832` DEFAULT: 832
num_frames	The number of frames in the generated video. TYPE: `int`, defaults to `81` DEFAULT: 81
num_inference_steps	The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference. TYPE: `int`, defaults to `50` DEFAULT: 50
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 image quality. TYPE: `float`, defaults to `5.0` DEFAULT: 5.0
num_videos_per_prompt	The number of images to generate per prompt. TYPE: `int`, *optional*, defaults to 1 DEFAULT: 1
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 image 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. 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
output_type	The output format of the generated image. Choose between PIL.Image or np.array. TYPE: `str`, *optional*, defaults to `"np"` DEFAULT: 'np'
return_dict	Whether or not to return a [WanPipelineOutput] instead of a plain tuple. TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False
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
callback_on_step_end	A function or a subclass of PipelineCallback or MultiPipelineCallbacks that is called at the end of each denoising step during the inference. 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`, `PipelineCallback`, `MultiPipelineCallbacks`, *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']
max_sequence_length	The maximum sequence length of the text encoder. If the prompt is longer than this, it will be truncated. If the prompt is shorter, it will be padded to this length. TYPE: `int`, defaults to `512` DEFAULT: 512

RETURNS	DESCRIPTION
	[~WanPipelineOutput] or tuple: If return_dict is True, [WanPipelineOutput] is returned, otherwise a tuple is returned where the first element is a list with the generated images and the second element is a list of bools indicating whether the corresponding generated image contains "not-safe-for-work" (nsfw) content.

Source code in mindone/diffusers/pipelines/wan/pipeline_wan.py

def __call__(
    self,
    prompt: Union[str, List[str]] = None,
    negative_prompt: Union[str, List[str]] = None,
    height: int = 480,
    width: int = 832,
    num_frames: int = 81,
    num_inference_steps: int = 50,
    guidance_scale: float = 5.0,
    num_videos_per_prompt: Optional[int] = 1,
    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,
    output_type: Optional[str] = "np",
    return_dict: bool = False,
    attention_kwargs: Optional[Dict[str, Any]] = None,
    callback_on_step_end: Optional[
        Union[Callable[[int, int, Dict], None], PipelineCallback, MultiPipelineCallbacks]
    ] = None,
    callback_on_step_end_tensor_inputs: List[str] = ["latents"],
    max_sequence_length: int = 512,
):
    r"""
    The call function to the pipeline for generation.

    Args:
        prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts to guide the image generation. If not defined, pass `prompt_embeds` instead.
        negative_prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts to avoid during image generation. If not defined, pass `negative_prompt_embeds`
            instead. Ignored when not using guidance (`guidance_scale` < `1`).
        height (`int`, defaults to `480`):
            The height in pixels of the generated image.
        width (`int`, defaults to `832`):
            The width in pixels of the generated image.
        num_frames (`int`, defaults to `81`):
            The number of frames in the generated video.
        num_inference_steps (`int`, defaults to `50`):
            The number of denoising steps. More denoising steps usually lead to a higher quality image at the
            expense of slower inference.
        guidance_scale (`float`, defaults to `5.0`):
            Guidance scale as defined in [Classifier-Free Diffusion
            Guidance](https://huggingface.co/papers/2207.12598). `guidance_scale` is defined as `w` of equation 2.
            of [Imagen Paper](https://huggingface.co/papers/2205.11487). 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 image quality.
        num_videos_per_prompt (`int`, *optional*, defaults to 1):
            The number of images to generate per prompt.
        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 image
            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`.
        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.
        output_type (`str`, *optional*, defaults to `"np"`):
            The output format of the generated image. Choose between `PIL.Image` or `np.array`.
        return_dict (`bool`, *optional*, defaults to `False`):
            Whether or not to return a [`WanPipelineOutput`] instead of a plain tuple.
        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).
        callback_on_step_end (`Callable`, `PipelineCallback`, `MultiPipelineCallbacks`, *optional*):
            A function or a subclass of `PipelineCallback` or `MultiPipelineCallbacks` that is called at the end of
            each denoising step during the inference. 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.
        max_sequence_length (`int`, defaults to `512`):
            The maximum sequence length of the text encoder. If the prompt is longer than this, it will be
            truncated. If the prompt is shorter, it will be padded to this length.

    Examples:

    Returns:
        [`~WanPipelineOutput`] or `tuple`:
            If `return_dict` is `True`, [`WanPipelineOutput`] is returned, otherwise a `tuple` is returned where
            the first element is a list with the generated images and the second element is a list of `bool`s
            indicating whether the corresponding generated image contains "not-safe-for-work" (nsfw) content.
    """

    if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)):
        callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs

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

    if num_frames % self.vae_scale_factor_temporal != 1:
        logger.warning(
            f"`num_frames - 1` has to be divisible by {self.vae_scale_factor_temporal}. Rounding to the nearest number."
        )
        num_frames = num_frames // self.vae_scale_factor_temporal * self.vae_scale_factor_temporal + 1
    num_frames = max(num_frames, 1)

    self._guidance_scale = guidance_scale
    self._attention_kwargs = attention_kwargs
    self._current_timestep = None
    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
    prompt_embeds, negative_prompt_embeds = self.encode_prompt(
        prompt=prompt,
        negative_prompt=negative_prompt,
        do_classifier_free_guidance=self.do_classifier_free_guidance,
        num_videos_per_prompt=num_videos_per_prompt,
        prompt_embeds=prompt_embeds,
        negative_prompt_embeds=negative_prompt_embeds,
        max_sequence_length=max_sequence_length,
    )

    transformer_dtype = self.transformer.dtype
    prompt_embeds = prompt_embeds.to(transformer_dtype)
    if negative_prompt_embeds is not None:
        negative_prompt_embeds = negative_prompt_embeds.to(transformer_dtype)

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

    # 5. Prepare latent variables
    num_channels_latents = self.transformer.config.in_channels
    latents = self.prepare_latents(
        batch_size * num_videos_per_prompt,
        num_channels_latents,
        height,
        width,
        num_frames,
        ms.float32,
        generator,
        latents,
    )

    # 6. Denoising loop
    num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
    self._num_timesteps = len(timesteps)

    with self.progress_bar(total=num_inference_steps) as progress_bar:
        for i, t in enumerate(timesteps):
            if self.interrupt:
                continue

            self._current_timestep = t
            latent_model_input = latents.to(transformer_dtype)
            timestep = t.broadcast_to((latents.shape[0],))

            noise_pred = self.transformer(
                hidden_states=latent_model_input,
                timestep=timestep,
                encoder_hidden_states=prompt_embeds,
                attention_kwargs=attention_kwargs,
                return_dict=False,
            )[0]

            if self.do_classifier_free_guidance:
                noise_uncond = self.transformer(
                    hidden_states=latent_model_input,
                    timestep=timestep,
                    encoder_hidden_states=negative_prompt_embeds,
                    attention_kwargs=attention_kwargs,
                    return_dict=False,
                )[0]
                noise_pred = noise_uncond + guidance_scale * (noise_pred - noise_uncond)

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

            # 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()

    self._current_timestep = None

    if not output_type == "latent":
        latents = latents.to(self.vae.dtype)
        latents_mean = (
            ms.tensor(self.vae.config.latents_mean).view(1, self.vae.config.z_dim, 1, 1, 1).to(latents.dtype)
        )
        latents_std = 1.0 / ms.tensor(self.vae.config.latents_std).view(1, self.vae.config.z_dim, 1, 1, 1).to(
            latents.dtype
        )
        latents = latents / latents_std + latents_mean
        # TODO: we use pynative mode here since cache in vae.decode which not supported in graph mode
        with pynative_context():
            video = self.vae.decode(latents, return_dict=False)[0]
        video = self.video_processor.postprocess_video(video, output_type=output_type)
    else:
        video = latents

    if not return_dict:
        return (video,)

    return WanPipelineOutput(frames=video)

mindone.diffusers.WanPipeline.encode_prompt(prompt, negative_prompt=None, do_classifier_free_guidance=True, num_videos_per_prompt=1, prompt_embeds=None, negative_prompt_embeds=None, max_sequence_length=226, dtype=None)

Encodes the prompt into text encoder hidden states.

PARAMETER	DESCRIPTION
prompt	prompt to be encoded TYPE: `str` or `List[str]`, *optional*
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
do_classifier_free_guidance	Whether to use classifier free guidance or not. TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True
num_videos_per_prompt	Number of videos that should be generated per prompt. TYPE: `int`, *optional*, defaults to 1 DEFAULT: 1
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
dtype	(ms.Type, optional): mindspore dtype TYPE: Optional[Type] DEFAULT: None

Source code in mindone/diffusers/pipelines/wan/pipeline_wan.py

def encode_prompt(
    self,
    prompt: Union[str, List[str]],
    negative_prompt: Optional[Union[str, List[str]]] = None,
    do_classifier_free_guidance: bool = True,
    num_videos_per_prompt: int = 1,
    prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    max_sequence_length: int = 226,
    dtype: Optional[ms.Type] = None,
):
    r"""
    Encodes the prompt into text encoder hidden states.

    Args:
        prompt (`str` or `List[str]`, *optional*):
            prompt to be encoded
        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`).
        do_classifier_free_guidance (`bool`, *optional*, defaults to `True`):
            Whether to use classifier free guidance or not.
        num_videos_per_prompt (`int`, *optional*, defaults to 1):
            Number of videos that should be generated per prompt.
        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.
        dtype: (`ms.Type`, *optional*):
            mindspore dtype
    """
    prompt = [prompt] if isinstance(prompt, str) else prompt
    if prompt is not None:
        batch_size = len(prompt)
    else:
        batch_size = prompt_embeds.shape[0]

    if prompt_embeds is None:
        prompt_embeds = self._get_t5_prompt_embeds(
            prompt=prompt,
            num_videos_per_prompt=num_videos_per_prompt,
            max_sequence_length=max_sequence_length,
            dtype=dtype,
        )

    if do_classifier_free_guidance and negative_prompt_embeds is None:
        negative_prompt = negative_prompt or ""
        negative_prompt = batch_size * [negative_prompt] if isinstance(negative_prompt, str) else negative_prompt

        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`."
            )

        negative_prompt_embeds = self._get_t5_prompt_embeds(
            prompt=negative_prompt,
            num_videos_per_prompt=num_videos_per_prompt,
            max_sequence_length=max_sequence_length,
            dtype=dtype,
        )

    return prompt_embeds, negative_prompt_embeds

mindone.diffusers.WanImageToVideoPipeline

Bases: DiffusionPipeline, WanLoraLoaderMixin

Pipeline for image-to-video generation using Wan.

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.).

PARAMETER	DESCRIPTION
tokenizer	Tokenizer from T5, specifically the google/umt5-xxl variant. TYPE: [`T5Tokenizer`]
text_encoder	T5, specifically the google/umt5-xxl variant. TYPE: [`T5EncoderModel`]
image_encoder	CLIP, specifically the clip-vit-huge-patch14 variant. TYPE: [`CLIPVisionModel`]
transformer	Conditional Transformer to denoise the input latents. TYPE: [`WanTransformer3DModel`]
scheduler	A scheduler to be used in combination with transformer to denoise the encoded image latents. TYPE: [`UniPCMultistepScheduler`]
vae	Variational Auto-Encoder (VAE) Model to encode and decode videos to and from latent representations. TYPE: [`AutoencoderKLWan`]

Source code in mindone/diffusers/pipelines/wan/pipeline_wan_i2v.py

class WanImageToVideoPipeline(DiffusionPipeline, WanLoraLoaderMixin):
    r"""
    Pipeline for image-to-video generation using Wan.

    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.).

    Args:
        tokenizer ([`T5Tokenizer`]):
            Tokenizer from [T5](https://huggingface.co/docs/transformers/en/model_doc/t5#transformers.T5Tokenizer),
            specifically the [google/umt5-xxl](https://huggingface.co/google/umt5-xxl) variant.
        text_encoder ([`T5EncoderModel`]):
            [T5](https://huggingface.co/docs/transformers/en/model_doc/t5#transformers.T5EncoderModel), specifically
            the [google/umt5-xxl](https://huggingface.co/google/umt5-xxl) variant.
        image_encoder ([`CLIPVisionModel`]):
            [CLIP](https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPVisionModel), specifically
            the
            [clip-vit-huge-patch14](https://github.com/mlfoundations/open_clip/blob/main/docs/PRETRAINED.md#vit-h14-xlm-roberta-large)
            variant.
        transformer ([`WanTransformer3DModel`]):
            Conditional Transformer to denoise the input latents.
        scheduler ([`UniPCMultistepScheduler`]):
            A scheduler to be used in combination with `transformer` to denoise the encoded image latents.
        vae ([`AutoencoderKLWan`]):
            Variational Auto-Encoder (VAE) Model to encode and decode videos to and from latent representations.
    """

    model_cpu_offload_seq = "text_encoder->image_encoder->transformer->vae"
    _callback_tensor_inputs = ["latents", "prompt_embeds", "negative_prompt_embeds"]

    def __init__(
        self,
        tokenizer: AutoTokenizer,
        text_encoder: UMT5EncoderModel,
        image_encoder: CLIPVisionModel,
        image_processor: CLIPImageProcessor,
        transformer: WanTransformer3DModel,
        vae: AutoencoderKLWan,
        scheduler: FlowMatchEulerDiscreteScheduler,
    ):
        super().__init__()

        self.register_modules(
            vae=vae,
            text_encoder=text_encoder,
            tokenizer=tokenizer,
            image_encoder=image_encoder,
            transformer=transformer,
            scheduler=scheduler,
            image_processor=image_processor,
        )

        self.vae_scale_factor_temporal = 2 ** sum(self.vae.temperal_downsample) if getattr(self, "vae", None) else 4
        self.vae_scale_factor_spatial = 2 ** len(self.vae.temperal_downsample) if getattr(self, "vae", None) else 8
        self.video_processor = VideoProcessor(vae_scale_factor=self.vae_scale_factor_spatial)
        self.image_processor = image_processor

    def _get_t5_prompt_embeds(
        self,
        prompt: Union[str, List[str]] = None,
        num_videos_per_prompt: int = 1,
        max_sequence_length: int = 512,
        dtype: Optional[ms.Type] = None,
    ):
        dtype = dtype or self.text_encoder.dtype

        prompt = [prompt] if isinstance(prompt, str) else prompt
        prompt = [prompt_clean(u) for u in prompt]
        batch_size = len(prompt)

        text_inputs = self.tokenizer(
            prompt,
            padding="max_length",
            max_length=max_sequence_length,
            truncation=True,
            add_special_tokens=True,
            return_attention_mask=True,
            return_tensors="np",
        )
        text_input_ids, mask = ms.tensor(text_inputs.input_ids), ms.tensor(text_inputs.attention_mask)
        seq_lens = mask.gt(0).sum(dim=1).long()

        prompt_embeds = self.text_encoder(text_input_ids, mask)[0]
        prompt_embeds = prompt_embeds.to(dtype=dtype)
        prompt_embeds = [u[:v] for u, v in zip(prompt_embeds, seq_lens)]
        prompt_embeds = mint.stack(
            [mint.cat([u, u.new_zeros((max_sequence_length - u.shape[0], u.shape[1]))]) for u in prompt_embeds], dim=0
        )

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

        return prompt_embeds

    def encode_image(
        self,
        image: PipelineImageInput,
    ):
        image = self.image_processor(images=image, return_tensors="np")
        for key in image.keys():
            image[key] = ms.tensor(image[key])
        image_embeds = self.image_encoder(**image, output_hidden_states=True)
        return image_embeds[2][-2]

    # Copied from diffusers.pipelines.wan.pipeline_wan.WanPipeline.encode_prompt
    def encode_prompt(
        self,
        prompt: Union[str, List[str]],
        negative_prompt: Optional[Union[str, List[str]]] = None,
        do_classifier_free_guidance: bool = True,
        num_videos_per_prompt: int = 1,
        prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        max_sequence_length: int = 226,
        dtype: Optional[ms.Type] = None,
    ):
        r"""
        Encodes the prompt into text encoder hidden states.

        Args:
            prompt (`str` or `List[str]`, *optional*):
                prompt to be encoded
            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`).
            do_classifier_free_guidance (`bool`, *optional*, defaults to `True`):
                Whether to use classifier free guidance or not.
            num_videos_per_prompt (`int`, *optional*, defaults to 1):
                Number of videos that should be generated per prompt.
            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.
            dtype: (`ms.Type`, *optional*):
                mindspore dtype
        """
        prompt = [prompt] if isinstance(prompt, str) else prompt
        if prompt is not None:
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        if prompt_embeds is None:
            prompt_embeds = self._get_t5_prompt_embeds(
                prompt=prompt,
                num_videos_per_prompt=num_videos_per_prompt,
                max_sequence_length=max_sequence_length,
                dtype=dtype,
            )

        if do_classifier_free_guidance and negative_prompt_embeds is None:
            negative_prompt = negative_prompt or ""
            negative_prompt = batch_size * [negative_prompt] if isinstance(negative_prompt, str) else negative_prompt

            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`."
                )

            negative_prompt_embeds = self._get_t5_prompt_embeds(
                prompt=negative_prompt,
                num_videos_per_prompt=num_videos_per_prompt,
                max_sequence_length=max_sequence_length,
                dtype=dtype,
            )

        return prompt_embeds, negative_prompt_embeds

    def check_inputs(
        self,
        prompt,
        negative_prompt,
        image,
        height,
        width,
        prompt_embeds=None,
        negative_prompt_embeds=None,
        image_embeds=None,
        callback_on_step_end_tensor_inputs=None,
    ):
        if image is not None and image_embeds is not None:
            raise ValueError(
                f"Cannot forward both `image`: {image} and `image_embeds`: {image_embeds}. Please make sure to"
                " only forward one of the two."
            )
        if image is None and image_embeds is None:
            raise ValueError(
                "Provide either `image` or `prompt_embeds`. Cannot leave both `image` and `image_embeds` undefined."
            )
        if image is not None and not isinstance(image, ms.Tensor) and not isinstance(image, PIL.Image.Image):
            raise ValueError(f"`image` has to be of type `ms.Tensor` or `PIL.Image.Image` but is {type(image)}")
        if height % 16 != 0 or width % 16 != 0:
            raise ValueError(f"`height` and `width` have to be divisible by 16 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 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`: {negative_prompt_embeds}. Please make sure to"  # noqa: E501
                " 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 negative_prompt is not None and (
            not isinstance(negative_prompt, str) and not isinstance(negative_prompt, list)
        ):
            raise ValueError(f"`negative_prompt` has to be of type `str` or `list` but is {type(negative_prompt)}")

    def prepare_latents(
        self,
        image: PipelineImageInput,
        batch_size: int,
        num_channels_latents: int = 16,
        height: int = 480,
        width: int = 832,
        num_frames: int = 81,
        dtype: Optional[ms.Type] = None,
        generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
        latents: Optional[ms.Tensor] = None,
        last_image: Optional[ms.Tensor] = None,
    ) -> Tuple[ms.Tensor, ms.Tensor]:
        num_latent_frames = (num_frames - 1) // self.vae_scale_factor_temporal + 1
        latent_height = height // self.vae_scale_factor_spatial
        latent_width = width // self.vae_scale_factor_spatial

        shape = (batch_size, num_channels_latents, num_latent_frames, latent_height, latent_width)
        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)
        else:
            latents = latents.to(dtype=dtype)

        image = image.unsqueeze(2)
        if last_image is None:
            video_condition = mint.cat(
                [image, image.new_zeros((image.shape[0], image.shape[1], num_frames - 1, height, width))], dim=2
            )
        else:
            last_image = last_image.unsqueeze(2)
            video_condition = mint.cat(
                [image, image.new_zeros((image.shape[0], image.shape[1], num_frames - 2, height, width)), last_image],
                dim=2,
            )
        video_condition = video_condition.to(dtype=self.vae.dtype)

        latents_mean = ms.tensor(self.vae.config.latents_mean).view(1, self.vae.config.z_dim, 1, 1, 1).to(latents.dtype)
        latents_std = 1.0 / ms.tensor(self.vae.config.latents_std).view(1, self.vae.config.z_dim, 1, 1, 1).to(
            latents.dtype
        )

        # TODO: we use pynative mode here since there is cache in vae.encode which not supported in graph mode
        with pynative_context():
            if isinstance(generator, list):
                latent_condition = [
                    retrieve_latents(self.vae, self.vae.encode(video_condition)[0], sample_mode="argmax")
                    for _ in generator
                ]
                latent_condition = mint.cat(latent_condition)
            else:
                latent_condition = retrieve_latents(self.vae, self.vae.encode(video_condition)[0], sample_mode="argmax")
                latent_condition = latent_condition.tile((batch_size, 1, 1, 1, 1))

        latent_condition = latent_condition.to(dtype)
        latent_condition = (latent_condition - latents_mean) * latents_std

        mask_lat_size = mint.ones((batch_size, 1, num_frames, latent_height, latent_width))

        if last_image is None:
            mask_lat_size[:, :, list(range(1, num_frames))] = 0
        else:
            mask_lat_size[:, :, list(range(1, num_frames - 1))] = 0
        first_frame_mask = mask_lat_size[:, :, 0:1]
        first_frame_mask = mint.repeat_interleave(first_frame_mask, dim=2, repeats=self.vae_scale_factor_temporal)
        mask_lat_size = mint.concat([first_frame_mask, mask_lat_size[:, :, 1:, :]], dim=2)
        mask_lat_size = mask_lat_size.view(batch_size, -1, self.vae_scale_factor_temporal, latent_height, latent_width)
        mask_lat_size = mask_lat_size.swapaxes(1, 2)

        return latents, mint.concat([mask_lat_size, latent_condition], dim=1)

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

    @property
    def do_classifier_free_guidance(self):
        return self._guidance_scale > 1

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

    @property
    def current_timestep(self):
        return self._current_timestep

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

    @property
    def attention_kwargs(self):
        return self._attention_kwargs

    def __call__(
        self,
        image: PipelineImageInput,
        prompt: Union[str, List[str]] = None,
        negative_prompt: Union[str, List[str]] = None,
        height: int = 480,
        width: int = 832,
        num_frames: int = 81,
        num_inference_steps: int = 50,
        guidance_scale: float = 5.0,
        num_videos_per_prompt: Optional[int] = 1,
        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,
        image_embeds: Optional[ms.Tensor] = None,
        last_image: Optional[ms.Tensor] = None,
        output_type: Optional[str] = "np",
        return_dict: bool = False,
        attention_kwargs: Optional[Dict[str, Any]] = None,
        callback_on_step_end: Optional[
            Union[Callable[[int, int, Dict], None], PipelineCallback, MultiPipelineCallbacks]
        ] = None,
        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
        max_sequence_length: int = 512,
    ):
        r"""
        The call function to the pipeline for generation.

        Args:
            image (`PipelineImageInput`):
                The input image to condition the generation on. Must be an image, a list of images or a `ms.Tensor`.
            prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
                instead.
            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`).
            height (`int`, defaults to `480`):
                The height of the generated video.
            width (`int`, defaults to `832`):
                The width of the generated video.
            num_frames (`int`, defaults to `81`):
                The number of frames in the generated video.
            num_inference_steps (`int`, defaults to `50`):
                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                expense of slower inference.
            guidance_scale (`float`, defaults to `5.0`):
                Guidance scale as defined in [Classifier-Free Diffusion
                Guidance](https://huggingface.co/papers/2207.12598). `guidance_scale` is defined as `w` of equation 2.
                of [Imagen Paper](https://huggingface.co/papers/2205.11487). 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 image quality.
            num_videos_per_prompt (`int`, *optional*, defaults to 1):
                The number of images to generate per prompt.
            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 image
                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`.
            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 text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
                provided, text embeddings are generated from the `negative_prompt` input argument.
            image_embeds (`ms.Tensor`, *optional*):
                Pre-generated image embeddings. Can be used to easily tweak image inputs (weighting). If not provided,
                image embeddings are generated from the `image` input argument.
            output_type (`str`, *optional*, defaults to `"np"`):
                The output format of the generated image. Choose between `PIL.Image` or `np.array`.
            return_dict (`bool`, *optional*, defaults to `False`):
                Whether or not to return a [`WanPipelineOutput`] instead of a plain tuple.
            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).
            callback_on_step_end (`Callable`, `PipelineCallback`, `MultiPipelineCallbacks`, *optional*):
                A function or a subclass of `PipelineCallback` or `MultiPipelineCallbacks` that is called at the end of
                each denoising step during the inference. 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.
            max_sequence_length (`int`, defaults to `512`):
                The maximum sequence length of the text encoder. If the prompt is longer than this, it will be
                truncated. If the prompt is shorter, it will be padded to this length.

        Examples:

        Returns:
            [`~WanPipelineOutput`] or `tuple`:
                If `return_dict` is `True`, [`WanPipelineOutput`] is returned, otherwise a `tuple` is returned where
                the first element is a list with the generated images and the second element is a list of `bool`s
                indicating whether the corresponding generated image contains "not-safe-for-work" (nsfw) content.
        """

        if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)):
            callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs

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

        if num_frames % self.vae_scale_factor_temporal != 1:
            logger.warning(
                f"`num_frames - 1` has to be divisible by {self.vae_scale_factor_temporal}. Rounding to the nearest number."
            )
            num_frames = num_frames // self.vae_scale_factor_temporal * self.vae_scale_factor_temporal + 1
        num_frames = max(num_frames, 1)

        self._guidance_scale = guidance_scale
        self._attention_kwargs = attention_kwargs
        self._current_timestep = None
        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
        prompt_embeds, negative_prompt_embeds = self.encode_prompt(
            prompt=prompt,
            negative_prompt=negative_prompt,
            do_classifier_free_guidance=self.do_classifier_free_guidance,
            num_videos_per_prompt=num_videos_per_prompt,
            prompt_embeds=prompt_embeds,
            negative_prompt_embeds=negative_prompt_embeds,
            max_sequence_length=max_sequence_length,
        )

        # Encode image embedding
        transformer_dtype = self.transformer.dtype
        prompt_embeds = prompt_embeds.to(transformer_dtype)
        if negative_prompt_embeds is not None:
            negative_prompt_embeds = negative_prompt_embeds.to(transformer_dtype)

        if image_embeds is None:
            if last_image is None:
                image_embeds = self.encode_image(image)
            else:
                image_embeds = self.encode_image([image, last_image])
        image_embeds = image_embeds.tile((batch_size, 1, 1))
        image_embeds = image_embeds.to(transformer_dtype)

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

        # 5. Prepare latent variables
        num_channels_latents = self.vae.config.z_dim
        image = self.video_processor.preprocess(image, height=height, width=width).to(dtype=ms.float32)
        if last_image is not None:
            last_image = self.video_processor.preprocess(last_image, height=height, width=width).to(dtype=ms.float32)
        latents, condition = self.prepare_latents(
            image,
            batch_size * num_videos_per_prompt,
            num_channels_latents,
            height,
            width,
            num_frames,
            ms.float32,
            generator,
            latents,
            last_image,
        )

        # 6. Denoising loop
        num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
        self._num_timesteps = len(timesteps)

        with self.progress_bar(total=num_inference_steps) as progress_bar:
            for i, t in enumerate(timesteps):
                if self.interrupt:
                    continue

                self._current_timestep = t
                latent_model_input = mint.cat([latents, condition], dim=1).to(transformer_dtype)
                timestep = t.broadcast_to((latents.shape[0],))

                noise_pred = self.transformer(
                    hidden_states=latent_model_input,
                    timestep=timestep,
                    encoder_hidden_states=prompt_embeds,
                    encoder_hidden_states_image=image_embeds,
                    attention_kwargs=attention_kwargs,
                    return_dict=False,
                )[0]

                if self.do_classifier_free_guidance:
                    noise_uncond = self.transformer(
                        hidden_states=latent_model_input,
                        timestep=timestep,
                        encoder_hidden_states=negative_prompt_embeds,
                        encoder_hidden_states_image=image_embeds,
                        attention_kwargs=attention_kwargs,
                        return_dict=False,
                    )[0]
                    noise_pred = noise_uncond + guidance_scale * (noise_pred - noise_uncond)

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

                # 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()

        self._current_timestep = None

        if not output_type == "latent":
            latents = latents.to(self.vae.dtype)
            latents_mean = (
                ms.tensor(self.vae.config.latents_mean).view(1, self.vae.config.z_dim, 1, 1, 1).to(latents.dtype)
            )
            latents_std = 1.0 / ms.tensor(self.vae.config.latents_std).view(1, self.vae.config.z_dim, 1, 1, 1).to(
                latents.dtype
            )
            latents = latents / latents_std + latents_mean
            # TODO: we use pynative mode here since cache in vae.decode which not supported in graph mode
            with pynative_context():
                video = self.vae.decode(latents, return_dict=False)[0]
            video = self.video_processor.postprocess_video(video, output_type=output_type)
        else:
            video = latents

        if not return_dict:
            return (video,)

        return WanPipelineOutput(frames=video)

mindone.diffusers.WanImageToVideoPipeline.__call__(image, prompt=None, negative_prompt=None, height=480, width=832, num_frames=81, num_inference_steps=50, guidance_scale=5.0, num_videos_per_prompt=1, generator=None, latents=None, prompt_embeds=None, negative_prompt_embeds=None, image_embeds=None, last_image=None, output_type='np', return_dict=False, attention_kwargs=None, callback_on_step_end=None, callback_on_step_end_tensor_inputs=['latents'], max_sequence_length=512)

The call function to the pipeline for generation.

PARAMETER	DESCRIPTION
image	The input image to condition the generation on. Must be an image, a list of images or a ms.Tensor. TYPE: `PipelineImageInput`
prompt	The prompt or prompts to guide the image generation. If not defined, one has to pass prompt_embeds. instead. TYPE: `str` or `List[str]`, *optional* DEFAULT: None
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
height	The height of the generated video. TYPE: `int`, defaults to `480` DEFAULT: 480
width	The width of the generated video. TYPE: `int`, defaults to `832` DEFAULT: 832
num_frames	The number of frames in the generated video. TYPE: `int`, defaults to `81` DEFAULT: 81
num_inference_steps	The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference. TYPE: `int`, defaults to `50` DEFAULT: 50
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 image quality. TYPE: `float`, defaults to `5.0` DEFAULT: 5.0
num_videos_per_prompt	The number of images to generate per prompt. TYPE: `int`, *optional*, defaults to 1 DEFAULT: 1
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 image 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. 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 text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not provided, text embeddings are generated from the negative_prompt input argument. TYPE: `ms.Tensor`, *optional* DEFAULT: None
image_embeds	Pre-generated image embeddings. Can be used to easily tweak image inputs (weighting). If not provided, image embeddings are generated from the image input argument. TYPE: `ms.Tensor`, *optional* DEFAULT: None
output_type	The output format of the generated image. Choose between PIL.Image or np.array. TYPE: `str`, *optional*, defaults to `"np"` DEFAULT: 'np'
return_dict	Whether or not to return a [WanPipelineOutput] instead of a plain tuple. TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False
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
callback_on_step_end	A function or a subclass of PipelineCallback or MultiPipelineCallbacks that is called at the end of each denoising step during the inference. 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`, `PipelineCallback`, `MultiPipelineCallbacks`, *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']
max_sequence_length	The maximum sequence length of the text encoder. If the prompt is longer than this, it will be truncated. If the prompt is shorter, it will be padded to this length. TYPE: `int`, defaults to `512` DEFAULT: 512

RETURNS	DESCRIPTION
	[~WanPipelineOutput] or tuple: If return_dict is True, [WanPipelineOutput] is returned, otherwise a tuple is returned where the first element is a list with the generated images and the second element is a list of bools indicating whether the corresponding generated image contains "not-safe-for-work" (nsfw) content.

Source code in mindone/diffusers/pipelines/wan/pipeline_wan_i2v.py

def __call__(
    self,
    image: PipelineImageInput,
    prompt: Union[str, List[str]] = None,
    negative_prompt: Union[str, List[str]] = None,
    height: int = 480,
    width: int = 832,
    num_frames: int = 81,
    num_inference_steps: int = 50,
    guidance_scale: float = 5.0,
    num_videos_per_prompt: Optional[int] = 1,
    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,
    image_embeds: Optional[ms.Tensor] = None,
    last_image: Optional[ms.Tensor] = None,
    output_type: Optional[str] = "np",
    return_dict: bool = False,
    attention_kwargs: Optional[Dict[str, Any]] = None,
    callback_on_step_end: Optional[
        Union[Callable[[int, int, Dict], None], PipelineCallback, MultiPipelineCallbacks]
    ] = None,
    callback_on_step_end_tensor_inputs: List[str] = ["latents"],
    max_sequence_length: int = 512,
):
    r"""
    The call function to the pipeline for generation.

    Args:
        image (`PipelineImageInput`):
            The input image to condition the generation on. Must be an image, a list of images or a `ms.Tensor`.
        prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
            instead.
        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`).
        height (`int`, defaults to `480`):
            The height of the generated video.
        width (`int`, defaults to `832`):
            The width of the generated video.
        num_frames (`int`, defaults to `81`):
            The number of frames in the generated video.
        num_inference_steps (`int`, defaults to `50`):
            The number of denoising steps. More denoising steps usually lead to a higher quality image at the
            expense of slower inference.
        guidance_scale (`float`, defaults to `5.0`):
            Guidance scale as defined in [Classifier-Free Diffusion
            Guidance](https://huggingface.co/papers/2207.12598). `guidance_scale` is defined as `w` of equation 2.
            of [Imagen Paper](https://huggingface.co/papers/2205.11487). 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 image quality.
        num_videos_per_prompt (`int`, *optional*, defaults to 1):
            The number of images to generate per prompt.
        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 image
            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`.
        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 text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
            provided, text embeddings are generated from the `negative_prompt` input argument.
        image_embeds (`ms.Tensor`, *optional*):
            Pre-generated image embeddings. Can be used to easily tweak image inputs (weighting). If not provided,
            image embeddings are generated from the `image` input argument.
        output_type (`str`, *optional*, defaults to `"np"`):
            The output format of the generated image. Choose between `PIL.Image` or `np.array`.
        return_dict (`bool`, *optional*, defaults to `False`):
            Whether or not to return a [`WanPipelineOutput`] instead of a plain tuple.
        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).
        callback_on_step_end (`Callable`, `PipelineCallback`, `MultiPipelineCallbacks`, *optional*):
            A function or a subclass of `PipelineCallback` or `MultiPipelineCallbacks` that is called at the end of
            each denoising step during the inference. 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.
        max_sequence_length (`int`, defaults to `512`):
            The maximum sequence length of the text encoder. If the prompt is longer than this, it will be
            truncated. If the prompt is shorter, it will be padded to this length.

    Examples:

    Returns:
        [`~WanPipelineOutput`] or `tuple`:
            If `return_dict` is `True`, [`WanPipelineOutput`] is returned, otherwise a `tuple` is returned where
            the first element is a list with the generated images and the second element is a list of `bool`s
            indicating whether the corresponding generated image contains "not-safe-for-work" (nsfw) content.
    """

    if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)):
        callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs

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

    if num_frames % self.vae_scale_factor_temporal != 1:
        logger.warning(
            f"`num_frames - 1` has to be divisible by {self.vae_scale_factor_temporal}. Rounding to the nearest number."
        )
        num_frames = num_frames // self.vae_scale_factor_temporal * self.vae_scale_factor_temporal + 1
    num_frames = max(num_frames, 1)

    self._guidance_scale = guidance_scale
    self._attention_kwargs = attention_kwargs
    self._current_timestep = None
    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
    prompt_embeds, negative_prompt_embeds = self.encode_prompt(
        prompt=prompt,
        negative_prompt=negative_prompt,
        do_classifier_free_guidance=self.do_classifier_free_guidance,
        num_videos_per_prompt=num_videos_per_prompt,
        prompt_embeds=prompt_embeds,
        negative_prompt_embeds=negative_prompt_embeds,
        max_sequence_length=max_sequence_length,
    )

    # Encode image embedding
    transformer_dtype = self.transformer.dtype
    prompt_embeds = prompt_embeds.to(transformer_dtype)
    if negative_prompt_embeds is not None:
        negative_prompt_embeds = negative_prompt_embeds.to(transformer_dtype)

    if image_embeds is None:
        if last_image is None:
            image_embeds = self.encode_image(image)
        else:
            image_embeds = self.encode_image([image, last_image])
    image_embeds = image_embeds.tile((batch_size, 1, 1))
    image_embeds = image_embeds.to(transformer_dtype)

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

    # 5. Prepare latent variables
    num_channels_latents = self.vae.config.z_dim
    image = self.video_processor.preprocess(image, height=height, width=width).to(dtype=ms.float32)
    if last_image is not None:
        last_image = self.video_processor.preprocess(last_image, height=height, width=width).to(dtype=ms.float32)
    latents, condition = self.prepare_latents(
        image,
        batch_size * num_videos_per_prompt,
        num_channels_latents,
        height,
        width,
        num_frames,
        ms.float32,
        generator,
        latents,
        last_image,
    )

    # 6. Denoising loop
    num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
    self._num_timesteps = len(timesteps)

    with self.progress_bar(total=num_inference_steps) as progress_bar:
        for i, t in enumerate(timesteps):
            if self.interrupt:
                continue

            self._current_timestep = t
            latent_model_input = mint.cat([latents, condition], dim=1).to(transformer_dtype)
            timestep = t.broadcast_to((latents.shape[0],))

            noise_pred = self.transformer(
                hidden_states=latent_model_input,
                timestep=timestep,
                encoder_hidden_states=prompt_embeds,
                encoder_hidden_states_image=image_embeds,
                attention_kwargs=attention_kwargs,
                return_dict=False,
            )[0]

            if self.do_classifier_free_guidance:
                noise_uncond = self.transformer(
                    hidden_states=latent_model_input,
                    timestep=timestep,
                    encoder_hidden_states=negative_prompt_embeds,
                    encoder_hidden_states_image=image_embeds,
                    attention_kwargs=attention_kwargs,
                    return_dict=False,
                )[0]
                noise_pred = noise_uncond + guidance_scale * (noise_pred - noise_uncond)

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

            # 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()

    self._current_timestep = None

    if not output_type == "latent":
        latents = latents.to(self.vae.dtype)
        latents_mean = (
            ms.tensor(self.vae.config.latents_mean).view(1, self.vae.config.z_dim, 1, 1, 1).to(latents.dtype)
        )
        latents_std = 1.0 / ms.tensor(self.vae.config.latents_std).view(1, self.vae.config.z_dim, 1, 1, 1).to(
            latents.dtype
        )
        latents = latents / latents_std + latents_mean
        # TODO: we use pynative mode here since cache in vae.decode which not supported in graph mode
        with pynative_context():
            video = self.vae.decode(latents, return_dict=False)[0]
        video = self.video_processor.postprocess_video(video, output_type=output_type)
    else:
        video = latents

    if not return_dict:
        return (video,)

    return WanPipelineOutput(frames=video)

mindone.diffusers.WanImageToVideoPipeline.encode_prompt(prompt, negative_prompt=None, do_classifier_free_guidance=True, num_videos_per_prompt=1, prompt_embeds=None, negative_prompt_embeds=None, max_sequence_length=226, dtype=None)

Encodes the prompt into text encoder hidden states.

PARAMETER	DESCRIPTION
prompt	prompt to be encoded TYPE: `str` or `List[str]`, *optional*
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
do_classifier_free_guidance	Whether to use classifier free guidance or not. TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True
num_videos_per_prompt	Number of videos that should be generated per prompt. TYPE: `int`, *optional*, defaults to 1 DEFAULT: 1
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
dtype	(ms.Type, optional): mindspore dtype TYPE: Optional[Type] DEFAULT: None

Source code in mindone/diffusers/pipelines/wan/pipeline_wan_i2v.py

def encode_prompt(
    self,
    prompt: Union[str, List[str]],
    negative_prompt: Optional[Union[str, List[str]]] = None,
    do_classifier_free_guidance: bool = True,
    num_videos_per_prompt: int = 1,
    prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    max_sequence_length: int = 226,
    dtype: Optional[ms.Type] = None,
):
    r"""
    Encodes the prompt into text encoder hidden states.

    Args:
        prompt (`str` or `List[str]`, *optional*):
            prompt to be encoded
        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`).
        do_classifier_free_guidance (`bool`, *optional*, defaults to `True`):
            Whether to use classifier free guidance or not.
        num_videos_per_prompt (`int`, *optional*, defaults to 1):
            Number of videos that should be generated per prompt.
        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.
        dtype: (`ms.Type`, *optional*):
            mindspore dtype
    """
    prompt = [prompt] if isinstance(prompt, str) else prompt
    if prompt is not None:
        batch_size = len(prompt)
    else:
        batch_size = prompt_embeds.shape[0]

    if prompt_embeds is None:
        prompt_embeds = self._get_t5_prompt_embeds(
            prompt=prompt,
            num_videos_per_prompt=num_videos_per_prompt,
            max_sequence_length=max_sequence_length,
            dtype=dtype,
        )

    if do_classifier_free_guidance and negative_prompt_embeds is None:
        negative_prompt = negative_prompt or ""
        negative_prompt = batch_size * [negative_prompt] if isinstance(negative_prompt, str) else negative_prompt

        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`."
            )

        negative_prompt_embeds = self._get_t5_prompt_embeds(
            prompt=negative_prompt,
            num_videos_per_prompt=num_videos_per_prompt,
            max_sequence_length=max_sequence_length,
            dtype=dtype,
        )

    return prompt_embeds, negative_prompt_embeds

mindone.diffusers.WanVideoToVideoPipeline

Bases: DiffusionPipeline, WanLoraLoaderMixin

Pipeline for video-to-video generation using Wan.

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.).

PARAMETER	DESCRIPTION
tokenizer	Tokenizer from T5, specifically the google/umt5-xxl variant. TYPE: [`T5Tokenizer`]
text_encoder	T5, specifically the google/umt5-xxl variant. TYPE: [`T5EncoderModel`]
transformer	Conditional Transformer to denoise the input latents. TYPE: [`WanTransformer3DModel`]
scheduler	A scheduler to be used in combination with transformer to denoise the encoded image latents. TYPE: [`UniPCMultistepScheduler`]
vae	Variational Auto-Encoder (VAE) Model to encode and decode videos to and from latent representations. TYPE: [`AutoencoderKLWan`]

Source code in mindone/diffusers/pipelines/wan/pipeline_wan_video2video.py

class WanVideoToVideoPipeline(DiffusionPipeline, WanLoraLoaderMixin):
    r"""
    Pipeline for video-to-video generation using Wan.

    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.).

    Args:
        tokenizer ([`T5Tokenizer`]):
            Tokenizer from [T5](https://huggingface.co/docs/transformers/en/model_doc/t5#transformers.T5Tokenizer),
            specifically the [google/umt5-xxl](https://huggingface.co/google/umt5-xxl) variant.
        text_encoder ([`T5EncoderModel`]):
            [T5](https://huggingface.co/docs/transformers/en/model_doc/t5#transformers.T5EncoderModel), specifically
            the [google/umt5-xxl](https://huggingface.co/google/umt5-xxl) variant.
        transformer ([`WanTransformer3DModel`]):
            Conditional Transformer to denoise the input latents.
        scheduler ([`UniPCMultistepScheduler`]):
            A scheduler to be used in combination with `transformer` to denoise the encoded image latents.
        vae ([`AutoencoderKLWan`]):
            Variational Auto-Encoder (VAE) Model to encode and decode videos to and from latent representations.
    """

    model_cpu_offload_seq = "text_encoder->transformer->vae"
    _callback_tensor_inputs = ["latents", "prompt_embeds", "negative_prompt_embeds"]

    def __init__(
        self,
        tokenizer: AutoTokenizer,
        text_encoder: UMT5EncoderModel,
        transformer: WanTransformer3DModel,
        vae: AutoencoderKLWan,
        scheduler: FlowMatchEulerDiscreteScheduler,
    ):
        super().__init__()

        self.register_modules(
            vae=vae,
            text_encoder=text_encoder,
            tokenizer=tokenizer,
            transformer=transformer,
            scheduler=scheduler,
        )

        self.vae_scale_factor_temporal = 2 ** sum(self.vae.temperal_downsample) if getattr(self, "vae", None) else 4
        self.vae_scale_factor_spatial = 2 ** len(self.vae.temperal_downsample) if getattr(self, "vae", None) else 8
        self.video_processor = VideoProcessor(vae_scale_factor=self.vae_scale_factor_spatial)

    # Copied from diffusers.pipelines.wan.pipeline_wan.WanPipeline._get_t5_prompt_embeds
    def _get_t5_prompt_embeds(
        self,
        prompt: Union[str, List[str]] = None,
        num_videos_per_prompt: int = 1,
        max_sequence_length: int = 226,
        dtype: Optional[ms.Type] = None,
    ):
        dtype = dtype or self.text_encoder.dtype

        prompt = [prompt] if isinstance(prompt, str) else prompt
        prompt = [prompt_clean(u) for u in prompt]
        batch_size = len(prompt)

        text_inputs = self.tokenizer(
            prompt,
            padding="max_length",
            max_length=max_sequence_length,
            truncation=True,
            add_special_tokens=True,
            return_attention_mask=True,
            return_tensors="np",
        )
        text_input_ids, mask = ms.tensor(text_inputs.input_ids), ms.tensor(text_inputs.attention_mask)
        seq_lens = mask.gt(0).sum(dim=1).long()

        prompt_embeds = self.text_encoder(text_input_ids, mask)[0]
        prompt_embeds = prompt_embeds.to(dtype=dtype)
        prompt_embeds = [u[:v] for u, v in zip(prompt_embeds, seq_lens)]
        prompt_embeds = mint.stack(
            [mint.cat([u, u.new_zeros((max_sequence_length - u.shape[0], u.shape[1]))]) for u in prompt_embeds], dim=0
        )

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

        return prompt_embeds

    # Copied from diffusers.pipelines.wan.pipeline_wan.WanPipeline.encode_prompt
    def encode_prompt(
        self,
        prompt: Union[str, List[str]],
        negative_prompt: Optional[Union[str, List[str]]] = None,
        do_classifier_free_guidance: bool = True,
        num_videos_per_prompt: int = 1,
        prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        max_sequence_length: int = 226,
        dtype: Optional[ms.Type] = None,
    ):
        r"""
        Encodes the prompt into text encoder hidden states.

        Args:
            prompt (`str` or `List[str]`, *optional*):
                prompt to be encoded
            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`).
            do_classifier_free_guidance (`bool`, *optional*, defaults to `True`):
                Whether to use classifier free guidance or not.
            num_videos_per_prompt (`int`, *optional*, defaults to 1):
                Number of videos that should be generated per prompt.
            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.
            dtype: (`ms.Type`, *optional*):
                mindspore dtype
        """
        prompt = [prompt] if isinstance(prompt, str) else prompt
        if prompt is not None:
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        if prompt_embeds is None:
            prompt_embeds = self._get_t5_prompt_embeds(
                prompt=prompt,
                num_videos_per_prompt=num_videos_per_prompt,
                max_sequence_length=max_sequence_length,
                dtype=dtype,
            )

        if do_classifier_free_guidance and negative_prompt_embeds is None:
            negative_prompt = negative_prompt or ""
            negative_prompt = batch_size * [negative_prompt] if isinstance(negative_prompt, str) else negative_prompt

            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`."
                )

            negative_prompt_embeds = self._get_t5_prompt_embeds(
                prompt=negative_prompt,
                num_videos_per_prompt=num_videos_per_prompt,
                max_sequence_length=max_sequence_length,
                dtype=dtype,
            )

        return prompt_embeds, negative_prompt_embeds

    def check_inputs(
        self,
        prompt,
        negative_prompt,
        height,
        width,
        video=None,
        latents=None,
        prompt_embeds=None,
        negative_prompt_embeds=None,
        callback_on_step_end_tensor_inputs=None,
    ):
        if height % 16 != 0 or width % 16 != 0:
            raise ValueError(f"`height` and `width` have to be divisible by 16 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 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`: {negative_prompt_embeds}. Please make sure to"  # noqa: E501
                " 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 negative_prompt is not None and (
            not isinstance(negative_prompt, str) and not isinstance(negative_prompt, list)
        ):
            raise ValueError(f"`negative_prompt` has to be of type `str` or `list` but is {type(negative_prompt)}")

        if video is not None and latents is not None:
            raise ValueError("Only one of `video` or `latents` should be provided")

    def prepare_latents(
        self,
        video: Optional[ms.Tensor] = None,
        batch_size: int = 1,
        num_channels_latents: int = 16,
        height: int = 480,
        width: int = 832,
        dtype: Optional[ms.Type] = None,
        generator: Optional[np.random.Generator] = None,
        latents: Optional[ms.Tensor] = None,
        timestep: Optional[ms.Tensor] = 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."
            )

        num_latent_frames = (
            (video.shape[2] - 1) // self.vae_scale_factor_temporal + 1 if latents is None else latents.shape[1]
        )
        shape = (
            batch_size,
            num_channels_latents,
            num_latent_frames,
            height // self.vae_scale_factor_spatial,
            width // self.vae_scale_factor_spatial,
        )

        if latents is None:
            # TODO: we use pynative mode here since cache in vae.encode which not supported in graph mode
            with pynative_context():
                init_latents = [
                    retrieve_latents(self.vae, self.vae.encode(vid.unsqueeze(0))[0], sample_mode="argmax")
                    for vid in video
                ]

            init_latents = mint.cat(init_latents, dim=0).to(dtype)

            latents_mean = ms.tensor(self.vae.config.latents_mean).view(1, self.vae.config.z_dim, 1, 1, 1).to(dtype)
            latents_std = 1.0 / ms.tensor(self.vae.config.latents_std).view(1, self.vae.config.z_dim, 1, 1, 1).to(dtype)

            init_latents = (init_latents - latents_mean) * latents_std

            noise = randn_tensor(shape, generator=generator, dtype=dtype)
            if hasattr(self.scheduler, "add_noise"):
                latents = self.scheduler.add_noise(init_latents, noise, timestep)
            else:
                latents = self.scheduler.scale_noise(init_latents, timestep, noise)

        return latents

    # Copied from diffusers.pipelines.animatediff.pipeline_animatediff_video2video.AnimateDiffVideoToVideoPipeline.get_timesteps
    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

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

    @property
    def do_classifier_free_guidance(self):
        return self._guidance_scale > 1.0

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

    @property
    def current_timestep(self):
        return self._current_timestep

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

    @property
    def attention_kwargs(self):
        return self._attention_kwargs

    def __call__(
        self,
        video: List[Image.Image] = None,
        prompt: Union[str, List[str]] = None,
        negative_prompt: Union[str, List[str]] = None,
        height: int = 480,
        width: int = 832,
        num_inference_steps: int = 50,
        timesteps: Optional[List[int]] = None,
        guidance_scale: float = 5.0,
        strength: float = 0.8,
        num_videos_per_prompt: Optional[int] = 1,
        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,
        output_type: Optional[str] = "np",
        return_dict: bool = False,
        attention_kwargs: Optional[Dict[str, Any]] = None,
        callback_on_step_end: Optional[
            Union[Callable[[int, int, Dict], None], PipelineCallback, MultiPipelineCallbacks]
        ] = None,
        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
        max_sequence_length: int = 512,
    ):
        r"""
        The call function to the pipeline for generation.

        Args:
            prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`
                instead.
            height (`int`, defaults to `480`):
                The height in pixels of the generated image.
            width (`int`, defaults to `832`):
                The width in pixels of the generated image.
            num_frames (`int`, defaults to `81`):
                The number of frames in the generated video.
            num_inference_steps (`int`, defaults to `50`):
                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                expense of slower inference.
            guidance_scale (`float`, defaults to `5.0`):
                Guidance scale as defined in [Classifier-Free Diffusion
                Guidance](https://huggingface.co/papers/2207.12598). `guidance_scale` is defined as `w` of equation 2.
                of [Imagen Paper](https://huggingface.co/papers/2205.11487). 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 image quality.
            strength (`float`, defaults to `0.8`):
                Higher strength leads to more differences between original image and generated video.
            num_videos_per_prompt (`int`, *optional*, defaults to 1):
                The number of images to generate per prompt.
            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 image
                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`.
            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.
            output_type (`str`, *optional*, defaults to `"np"`):
                The output format of the generated image. Choose between `PIL.Image` or `np.array`.
            return_dict (`bool`, *optional*, defaults to `False`):
                Whether or not to return a [`WanPipelineOutput`] instead of a plain tuple.
            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).
            callback_on_step_end (`Callable`, `PipelineCallback`, `MultiPipelineCallbacks`, *optional*):
                A function or a subclass of `PipelineCallback` or `MultiPipelineCallbacks` that is called at the end of
                each denoising step during the inference. 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.
            max_sequence_length (`int`, defaults to `512`):
                The maximum sequence length of the text encoder. If the prompt is longer than this, it will be
                truncated. If the prompt is shorter, it will be padded to this length.

        Examples:

        Returns:
            [`~WanPipelineOutput`] or `tuple`:
                If `return_dict` is `True`, [`WanPipelineOutput`] is returned, otherwise a `tuple` is returned where
                the first element is a list with the generated images and the second element is a list of `bool`s
                indicating whether the corresponding generated image contains "not-safe-for-work" (nsfw) content.
        """

        if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)):
            callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs

        height = height or self.transformer.config.sample_height * self.vae_scale_factor_spatial
        width = width or self.transformer.config.sample_width * self.vae_scale_factor_spatial
        num_videos_per_prompt = 1

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

        self._guidance_scale = guidance_scale
        self._attention_kwargs = attention_kwargs
        self._current_timestep = None
        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
        prompt_embeds, negative_prompt_embeds = self.encode_prompt(
            prompt=prompt,
            negative_prompt=negative_prompt,
            do_classifier_free_guidance=self.do_classifier_free_guidance,
            num_videos_per_prompt=num_videos_per_prompt,
            prompt_embeds=prompt_embeds,
            negative_prompt_embeds=negative_prompt_embeds,
            max_sequence_length=max_sequence_length,
        )

        transformer_dtype = self.transformer.dtype
        prompt_embeds = prompt_embeds.to(transformer_dtype)
        if negative_prompt_embeds is not None:
            negative_prompt_embeds = negative_prompt_embeds.to(transformer_dtype)

        # 4. Prepare timesteps
        timesteps, num_inference_steps = retrieve_timesteps(self.scheduler, num_inference_steps, timesteps)
        timesteps, num_inference_steps = self.get_timesteps(num_inference_steps, timesteps, strength)
        latent_timestep = timesteps[:1].repeat(batch_size * num_videos_per_prompt)
        self._num_timesteps = len(timesteps)

        if latents is None:
            video = self.video_processor.preprocess_video(video, height=height, width=width).to(dtype=ms.float32)

        # 5. Prepare latent variables
        num_channels_latents = self.transformer.config.in_channels
        latents = self.prepare_latents(
            video,
            batch_size * num_videos_per_prompt,
            num_channels_latents,
            height,
            width,
            ms.float32,
            generator,
            latents,
            latent_timestep,
        )

        # 6. Denoising loop
        num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
        self._num_timesteps = len(timesteps)

        with self.progress_bar(total=num_inference_steps) as progress_bar:
            for i, t in enumerate(timesteps):
                if self.interrupt:
                    continue

                self._current_timestep = t
                latent_model_input = latents.to(transformer_dtype)
                timestep = t.broadcast_to((latents.shape[0],))

                noise_pred = self.transformer(
                    hidden_states=latent_model_input,
                    timestep=timestep,
                    encoder_hidden_states=prompt_embeds,
                    attention_kwargs=attention_kwargs,
                    return_dict=False,
                )[0]

                if self.do_classifier_free_guidance:
                    noise_uncond = self.transformer(
                        hidden_states=latent_model_input,
                        timestep=timestep,
                        encoder_hidden_states=negative_prompt_embeds,
                        attention_kwargs=attention_kwargs,
                        return_dict=False,
                    )[0]
                    noise_pred = noise_uncond + guidance_scale * (noise_pred - noise_uncond)

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

                # 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()

        self._current_timestep = None

        if not output_type == "latent":
            latents = latents.to(self.vae.dtype)
            latents_mean = (
                ms.tensor(self.vae.config.latents_mean).view(1, self.vae.config.z_dim, 1, 1, 1).to(latents.dtype)
            )
            latents_std = 1.0 / ms.tensor(self.vae.config.latents_std).view(1, self.vae.config.z_dim, 1, 1, 1).to(
                latents.dtype
            )
            latents = latents / latents_std + latents_mean
            # TODO: we use pynative mode here since cache in vae.decode which not supported in graph mode
            with pynative_context():
                video = self.vae.decode(latents, return_dict=False)[0]
            video = self.video_processor.postprocess_video(video, output_type=output_type)
        else:
            video = latents

        if not return_dict:
            return (video,)

        return WanPipelineOutput(frames=video)

mindone.diffusers.WanVideoToVideoPipeline.__call__(video=None, prompt=None, negative_prompt=None, height=480, width=832, num_inference_steps=50, timesteps=None, guidance_scale=5.0, strength=0.8, num_videos_per_prompt=1, generator=None, latents=None, prompt_embeds=None, negative_prompt_embeds=None, output_type='np', return_dict=False, attention_kwargs=None, callback_on_step_end=None, callback_on_step_end_tensor_inputs=['latents'], max_sequence_length=512)

The call function to the pipeline for generation.

PARAMETER	DESCRIPTION
prompt	The prompt or prompts to guide the image generation. If not defined, one has to pass prompt_embeds instead. TYPE: `str` or `List[str]`, *optional* DEFAULT: None
height	The height in pixels of the generated image. TYPE: `int`, defaults to `480` DEFAULT: 480
width	The width in pixels of the generated image. TYPE: `int`, defaults to `832` DEFAULT: 832
num_frames	The number of frames in the generated video. TYPE: `int`, defaults to `81`
num_inference_steps	The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference. TYPE: `int`, defaults to `50` DEFAULT: 50
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 image quality. TYPE: `float`, defaults to `5.0` DEFAULT: 5.0
strength	Higher strength leads to more differences between original image and generated video. TYPE: `float`, defaults to `0.8` DEFAULT: 0.8
num_videos_per_prompt	The number of images to generate per prompt. TYPE: `int`, *optional*, defaults to 1 DEFAULT: 1
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 image 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. 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
output_type	The output format of the generated image. Choose between PIL.Image or np.array. TYPE: `str`, *optional*, defaults to `"np"` DEFAULT: 'np'
return_dict	Whether or not to return a [WanPipelineOutput] instead of a plain tuple. TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False
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
callback_on_step_end	A function or a subclass of PipelineCallback or MultiPipelineCallbacks that is called at the end of each denoising step during the inference. 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`, `PipelineCallback`, `MultiPipelineCallbacks`, *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']
max_sequence_length	The maximum sequence length of the text encoder. If the prompt is longer than this, it will be truncated. If the prompt is shorter, it will be padded to this length. TYPE: `int`, defaults to `512` DEFAULT: 512

RETURNS	DESCRIPTION
	[~WanPipelineOutput] or tuple: If return_dict is True, [WanPipelineOutput] is returned, otherwise a tuple is returned where the first element is a list with the generated images and the second element is a list of bools indicating whether the corresponding generated image contains "not-safe-for-work" (nsfw) content.

Source code in mindone/diffusers/pipelines/wan/pipeline_wan_video2video.py

def __call__(
    self,
    video: List[Image.Image] = None,
    prompt: Union[str, List[str]] = None,
    negative_prompt: Union[str, List[str]] = None,
    height: int = 480,
    width: int = 832,
    num_inference_steps: int = 50,
    timesteps: Optional[List[int]] = None,
    guidance_scale: float = 5.0,
    strength: float = 0.8,
    num_videos_per_prompt: Optional[int] = 1,
    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,
    output_type: Optional[str] = "np",
    return_dict: bool = False,
    attention_kwargs: Optional[Dict[str, Any]] = None,
    callback_on_step_end: Optional[
        Union[Callable[[int, int, Dict], None], PipelineCallback, MultiPipelineCallbacks]
    ] = None,
    callback_on_step_end_tensor_inputs: List[str] = ["latents"],
    max_sequence_length: int = 512,
):
    r"""
    The call function to the pipeline for generation.

    Args:
        prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`
            instead.
        height (`int`, defaults to `480`):
            The height in pixels of the generated image.
        width (`int`, defaults to `832`):
            The width in pixels of the generated image.
        num_frames (`int`, defaults to `81`):
            The number of frames in the generated video.
        num_inference_steps (`int`, defaults to `50`):
            The number of denoising steps. More denoising steps usually lead to a higher quality image at the
            expense of slower inference.
        guidance_scale (`float`, defaults to `5.0`):
            Guidance scale as defined in [Classifier-Free Diffusion
            Guidance](https://huggingface.co/papers/2207.12598). `guidance_scale` is defined as `w` of equation 2.
            of [Imagen Paper](https://huggingface.co/papers/2205.11487). 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 image quality.
        strength (`float`, defaults to `0.8`):
            Higher strength leads to more differences between original image and generated video.
        num_videos_per_prompt (`int`, *optional*, defaults to 1):
            The number of images to generate per prompt.
        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 image
            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`.
        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.
        output_type (`str`, *optional*, defaults to `"np"`):
            The output format of the generated image. Choose between `PIL.Image` or `np.array`.
        return_dict (`bool`, *optional*, defaults to `False`):
            Whether or not to return a [`WanPipelineOutput`] instead of a plain tuple.
        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).
        callback_on_step_end (`Callable`, `PipelineCallback`, `MultiPipelineCallbacks`, *optional*):
            A function or a subclass of `PipelineCallback` or `MultiPipelineCallbacks` that is called at the end of
            each denoising step during the inference. 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.
        max_sequence_length (`int`, defaults to `512`):
            The maximum sequence length of the text encoder. If the prompt is longer than this, it will be
            truncated. If the prompt is shorter, it will be padded to this length.

    Examples:

    Returns:
        [`~WanPipelineOutput`] or `tuple`:
            If `return_dict` is `True`, [`WanPipelineOutput`] is returned, otherwise a `tuple` is returned where
            the first element is a list with the generated images and the second element is a list of `bool`s
            indicating whether the corresponding generated image contains "not-safe-for-work" (nsfw) content.
    """

    if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)):
        callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs

    height = height or self.transformer.config.sample_height * self.vae_scale_factor_spatial
    width = width or self.transformer.config.sample_width * self.vae_scale_factor_spatial
    num_videos_per_prompt = 1

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

    self._guidance_scale = guidance_scale
    self._attention_kwargs = attention_kwargs
    self._current_timestep = None
    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
    prompt_embeds, negative_prompt_embeds = self.encode_prompt(
        prompt=prompt,
        negative_prompt=negative_prompt,
        do_classifier_free_guidance=self.do_classifier_free_guidance,
        num_videos_per_prompt=num_videos_per_prompt,
        prompt_embeds=prompt_embeds,
        negative_prompt_embeds=negative_prompt_embeds,
        max_sequence_length=max_sequence_length,
    )

    transformer_dtype = self.transformer.dtype
    prompt_embeds = prompt_embeds.to(transformer_dtype)
    if negative_prompt_embeds is not None:
        negative_prompt_embeds = negative_prompt_embeds.to(transformer_dtype)

    # 4. Prepare timesteps
    timesteps, num_inference_steps = retrieve_timesteps(self.scheduler, num_inference_steps, timesteps)
    timesteps, num_inference_steps = self.get_timesteps(num_inference_steps, timesteps, strength)
    latent_timestep = timesteps[:1].repeat(batch_size * num_videos_per_prompt)
    self._num_timesteps = len(timesteps)

    if latents is None:
        video = self.video_processor.preprocess_video(video, height=height, width=width).to(dtype=ms.float32)

    # 5. Prepare latent variables
    num_channels_latents = self.transformer.config.in_channels
    latents = self.prepare_latents(
        video,
        batch_size * num_videos_per_prompt,
        num_channels_latents,
        height,
        width,
        ms.float32,
        generator,
        latents,
        latent_timestep,
    )

    # 6. Denoising loop
    num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
    self._num_timesteps = len(timesteps)

    with self.progress_bar(total=num_inference_steps) as progress_bar:
        for i, t in enumerate(timesteps):
            if self.interrupt:
                continue

            self._current_timestep = t
            latent_model_input = latents.to(transformer_dtype)
            timestep = t.broadcast_to((latents.shape[0],))

            noise_pred = self.transformer(
                hidden_states=latent_model_input,
                timestep=timestep,
                encoder_hidden_states=prompt_embeds,
                attention_kwargs=attention_kwargs,
                return_dict=False,
            )[0]

            if self.do_classifier_free_guidance:
                noise_uncond = self.transformer(
                    hidden_states=latent_model_input,
                    timestep=timestep,
                    encoder_hidden_states=negative_prompt_embeds,
                    attention_kwargs=attention_kwargs,
                    return_dict=False,
                )[0]
                noise_pred = noise_uncond + guidance_scale * (noise_pred - noise_uncond)

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

            # 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()

    self._current_timestep = None

    if not output_type == "latent":
        latents = latents.to(self.vae.dtype)
        latents_mean = (
            ms.tensor(self.vae.config.latents_mean).view(1, self.vae.config.z_dim, 1, 1, 1).to(latents.dtype)
        )
        latents_std = 1.0 / ms.tensor(self.vae.config.latents_std).view(1, self.vae.config.z_dim, 1, 1, 1).to(
            latents.dtype
        )
        latents = latents / latents_std + latents_mean
        # TODO: we use pynative mode here since cache in vae.decode which not supported in graph mode
        with pynative_context():
            video = self.vae.decode(latents, return_dict=False)[0]
        video = self.video_processor.postprocess_video(video, output_type=output_type)
    else:
        video = latents

    if not return_dict:
        return (video,)

    return WanPipelineOutput(frames=video)

mindone.diffusers.WanVideoToVideoPipeline.encode_prompt(prompt, negative_prompt=None, do_classifier_free_guidance=True, num_videos_per_prompt=1, prompt_embeds=None, negative_prompt_embeds=None, max_sequence_length=226, dtype=None)

Encodes the prompt into text encoder hidden states.

PARAMETER	DESCRIPTION
prompt	prompt to be encoded TYPE: `str` or `List[str]`, *optional*
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
do_classifier_free_guidance	Whether to use classifier free guidance or not. TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True
num_videos_per_prompt	Number of videos that should be generated per prompt. TYPE: `int`, *optional*, defaults to 1 DEFAULT: 1
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
dtype	(ms.Type, optional): mindspore dtype TYPE: Optional[Type] DEFAULT: None

Source code in mindone/diffusers/pipelines/wan/pipeline_wan_video2video.py

def encode_prompt(
    self,
    prompt: Union[str, List[str]],
    negative_prompt: Optional[Union[str, List[str]]] = None,
    do_classifier_free_guidance: bool = True,
    num_videos_per_prompt: int = 1,
    prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    max_sequence_length: int = 226,
    dtype: Optional[ms.Type] = None,
):
    r"""
    Encodes the prompt into text encoder hidden states.

    Args:
        prompt (`str` or `List[str]`, *optional*):
            prompt to be encoded
        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`).
        do_classifier_free_guidance (`bool`, *optional*, defaults to `True`):
            Whether to use classifier free guidance or not.
        num_videos_per_prompt (`int`, *optional*, defaults to 1):
            Number of videos that should be generated per prompt.
        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.
        dtype: (`ms.Type`, *optional*):
            mindspore dtype
    """
    prompt = [prompt] if isinstance(prompt, str) else prompt
    if prompt is not None:
        batch_size = len(prompt)
    else:
        batch_size = prompt_embeds.shape[0]

    if prompt_embeds is None:
        prompt_embeds = self._get_t5_prompt_embeds(
            prompt=prompt,
            num_videos_per_prompt=num_videos_per_prompt,
            max_sequence_length=max_sequence_length,
            dtype=dtype,
        )

    if do_classifier_free_guidance and negative_prompt_embeds is None:
        negative_prompt = negative_prompt or ""
        negative_prompt = batch_size * [negative_prompt] if isinstance(negative_prompt, str) else negative_prompt

        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`."
            )

        negative_prompt_embeds = self._get_t5_prompt_embeds(
            prompt=negative_prompt,
            num_videos_per_prompt=num_videos_per_prompt,
            max_sequence_length=max_sequence_length,
            dtype=dtype,
        )

    return prompt_embeds, negative_prompt_embeds

mindone.diffusers.pipelines.wan.pipeline_output.WanPipelineOutput dataclass

Bases: BaseOutput

Output class for Wan pipelines.

PARAMETER	DESCRIPTION
frames	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 MindSpore tensor of shape (batch_size, num_frames, channels, height, width). TYPE: `ms.Tensor`, `np.ndarray`, or List[List[PIL.Image.Image]]

Source code in mindone/diffusers/pipelines/wan/pipeline_output.py

@dataclass
class WanPipelineOutput(BaseOutput):
    r"""
    Output class for Wan pipelines.

    Args:
        frames (`ms.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 MindSpore tensor of
            shape `(batch_size, num_frames, channels, height, width)`.
    """

    frames: ms.Tensor