Skip to content

Wan

LoRA

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

Bases: DiffusionPipeline, WanLoraLoaderMixin

Pipeline for controllable generation using Wan.

This model inherits from [DiffusionPipeline]. Check the superclass documentation for the generic methods implemented for all pipelines (downloading, saving, 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_vace.py
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
class WanVACEPipeline(DiffusionPipeline, WanLoraLoaderMixin):
    r"""
    Pipeline for controllable generation using Wan.

    This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods
    implemented for all pipelines (downloading, saving, 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: WanVACETransformer3DModel,
        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()

        with pynative_context():
            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.dtype`, *optional*):
                ms 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,
        video=None,
        mask=None,
        reference_images=None,
    ):
        base = self.vae_scale_factor_spatial * self.transformer.config.patch_size[1]
        if height % base != 0 or width % base != 0:
            raise ValueError(f"`height` and `width` have to be divisible by {base} 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 "
                f"{self._callback_tensor_inputs}, but found "
                f"{[k for k in callback_on_step_end_tensor_inputs if k not in self._callback_tensor_inputs]}"
            )

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

        if video is not None:
            if mask is not None:
                if len(video) != len(mask):
                    raise ValueError(
                        f"Length of `video` {len(video)} and `mask` {len(mask)} do not match. Please make sure that"
                        " they have the same length."
                    )
            if reference_images is not None:
                is_pil_image = isinstance(reference_images, PIL.Image.Image)
                is_list_of_pil_images = isinstance(reference_images, list) and all(
                    isinstance(ref_img, PIL.Image.Image) for ref_img in reference_images
                )
                is_list_of_list_of_pil_images = isinstance(reference_images, list) and all(
                    isinstance(ref_img, list) and all(isinstance(ref_img_, PIL.Image.Image) for ref_img_ in ref_img)
                    for ref_img in reference_images
                )
                if not (is_pil_image or is_list_of_pil_images or is_list_of_list_of_pil_images):
                    raise ValueError(
                        "`reference_images` has to be of type `PIL.Image.Image` or `list` of `PIL.Image.Image`, or "
                        "`list` of `list` of `PIL.Image.Image`, but is {type(reference_images)}"
                    )
                if is_list_of_list_of_pil_images and len(reference_images) != 1:
                    raise ValueError(
                        "The pipeline only supports generating one video at a time at the moment. When passing a list "
                        "of list of reference images, where the outer list corresponds to the batch size and the inner "
                        "list corresponds to list of conditioning images per video, please make sure to only pass "
                        "one inner list of reference images (i.e., `[[<image1>, <image2>, ...]]`"
                    )
        elif mask is not None:
            raise ValueError("`mask` can only be passed if `video` is passed as well.")

    def preprocess_conditions(
        self,
        video: Optional[List[PipelineImageInput]] = None,
        mask: Optional[List[PipelineImageInput]] = None,
        reference_images: Optional[Union[PIL.Image.Image, List[PIL.Image.Image], List[List[PIL.Image.Image]]]] = None,
        batch_size: int = 1,
        height: int = 480,
        width: int = 832,
        num_frames: int = 81,
        dtype: Optional[ms.Type] = None,
    ):
        if video is not None:
            base = self.vae_scale_factor_spatial * self.transformer.config.patch_size[1]
            video_height, video_width = self.video_processor.get_default_height_width(video[0])

            if video_height * video_width > height * width:
                scale = min(width / video_width, height / video_height)
                video_height, video_width = int(video_height * scale), int(video_width * scale)

            if video_height % base != 0 or video_width % base != 0:
                logger.warning(
                    f"Video height and width should be divisible by {base}, but got {video_height} and {video_width}. "
                )
                video_height = (video_height // base) * base
                video_width = (video_width // base) * base

            assert video_height * video_width <= height * width

            video = self.video_processor.preprocess_video(video, video_height, video_width)
            image_size = (video_height, video_width)  # Use the height/width of video (with possible rescaling)
        else:
            video = mint.zeros((batch_size, 3, num_frames, height, width), dtype=dtype)
            image_size = (height, width)  # Use the height/width provider by user

        if mask is not None:
            mask = self.video_processor.preprocess_video(mask, image_size[0], image_size[1])
            mask = mint.clamp((mask + 1) / 2, min=0, max=1)
        else:
            mask = mint.ones_like(video)

        video = video.to(dtype=dtype)
        mask = mask.to(dtype=dtype)

        # Make a list of list of images where the outer list corresponds to video batch size and the inner list
        # corresponds to list of conditioning images per video
        if reference_images is None or isinstance(reference_images, PIL.Image.Image):
            reference_images = [[reference_images] for _ in range(video.shape[0])]
        elif isinstance(reference_images, (list, tuple)) and isinstance(next(iter(reference_images)), PIL.Image.Image):
            reference_images = [reference_images]
        elif (
            isinstance(reference_images, (list, tuple))
            and isinstance(next(iter(reference_images)), list)
            and isinstance(next(iter(reference_images[0])), PIL.Image.Image)
        ):
            reference_images = reference_images
        else:
            raise ValueError(
                "`reference_images` has to be of type `PIL.Image.Image` or `list` of `PIL.Image.Image`, or "
                "`list` of `list` of `PIL.Image.Image`, but is {type(reference_images)}"
            )

        if video.shape[0] != len(reference_images):
            raise ValueError(
                f"Batch size of `video` {video.shape[0]} and length of `reference_images` {len(reference_images)} "
                f"does not match."
            )

        ref_images_lengths = [len(reference_images_batch) for reference_images_batch in reference_images]
        if any(length != ref_images_lengths[0] for length in ref_images_lengths):
            raise ValueError(
                f"All batches of `reference_images` should have the same length, but got {ref_images_lengths}. Support for this "
                "may be added in the future."
            )

        reference_images_preprocessed = []
        for i, reference_images_batch in enumerate(reference_images):
            preprocessed_images = []
            for j, image in enumerate(reference_images_batch):
                if image is None:
                    continue
                image = self.video_processor.preprocess(image, None, None)
                img_height, img_width = image.shape[-2:]
                scale = min(image_size[0] / img_height, image_size[1] / img_width)
                new_height, new_width = int(img_height * scale), int(img_width * scale)
                resized_image = mint.nn.functional.interpolate(
                    image, size=(new_height, new_width), mode="bilinear", align_corners=False
                ).squeeze(
                    0
                )  # [C, H, W]
                top = (image_size[0] - new_height) // 2
                left = (image_size[1] - new_width) // 2
                canvas = mint.ones((3, *image_size), dtype=dtype)
                canvas[:, top : top + new_height, left : left + new_width] = resized_image
                preprocessed_images.append(canvas)
            reference_images_preprocessed.append(preprocessed_images)

        return video, mask, reference_images_preprocessed

    def prepare_video_latents(
        self,
        video: ms.Tensor,
        mask: ms.Tensor,
        reference_images: Optional[List[List[ms.Tensor]]] = None,
        generator: Optional[Union[ms.Generator, List[ms.Generator]]] = None,
    ) -> ms.Tensor:
        if isinstance(generator, list):
            # TODO: support this
            raise ValueError("Passing a list of generators is not yet supported. This may be supported in the future.")

        if reference_images is None:
            # For each batch of video, we set no re
            # ference image (as one or more can be passed by user)
            reference_images = [[None] for _ in range(video.shape[0])]
        else:
            if video.shape[0] != len(reference_images):
                raise ValueError(
                    f"Batch size of `video` {video.shape[0]} and length of `reference_images` {len(reference_images)} "
                    f"does not match."
                )

        if video.shape[0] != 1:
            # TODO: support this
            raise ValueError(
                "Generating with more than one video is not yet supported. This may be supported in the future."
            )

        vae_dtype = self.vae.dtype
        video = video.to(dtype=vae_dtype)

        latents_mean = ms.tensor(self.vae.config.latents_mean, dtype=ms.float32).view(1, self.vae.config.z_dim, 1, 1, 1)
        latents_std = 1.0 / ms.tensor(self.vae.config.latents_std, dtype=ms.float32).view(
            1, self.vae.config.z_dim, 1, 1, 1
        )

        if mask is None:
            latents = retrieve_latents(self.vae.encode(video), generator, sample_mode="argmax").unbind(0)
            latents = ((latents.float() - latents_mean) * latents_std).to(vae_dtype)
        else:
            mask = mask.to(dtype=vae_dtype)
            mask = mint.where(mask > 0.5, 1.0, 0.0)
            inactive = video * (1 - mask)
            reactive = video * mask
            with pynative_context():
                inactive = retrieve_latents(self.vae, self.vae.encode(inactive)[0], sample_mode="argmax")
                reactive = retrieve_latents(self.vae, self.vae.encode(reactive)[0], sample_mode="argmax")
            inactive = ((inactive.float() - latents_mean) * latents_std).to(vae_dtype)
            reactive = ((reactive.float() - latents_mean) * latents_std).to(vae_dtype)
            latents = mint.cat([inactive, reactive], dim=1)

        latent_list = []
        for latent, reference_images_batch in zip(latents, reference_images):
            for reference_image in reference_images_batch:
                assert reference_image.ndim == 3
                reference_image = reference_image.to(dtype=vae_dtype)
                reference_image = reference_image[None, :, None, :, :]  # [1, C, 1, H, W]
                reference_latent = retrieve_latents(self.vae, self.vae.encode(reference_image)[0], sample_mode="argmax")
                reference_latent = ((reference_latent.float() - latents_mean) * latents_std).to(vae_dtype)
                reference_latent = reference_latent.squeeze(0)  # [C, 1, H, W]
                reference_latent = mint.cat([reference_latent, mint.zeros_like(reference_latent)], dim=0)
                latent = mint.cat([reference_latent.squeeze(0), latent], dim=1)
            latent_list.append(latent)
        return mint.stack(latent_list)

    def prepare_masks(
        self,
        mask: ms.Tensor,
        reference_images: Optional[List[ms.Tensor]] = None,
        generator: Optional[Union[ms.Generator, List[ms.Generator]]] = None,
    ) -> ms.Tensor:
        if isinstance(generator, list):
            # TODO: support this
            raise ValueError("Passing a list of generators is not yet supported. This may be supported in the future.")

        if reference_images is None:
            # For each batch of video, we set no reference image (as one or more can be passed by user)
            reference_images = [[None] for _ in range(mask.shape[0])]
        else:
            if mask.shape[0] != len(reference_images):
                raise ValueError(
                    f"Batch size of `mask` {mask.shape[0]} and length of `reference_images` {len(reference_images)} "
                    f"does not match."
                )

        if mask.shape[0] != 1:
            # TODO: support this
            raise ValueError(
                "Generating with more than one video is not yet supported. This may be supported in the future."
            )

        transformer_patch_size = self.transformer.config.patch_size[1]

        mask_list = []
        for mask_, reference_images_batch in zip(mask, reference_images):
            num_channels, num_frames, height, width = mask_.shape
            new_num_frames = (num_frames + self.vae_scale_factor_temporal - 1) // self.vae_scale_factor_temporal
            new_height = height // (self.vae_scale_factor_spatial * transformer_patch_size) * transformer_patch_size
            new_width = width // (self.vae_scale_factor_spatial * transformer_patch_size) * transformer_patch_size
            mask_ = mask_[0, :, :, :]
            mask_ = mask_.view(
                num_frames, new_height, self.vae_scale_factor_spatial, new_width, self.vae_scale_factor_spatial
            )
            mask_ = mask_.permute(2, 4, 0, 1, 3).flatten(0, 1)  # [8x8, num_frames, new_height, new_width]
            mask_ = mint.nn.functional.interpolate(
                mask_.unsqueeze(0), size=(new_num_frames, new_height, new_width), mode="nearest"
            ).squeeze(0)
            num_ref_images = len(reference_images_batch)
            if num_ref_images > 0:
                mask_padding = mint.zeros_like(mask_[:, :num_ref_images, :, :])
                mask_ = mint.cat([mask_padding, mask_], dim=1)
            mask_list.append(mask_)
        return mint.stack(mask_list)

    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[ms.Generator, List[ms.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,
        video: Optional[List[PipelineImageInput]] = None,
        mask: Optional[List[PipelineImageInput]] = None,
        reference_images: Optional[List[PipelineImageInput]] = None,
        conditioning_scale: Union[float, List[float], ms.Tensor] = 1.0,
        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: 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.
            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`).
            video (`List[PIL.Image.Image]`, *optional*):
                The input video or videos to be used as a starting point for the generation. The video should be a list
                of PIL images, a numpy array, or a mindspore tensor. Currently, the pipeline only supports generating one
                video at a time.
            mask (`List[PIL.Image.Image]`, *optional*):
                The input mask defines which video regions to condition on and which to generate. Black areas in the
                mask indicate conditioning regions, while white areas indicate regions for generation. The mask should
                be a list of PIL images, a numpy array, or a mindspore tensor. Currently supports generating a single video
                at a time.
            reference_images (`List[PIL.Image.Image]`, *optional*):
                A list of one or more reference images as extra conditioning for the generation. For example, if you
                are trying to inpaint a video to change the character, you can pass reference images of the new
                character here. Refer to the Diffusers [examples](https://github.com/huggingface/diffusers/pull/11582)
                and original [user
                guide](https://github.com/ali-vilab/VACE/blob/0897c6d055d7d9ea9e191dce763006664d9780f8/UserGuide.md)
                for a full list of supported tasks and use cases.
            conditioning_scale (`float`, `List[float]`, `ms.Tensor`, defaults to `1.0`):
                The conditioning scale to be applied when adding the control conditioning latent stream to the
                denoising latent stream in each control layer of the model. If a float is provided, it will be applied
                uniformly to all layers. If a list or tensor is provided, it should have the same length as the number
                of control layers in the model (`len(transformer.config.vace_layers)`).
            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://arxiv.org/abs/2207.12598).
                `guidance_scale` is defined as `w` of equation 2. of [Imagen
                Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
                1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
                usually at the expense of lower image quality.
            num_videos_per_prompt (`int`, *optional*, defaults to 1):
                The number of images to generate per prompt.
            generator (`np.random.Generator`):
                A [`np.random.Generator`] 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 `False`, [`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

        # Simplification of implementation for now
        if not isinstance(prompt, str):
            raise ValueError("Passing a list of prompts is not yet supported. This may be supported in the future.")
        if num_videos_per_prompt != 1:
            raise ValueError(
                "Generating multiple videos per prompt is not yet supported. This may be supported in the future."
            )

        # 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,
            video,
            mask,
            reference_images,
        )

        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}. "
                f"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]

        vae_dtype = self.vae.dtype
        transformer_dtype = self.transformer.dtype

        if isinstance(conditioning_scale, (int, float)):
            conditioning_scale = [conditioning_scale] * len(self.transformer.config.vace_layers)
        if isinstance(conditioning_scale, list):
            if len(conditioning_scale) != len(self.transformer.config.vace_layers):
                raise ValueError(
                    f"Length of `conditioning_scale` {len(conditioning_scale)} does not match number of layers "
                    f"{len(self.transformer.config.vace_layers)}."
                )
            conditioning_scale = ms.tensor(conditioning_scale)
        if isinstance(conditioning_scale, ms.Tensor):
            if conditioning_scale.shape[0] != len(self.transformer.config.vace_layers):
                raise ValueError(
                    f"Length of `conditioning_scale` {conditioning_scale.shape[0]} does not match number of layers "
                    f"{len(self.transformer.config.vace_layers)}."
                )
            conditioning_scale = conditioning_scale.to(dtype=transformer_dtype)

        # 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,
        )

        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
        video, mask, reference_images = self.preprocess_conditions(
            video,
            mask,
            reference_images,
            batch_size,
            height,
            width,
            num_frames,
            ms.float32,
        )
        num_reference_images = len(reference_images[0])

        conditioning_latents = self.prepare_video_latents(video, mask, reference_images, generator)
        mask = self.prepare_masks(mask, reference_images, generator).to(conditioning_latents.dtype)
        conditioning_latents = mint.cat([conditioning_latents, mask], dim=1)
        conditioning_latents = conditioning_latents.to(transformer_dtype)

        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 + num_reference_images * self.vae_scale_factor_temporal,
            ms.float32,
            generator,
            latents,
        )

        if conditioning_latents.shape[2] != latents.shape[2]:
            logger.warning(
                "The number of frames in the conditioning latents does not match the number of frames to be generated. "
                "Generation quality may be affected."
            )

        # 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.expand([latents.shape[0]])

                noise_pred = self.transformer(
                    hidden_states=latent_model_input,
                    timestep=timestep,
                    encoder_hidden_states=prompt_embeds,
                    control_hidden_states=conditioning_latents,
                    control_hidden_states_scale=conditioning_scale,
                    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,
                        control_hidden_states=conditioning_latents,
                        control_hidden_states_scale=conditioning_scale,
                        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[:, :, num_reference_images:]
            latents = latents.to(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, dtype=ms.float32).view(
                1, self.vae.config.z_dim, 1, 1, 1
            )
            latents = latents / latents_std + latents_mean
            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.WanVACEPipeline.__call__(prompt=None, negative_prompt=None, video=None, mask=None, reference_images=None, conditioning_scale=1.0, 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, 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

video

The input video or videos to be used as a starting point for the generation. The video should be a list of PIL images, a numpy array, or a mindspore tensor. Currently, the pipeline only supports generating one video at a time.

TYPE: `List[PIL.Image.Image]`, *optional* DEFAULT: None

mask

The input mask defines which video regions to condition on and which to generate. Black areas in the mask indicate conditioning regions, while white areas indicate regions for generation. The mask should be a list of PIL images, a numpy array, or a mindspore tensor. Currently supports generating a single video at a time.

TYPE: `List[PIL.Image.Image]`, *optional* DEFAULT: None

reference_images

A list of one or more reference images as extra conditioning for the generation. For example, if you are trying to inpaint a video to change the character, you can pass reference images of the new character here. Refer to the Diffusers examples and original user guide for a full list of supported tasks and use cases.

TYPE: `List[PIL.Image.Image]`, *optional* DEFAULT: None

conditioning_scale

The conditioning scale to be applied when adding the control conditioning latent stream to the denoising latent stream in each control layer of the model. If a float is provided, it will be applied uniformly to all layers. If a list or tensor is provided, it should have the same length as the number of control layers in the model (len(transformer.config.vace_layers)).

TYPE: `float`, `List[float]`, `ms.Tensor`, defaults to `1.0` DEFAULT: 1.0

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` 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 False, [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_vace.py
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
def __call__(
    self,
    prompt: Union[str, List[str]] = None,
    negative_prompt: Union[str, List[str]] = None,
    video: Optional[List[PipelineImageInput]] = None,
    mask: Optional[List[PipelineImageInput]] = None,
    reference_images: Optional[List[PipelineImageInput]] = None,
    conditioning_scale: Union[float, List[float], ms.Tensor] = 1.0,
    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: 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.
        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`).
        video (`List[PIL.Image.Image]`, *optional*):
            The input video or videos to be used as a starting point for the generation. The video should be a list
            of PIL images, a numpy array, or a mindspore tensor. Currently, the pipeline only supports generating one
            video at a time.
        mask (`List[PIL.Image.Image]`, *optional*):
            The input mask defines which video regions to condition on and which to generate. Black areas in the
            mask indicate conditioning regions, while white areas indicate regions for generation. The mask should
            be a list of PIL images, a numpy array, or a mindspore tensor. Currently supports generating a single video
            at a time.
        reference_images (`List[PIL.Image.Image]`, *optional*):
            A list of one or more reference images as extra conditioning for the generation. For example, if you
            are trying to inpaint a video to change the character, you can pass reference images of the new
            character here. Refer to the Diffusers [examples](https://github.com/huggingface/diffusers/pull/11582)
            and original [user
            guide](https://github.com/ali-vilab/VACE/blob/0897c6d055d7d9ea9e191dce763006664d9780f8/UserGuide.md)
            for a full list of supported tasks and use cases.
        conditioning_scale (`float`, `List[float]`, `ms.Tensor`, defaults to `1.0`):
            The conditioning scale to be applied when adding the control conditioning latent stream to the
            denoising latent stream in each control layer of the model. If a float is provided, it will be applied
            uniformly to all layers. If a list or tensor is provided, it should have the same length as the number
            of control layers in the model (`len(transformer.config.vace_layers)`).
        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://arxiv.org/abs/2207.12598).
            `guidance_scale` is defined as `w` of equation 2. of [Imagen
            Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
            1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
            usually at the expense of lower image quality.
        num_videos_per_prompt (`int`, *optional*, defaults to 1):
            The number of images to generate per prompt.
        generator (`np.random.Generator`):
            A [`np.random.Generator`] 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 `False`, [`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

    # Simplification of implementation for now
    if not isinstance(prompt, str):
        raise ValueError("Passing a list of prompts is not yet supported. This may be supported in the future.")
    if num_videos_per_prompt != 1:
        raise ValueError(
            "Generating multiple videos per prompt is not yet supported. This may be supported in the future."
        )

    # 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,
        video,
        mask,
        reference_images,
    )

    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}. "
            f"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]

    vae_dtype = self.vae.dtype
    transformer_dtype = self.transformer.dtype

    if isinstance(conditioning_scale, (int, float)):
        conditioning_scale = [conditioning_scale] * len(self.transformer.config.vace_layers)
    if isinstance(conditioning_scale, list):
        if len(conditioning_scale) != len(self.transformer.config.vace_layers):
            raise ValueError(
                f"Length of `conditioning_scale` {len(conditioning_scale)} does not match number of layers "
                f"{len(self.transformer.config.vace_layers)}."
            )
        conditioning_scale = ms.tensor(conditioning_scale)
    if isinstance(conditioning_scale, ms.Tensor):
        if conditioning_scale.shape[0] != len(self.transformer.config.vace_layers):
            raise ValueError(
                f"Length of `conditioning_scale` {conditioning_scale.shape[0]} does not match number of layers "
                f"{len(self.transformer.config.vace_layers)}."
            )
        conditioning_scale = conditioning_scale.to(dtype=transformer_dtype)

    # 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,
    )

    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
    video, mask, reference_images = self.preprocess_conditions(
        video,
        mask,
        reference_images,
        batch_size,
        height,
        width,
        num_frames,
        ms.float32,
    )
    num_reference_images = len(reference_images[0])

    conditioning_latents = self.prepare_video_latents(video, mask, reference_images, generator)
    mask = self.prepare_masks(mask, reference_images, generator).to(conditioning_latents.dtype)
    conditioning_latents = mint.cat([conditioning_latents, mask], dim=1)
    conditioning_latents = conditioning_latents.to(transformer_dtype)

    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 + num_reference_images * self.vae_scale_factor_temporal,
        ms.float32,
        generator,
        latents,
    )

    if conditioning_latents.shape[2] != latents.shape[2]:
        logger.warning(
            "The number of frames in the conditioning latents does not match the number of frames to be generated. "
            "Generation quality may be affected."
        )

    # 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.expand([latents.shape[0]])

            noise_pred = self.transformer(
                hidden_states=latent_model_input,
                timestep=timestep,
                encoder_hidden_states=prompt_embeds,
                control_hidden_states=conditioning_latents,
                control_hidden_states_scale=conditioning_scale,
                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,
                    control_hidden_states=conditioning_latents,
                    control_hidden_states_scale=conditioning_scale,
                    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[:, :, num_reference_images:]
        latents = latents.to(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, dtype=ms.float32).view(
            1, self.vae.config.z_dim, 1, 1, 1
        )
        latents = latents / latents_std + latents_mean
        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.WanVACEPipeline.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.dtype, optional): ms dtype

TYPE: Optional[Type] DEFAULT: None

Source code in mindone/diffusers/pipelines/wan/pipeline_wan_vace.py
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
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.dtype`, *optional*):
            ms 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
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
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
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
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
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
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
10
11
12
13
14
15
16
17
18
19
20
21
22
@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