Skip to content

Mochi 1 Preview

Mochi 1 Preview from Genmo.

Mochi 1 preview is an open state-of-the-art video generation model with high-fidelity motion and strong prompt adherence in preliminary evaluation. This model dramatically closes the gap between closed and open video generation systems. The model is released under a permissive Apache 2.0 license.

Tip

Make sure to check out the Schedulers guide to learn how to explore the tradeoff between scheduler speed and quality, and see the reuse components across pipelines section to learn how to efficiently load the same components into multiple pipelines.

Generating videos with Mochi-1 Preview

The following example will download the full precision mochi-1-preview weights and produce the highest quality results but will require at least 42GB VRAM to run.

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

pipe = MochiPipeline.from_pretrained("genmo/mochi-1-preview", mindspore_dtype=ms.float16)

# Enable memory savings
pipe.enable_vae_tiling()

prompt = "Close-up of a chameleon's eye, with its scaly skin changing color. Ultra high resolution 4k."

frames = pipe(prompt, num_inference_steps=28, guidance_scale=3.5)[0][0]

export_to_video(frames, "mochi.mp4", fps=30)

mindone.diffusers.MochiPipeline

Bases: DiffusionPipeline, Mochi1LoraLoaderMixin

The mochi pipeline for text-to-video generation.

Reference: https://github.com/genmoai/models

PARAMETER DESCRIPTION
transformer

Conditional Transformer architecture to denoise the encoded video latents.

TYPE: [`MochiTransformer3DModel`]

scheduler

A scheduler to be used in combination with transformer to denoise the encoded image latents.

TYPE: [`FlowMatchEulerDiscreteScheduler`]

vae

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

TYPE: [`AutoencoderKL`]

text_encoder

T5, specifically the google/t5-v1_1-xxl variant.

TYPE: [`T5EncoderModel`]

tokenizer

Tokenizer of class CLIPTokenizer.

TYPE: `CLIPTokenizer`

tokenizer

Second Tokenizer of class T5TokenizerFast.

TYPE: `T5TokenizerFast`

Source code in mindone/diffusers/pipelines/mochi/pipeline_mochi.py
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
class MochiPipeline(DiffusionPipeline, Mochi1LoraLoaderMixin):
    r"""
    The mochi pipeline for text-to-video generation.

    Reference: https://github.com/genmoai/models

    Args:
        transformer ([`MochiTransformer3DModel`]):
            Conditional Transformer architecture to denoise the encoded video latents.
        scheduler ([`FlowMatchEulerDiscreteScheduler`]):
            A scheduler to be used in combination with `transformer` to denoise the encoded image latents.
        vae ([`AutoencoderKL`]):
            Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
        text_encoder ([`T5EncoderModel`]):
            [T5](https://huggingface.co/docs/transformers/en/model_doc/t5#transformers.T5EncoderModel), specifically
            the [google/t5-v1_1-xxl](https://huggingface.co/google/t5-v1_1-xxl) variant.
        tokenizer (`CLIPTokenizer`):
            Tokenizer of class
            [CLIPTokenizer](https://huggingface.co/docs/transformers/en/model_doc/clip#transformers.CLIPTokenizer).
        tokenizer (`T5TokenizerFast`):
            Second Tokenizer of class
            [T5TokenizerFast](https://huggingface.co/docs/transformers/en/model_doc/t5#transformers.T5TokenizerFast).
    """

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

    def __init__(
        self,
        scheduler: FlowMatchEulerDiscreteScheduler,
        vae: AutoencoderKL,
        text_encoder: T5EncoderModel,
        tokenizer: T5TokenizerFast,
        transformer: MochiTransformer3DModel,
        force_zeros_for_empty_prompt: bool = False,
    ):
        super().__init__()

        self.register_modules(
            vae=vae,
            text_encoder=text_encoder,
            tokenizer=tokenizer,
            transformer=transformer,
            scheduler=scheduler,
        )
        # TODO: determine these scaling factors from model parameters
        self.vae_spatial_scale_factor = 8
        self.vae_temporal_scale_factor = 6
        self.patch_size = 2

        self.video_processor = VideoProcessor(vae_scale_factor=self.vae_spatial_scale_factor)
        self.tokenizer_max_length = (
            self.tokenizer.model_max_length if hasattr(self, "tokenizer") and self.tokenizer is not None else 256
        )
        self.default_height = 480
        self.default_width = 848
        self.register_to_config(force_zeros_for_empty_prompt=force_zeros_for_empty_prompt)

    def _get_t5_prompt_embeds(
        self,
        prompt: Union[str, List[str]] = None,
        num_videos_per_prompt: int = 1,
        max_sequence_length: int = 256,
        dtype: Optional[ms.Type] = None,
    ):
        dtype = dtype or self.text_encoder.dtype

        prompt = [prompt] if isinstance(prompt, str) else 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_tensors="np",
        )

        text_input_ids = ms.Tensor(text_inputs.input_ids)
        prompt_attention_mask = ms.Tensor(text_inputs.attention_mask, dtype=ms.bool_)

        # The original Mochi implementation zeros out empty negative prompts
        # but this can lead to overflow when placing the entire pipeline under the autocast context
        # adding this here so that we can enable zeroing prompts if necessary
        if self.config.force_zeros_for_empty_prompt and (prompt == "" or prompt[-1] == ""):
            text_input_ids = ops.zeros_like(text_input_ids)
            prompt_attention_mask = ops.zeros_like(prompt_attention_mask, dtype=ms.bool_)

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

        if untruncated_ids.shape[-1] >= text_input_ids.numpy().shape[-1] and not np.array_equal(
            text_input_ids.asnumpy(), untruncated_ids
        ):
            removed_text = self.tokenizer.batch_decode(untruncated_ids[:, max_sequence_length - 1 : -1])
            logger.warning(
                "The following part of your input was truncated because `max_sequence_length` is set to "
                f" {max_sequence_length} tokens: {removed_text}"
            )

        prompt_embeds = self.text_encoder(text_input_ids, attention_mask=prompt_attention_mask)[0]
        prompt_embeds = prompt_embeds.to(dtype=dtype)

        # 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)

        prompt_attention_mask = prompt_attention_mask.view(batch_size, -1)
        prompt_attention_mask = prompt_attention_mask.tile((num_videos_per_prompt, 1))

        return prompt_embeds, prompt_attention_mask

    # Adapted from diffusers.pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipeline.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,
        prompt_attention_mask: Optional[ms.Tensor] = None,
        negative_prompt_attention_mask: Optional[ms.Tensor] = None,
        max_sequence_length: int = 256,
        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. ms device to place the resulting embeddings on
            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, prompt_attention_mask = 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, negative_prompt_attention_mask = 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, prompt_attention_mask, negative_prompt_embeds, negative_prompt_attention_mask

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

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

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

        if prompt_embeds is not None and prompt_attention_mask is None:
            raise ValueError("Must provide `prompt_attention_mask` when specifying `prompt_embeds`.")

        if negative_prompt_embeds is not None and negative_prompt_attention_mask is None:
            raise ValueError("Must provide `negative_prompt_attention_mask` when specifying `negative_prompt_embeds`.")

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

    def enable_vae_slicing(self):
        r"""
        Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to
        compute decoding in several steps. This is useful to save some memory and allow larger batch sizes.
        """
        self.vae.enable_slicing()

    def disable_vae_slicing(self):
        r"""
        Disable sliced VAE decoding. If `enable_vae_slicing` was previously enabled, this method will go back to
        computing decoding in one step.
        """
        self.vae.disable_slicing()

    def enable_vae_tiling(self):
        r"""
        Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to
        compute decoding and encoding in several steps. This is useful for saving a large amount of memory and to allow
        processing larger images.
        """
        self.vae.enable_tiling()

    def disable_vae_tiling(self):
        r"""
        Disable tiled VAE decoding. If `enable_vae_tiling` was previously enabled, this method will go back to
        computing decoding in one step.
        """
        self.vae.disable_tiling()

    def prepare_latents(
        self,
        batch_size,
        num_channels_latents,
        height,
        width,
        num_frames,
        dtype,
        device,
        generator,
        latents=None,
    ):
        height = height // self.vae_spatial_scale_factor
        width = width // self.vae_spatial_scale_factor
        num_frames = (num_frames - 1) // self.vae_temporal_scale_factor + 1

        shape = (batch_size, num_channels_latents, num_frames, height, width)

        if latents is not None:
            return latents.to(device=device, dtype=dtype)
        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=ms.float32)
        latents = latents.to(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 attention_kwargs(self):
        return self._attention_kwargs

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

    def __call__(
        self,
        prompt: Union[str, List[str]] = None,
        negative_prompt: Optional[Union[str, List[str]]] = None,
        height: Optional[int] = None,
        width: Optional[int] = None,
        num_frames: int = 19,
        num_inference_steps: int = 64,
        timesteps: List[int] = None,
        guidance_scale: float = 4.5,
        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,
        prompt_attention_mask: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_attention_mask: Optional[ms.Tensor] = None,
        output_type: Optional[str] = "pil",
        return_dict: bool = False,
        attention_kwargs: Optional[Dict[str, Any]] = None,
        callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
        max_sequence_length: int = 256,
    ):
        r"""
        Function invoked when calling 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`, *optional*, defaults to `self.default_height`):
                The height in pixels of the generated image. This is set to 480 by default for the best results.
            width (`int`, *optional*, defaults to `self.default_width`):
                The width in pixels of the generated image. This is set to 848 by default for the best results.
            num_frames (`int`, defaults to `19`):
                The number of video frames to generate
            num_inference_steps (`int`, *optional*, defaults to 50):
                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                expense of slower inference.
            timesteps (`List[int]`, *optional*):
                Custom timesteps to use for the denoising process with schedulers which support a `timesteps` argument
                in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
                passed will be used. Must be in descending order.
            guidance_scale (`float`, defaults to `4.5`):
                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 videos to generate per prompt.
            generator (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
                One or a list of [numpy generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
                to make generation deterministic.
            latents (`ms.Tensor`, *optional*):
                Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                tensor will ge generated by sampling using the supplied random `generator`.
            prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                provided, text embeddings will be generated from `prompt` input argument.
            prompt_attention_mask (`ms.Tensor`, *optional*):
                Pre-generated attention mask for text embeddings.
            negative_prompt_embeds (`ms.FloatTensor`, *optional*):
                Pre-generated negative text embeddings. For PixArt-Sigma this negative prompt should be "". If not
                provided, negative_prompt_embeds will be generated from `negative_prompt` input argument.
            negative_prompt_attention_mask (`ms.FloatTensor`, *optional*):
                Pre-generated attention mask for negative text embeddings.
            output_type (`str`, *optional*, defaults to `"pil"`):
                The output format of the generate image. Choose between
                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
            return_dict (`bool`, *optional*, defaults to `False`):
                Whether or not to return a [`~pipelines.mochi.MochiPipelineOutput`] 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`, *optional*):
                A function that calls at the end of each denoising steps during the inference. The function is called
                with the following arguments: `callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int,
                callback_kwargs: Dict)`. `callback_kwargs` will include a list of all tensors as specified by
                `callback_on_step_end_tensor_inputs`.
            callback_on_step_end_tensor_inputs (`List`, *optional*):
                The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
                will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
                `._callback_tensor_inputs` attribute of your pipeline class.
            max_sequence_length (`int` defaults to `256`):
                Maximum sequence length to use with the `prompt`.

        Examples:

        Returns:
            [`~pipelines.mochi.MochiPipelineOutput`] or `tuple`:
                If `return_dict` is `True`, [`~pipelines.mochi.MochiPipelineOutput`] is returned, otherwise a `tuple`
                is returned where the first element is a list with the generated images.
        """

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

        height = height or self.default_height
        width = width or self.default_width

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

        self._guidance_scale = guidance_scale
        self._attention_kwargs = attention_kwargs
        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. Prepare text embeddings
        (
            prompt_embeds,
            prompt_attention_mask,
            negative_prompt_embeds,
            negative_prompt_attention_mask,
        ) = 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,
            prompt_attention_mask=prompt_attention_mask,
            negative_prompt_attention_mask=negative_prompt_attention_mask,
            max_sequence_length=max_sequence_length,
        )
        # 4. 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,
            prompt_embeds.dtype,
            generator,
            latents,
        )

        if self.do_classifier_free_guidance:
            prompt_embeds = ops.cat([negative_prompt_embeds, prompt_embeds], axis=0)
            prompt_attention_mask = ops.cat([negative_prompt_attention_mask, prompt_attention_mask], axis=0)

        # 5. Prepare timestep
        # from https://github.com/genmoai/models/blob/075b6e36db58f1242921deff83a1066887b9c9e1/src/mochi_preview/infer.py#L77
        threshold_noise = 0.025
        sigmas = linear_quadratic_schedule(num_inference_steps, threshold_noise)
        sigmas = np.array(sigmas)

        timesteps, num_inference_steps = retrieve_timesteps(
            self.scheduler,
            num_inference_steps,
            timesteps,
            sigmas,
        )
        num_warmup_steps = max(len(timesteps) - num_inference_steps * self.scheduler.order, 0)
        self._num_timesteps = len(timesteps)

        # we're popping the `scale` instead of getting it because otherwise `scale` will be propagated
        # to the transformer and will raise RuntimeError.
        lora_scale = self.attention_kwargs.pop("scale", None) if self.attention_kwargs is not None else None
        if lora_scale is not None:
            # weight the lora layers by setting `lora_scale` for each PEFT layer
            scale_lora_layers(self.transformer, lora_scale)

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

                latent_model_input = ops.cat([latents] * 2) if self.do_classifier_free_guidance else latents
                # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
                timestep = t.broadcast_to((latent_model_input.shape[0],)).to(latents.dtype)

                noise_pred = self.transformer(
                    hidden_states=latent_model_input,
                    encoder_hidden_states=prompt_embeds,
                    timestep=timestep,
                    encoder_attention_mask=prompt_attention_mask,
                    attention_kwargs=attention_kwargs,
                    return_dict=False,
                )[0]
                # Mochi CFG + Sampling runs in FP32
                noise_pred = noise_pred.to(dtype=ms.float32)

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

                # compute the previous noisy sample x_t -> x_t-1
                latents_dtype = latents.dtype
                latents = self.scheduler.step(noise_pred, t, latents.to(ms.float32), return_dict=False)[0]
                latents = latents.to(latents_dtype)

                if latents.dtype != latents_dtype:
                    latents = latents.to(latents_dtype)

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

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

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

        if lora_scale is not None:
            # remove `lora_scale` from each PEFT layer
            unscale_lora_layers(self.transformer, lora_scale)

        if output_type == "latent":
            video = latents
        else:
            # unscale/denormalize the latents
            # denormalize with the mean and std if available and not None
            has_latents_mean = hasattr(self.vae.config, "latents_mean") and self.vae.config.latents_mean is not None
            has_latents_std = hasattr(self.vae.config, "latents_std") and self.vae.config.latents_std is not None
            if has_latents_mean and has_latents_std:
                latents_mean = ms.tensor(self.vae.config.latents_mean).view(1, 12, 1, 1, 1).to(latents.dtype)
                latents_std = ms.tensor(self.vae.config.latents_std).view(1, 12, 1, 1, 1).to(latents.dtype)
                latents = latents * latents_std / self.vae.config.scaling_factor + latents_mean
            else:
                latents = latents / self.vae.config.scaling_factor

            video = self.vae.decode(latents, return_dict=False)[0]
            video = self.video_processor.postprocess_video(video, output_type=output_type)

        if not return_dict:
            return (video,)

        return MochiPipelineOutput(frames=video)

mindone.diffusers.MochiPipeline.__call__(prompt=None, negative_prompt=None, height=None, width=None, num_frames=19, num_inference_steps=64, timesteps=None, guidance_scale=4.5, num_videos_per_prompt=1, generator=None, latents=None, prompt_embeds=None, prompt_attention_mask=None, negative_prompt_embeds=None, negative_prompt_attention_mask=None, output_type='pil', return_dict=False, attention_kwargs=None, callback_on_step_end=None, callback_on_step_end_tensor_inputs=['latents'], max_sequence_length=256)

Function invoked when calling 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. This is set to 480 by default for the best results.

TYPE: `int`, *optional*, defaults to `self.default_height` DEFAULT: None

width

The width in pixels of the generated image. This is set to 848 by default for the best results.

TYPE: `int`, *optional*, defaults to `self.default_width` DEFAULT: None

num_frames

The number of video frames to generate

TYPE: `int`, defaults to `19` DEFAULT: 19

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`, *optional*, defaults to 50 DEFAULT: 64

timesteps

Custom timesteps to use for the denoising process with schedulers which support a timesteps argument in their set_timesteps method. If not defined, the default behavior when num_inference_steps is passed will be used. Must be in descending order.

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

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 `4.5` DEFAULT: 4.5

num_videos_per_prompt

The number of videos to generate per prompt.

TYPE: `int`, *optional*, defaults to 1 DEFAULT: 1

generator

One or a list of numpy generator(s) to make generation deterministic.

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

latents

Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor will ge generated by sampling using the supplied random generator.

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

prompt_embeds

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

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

prompt_attention_mask

Pre-generated attention mask for text embeddings.

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

negative_prompt_embeds

Pre-generated negative text embeddings. For PixArt-Sigma this negative prompt should be "". If not provided, negative_prompt_embeds will be generated from negative_prompt input argument.

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

negative_prompt_attention_mask

Pre-generated attention mask for negative text embeddings.

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

output_type

The output format of the generate image. Choose between PIL: PIL.Image.Image or np.array.

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

return_dict

Whether or not to return a [~pipelines.mochi.MochiPipelineOutput] 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 that calls at the end of each denoising steps during the inference. The function is called with the following arguments: callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict). callback_kwargs will include a list of all tensors as specified by callback_on_step_end_tensor_inputs.

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

callback_on_step_end_tensor_inputs

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

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

max_sequence_length

Maximum sequence length to use with the prompt.

TYPE: `int` defaults to `256` DEFAULT: 256

RETURNS DESCRIPTION

[~pipelines.mochi.MochiPipelineOutput] or tuple: If return_dict is True, [~pipelines.mochi.MochiPipelineOutput] is returned, otherwise a tuple is returned where the first element is a list with the generated images.

Source code in mindone/diffusers/pipelines/mochi/pipeline_mochi.py
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
def __call__(
    self,
    prompt: Union[str, List[str]] = None,
    negative_prompt: Optional[Union[str, List[str]]] = None,
    height: Optional[int] = None,
    width: Optional[int] = None,
    num_frames: int = 19,
    num_inference_steps: int = 64,
    timesteps: List[int] = None,
    guidance_scale: float = 4.5,
    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,
    prompt_attention_mask: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_attention_mask: Optional[ms.Tensor] = None,
    output_type: Optional[str] = "pil",
    return_dict: bool = False,
    attention_kwargs: Optional[Dict[str, Any]] = None,
    callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
    callback_on_step_end_tensor_inputs: List[str] = ["latents"],
    max_sequence_length: int = 256,
):
    r"""
    Function invoked when calling 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`, *optional*, defaults to `self.default_height`):
            The height in pixels of the generated image. This is set to 480 by default for the best results.
        width (`int`, *optional*, defaults to `self.default_width`):
            The width in pixels of the generated image. This is set to 848 by default for the best results.
        num_frames (`int`, defaults to `19`):
            The number of video frames to generate
        num_inference_steps (`int`, *optional*, defaults to 50):
            The number of denoising steps. More denoising steps usually lead to a higher quality image at the
            expense of slower inference.
        timesteps (`List[int]`, *optional*):
            Custom timesteps to use for the denoising process with schedulers which support a `timesteps` argument
            in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
            passed will be used. Must be in descending order.
        guidance_scale (`float`, defaults to `4.5`):
            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 videos to generate per prompt.
        generator (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
            One or a list of [numpy generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
            to make generation deterministic.
        latents (`ms.Tensor`, *optional*):
            Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
            generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
            tensor will ge generated by sampling using the supplied random `generator`.
        prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
            provided, text embeddings will be generated from `prompt` input argument.
        prompt_attention_mask (`ms.Tensor`, *optional*):
            Pre-generated attention mask for text embeddings.
        negative_prompt_embeds (`ms.FloatTensor`, *optional*):
            Pre-generated negative text embeddings. For PixArt-Sigma this negative prompt should be "". If not
            provided, negative_prompt_embeds will be generated from `negative_prompt` input argument.
        negative_prompt_attention_mask (`ms.FloatTensor`, *optional*):
            Pre-generated attention mask for negative text embeddings.
        output_type (`str`, *optional*, defaults to `"pil"`):
            The output format of the generate image. Choose between
            [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
        return_dict (`bool`, *optional*, defaults to `False`):
            Whether or not to return a [`~pipelines.mochi.MochiPipelineOutput`] 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`, *optional*):
            A function that calls at the end of each denoising steps during the inference. The function is called
            with the following arguments: `callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int,
            callback_kwargs: Dict)`. `callback_kwargs` will include a list of all tensors as specified by
            `callback_on_step_end_tensor_inputs`.
        callback_on_step_end_tensor_inputs (`List`, *optional*):
            The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
            will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
            `._callback_tensor_inputs` attribute of your pipeline class.
        max_sequence_length (`int` defaults to `256`):
            Maximum sequence length to use with the `prompt`.

    Examples:

    Returns:
        [`~pipelines.mochi.MochiPipelineOutput`] or `tuple`:
            If `return_dict` is `True`, [`~pipelines.mochi.MochiPipelineOutput`] is returned, otherwise a `tuple`
            is returned where the first element is a list with the generated images.
    """

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

    height = height or self.default_height
    width = width or self.default_width

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

    self._guidance_scale = guidance_scale
    self._attention_kwargs = attention_kwargs
    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. Prepare text embeddings
    (
        prompt_embeds,
        prompt_attention_mask,
        negative_prompt_embeds,
        negative_prompt_attention_mask,
    ) = 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,
        prompt_attention_mask=prompt_attention_mask,
        negative_prompt_attention_mask=negative_prompt_attention_mask,
        max_sequence_length=max_sequence_length,
    )
    # 4. 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,
        prompt_embeds.dtype,
        generator,
        latents,
    )

    if self.do_classifier_free_guidance:
        prompt_embeds = ops.cat([negative_prompt_embeds, prompt_embeds], axis=0)
        prompt_attention_mask = ops.cat([negative_prompt_attention_mask, prompt_attention_mask], axis=0)

    # 5. Prepare timestep
    # from https://github.com/genmoai/models/blob/075b6e36db58f1242921deff83a1066887b9c9e1/src/mochi_preview/infer.py#L77
    threshold_noise = 0.025
    sigmas = linear_quadratic_schedule(num_inference_steps, threshold_noise)
    sigmas = np.array(sigmas)

    timesteps, num_inference_steps = retrieve_timesteps(
        self.scheduler,
        num_inference_steps,
        timesteps,
        sigmas,
    )
    num_warmup_steps = max(len(timesteps) - num_inference_steps * self.scheduler.order, 0)
    self._num_timesteps = len(timesteps)

    # we're popping the `scale` instead of getting it because otherwise `scale` will be propagated
    # to the transformer and will raise RuntimeError.
    lora_scale = self.attention_kwargs.pop("scale", None) if self.attention_kwargs is not None else None
    if lora_scale is not None:
        # weight the lora layers by setting `lora_scale` for each PEFT layer
        scale_lora_layers(self.transformer, lora_scale)

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

            latent_model_input = ops.cat([latents] * 2) if self.do_classifier_free_guidance else latents
            # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
            timestep = t.broadcast_to((latent_model_input.shape[0],)).to(latents.dtype)

            noise_pred = self.transformer(
                hidden_states=latent_model_input,
                encoder_hidden_states=prompt_embeds,
                timestep=timestep,
                encoder_attention_mask=prompt_attention_mask,
                attention_kwargs=attention_kwargs,
                return_dict=False,
            )[0]
            # Mochi CFG + Sampling runs in FP32
            noise_pred = noise_pred.to(dtype=ms.float32)

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

            # compute the previous noisy sample x_t -> x_t-1
            latents_dtype = latents.dtype
            latents = self.scheduler.step(noise_pred, t, latents.to(ms.float32), return_dict=False)[0]
            latents = latents.to(latents_dtype)

            if latents.dtype != latents_dtype:
                latents = latents.to(latents_dtype)

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

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

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

    if lora_scale is not None:
        # remove `lora_scale` from each PEFT layer
        unscale_lora_layers(self.transformer, lora_scale)

    if output_type == "latent":
        video = latents
    else:
        # unscale/denormalize the latents
        # denormalize with the mean and std if available and not None
        has_latents_mean = hasattr(self.vae.config, "latents_mean") and self.vae.config.latents_mean is not None
        has_latents_std = hasattr(self.vae.config, "latents_std") and self.vae.config.latents_std is not None
        if has_latents_mean and has_latents_std:
            latents_mean = ms.tensor(self.vae.config.latents_mean).view(1, 12, 1, 1, 1).to(latents.dtype)
            latents_std = ms.tensor(self.vae.config.latents_std).view(1, 12, 1, 1, 1).to(latents.dtype)
            latents = latents * latents_std / self.vae.config.scaling_factor + latents_mean
        else:
            latents = latents / self.vae.config.scaling_factor

        video = self.vae.decode(latents, return_dict=False)[0]
        video = self.video_processor.postprocess_video(video, output_type=output_type)

    if not return_dict:
        return (video,)

    return MochiPipelineOutput(frames=video)

mindone.diffusers.MochiPipeline.disable_vae_slicing()

Disable sliced VAE decoding. If enable_vae_slicing was previously enabled, this method will go back to computing decoding in one step.

Source code in mindone/diffusers/pipelines/mochi/pipeline_mochi.py
394
395
396
397
398
399
def disable_vae_slicing(self):
    r"""
    Disable sliced VAE decoding. If `enable_vae_slicing` was previously enabled, this method will go back to
    computing decoding in one step.
    """
    self.vae.disable_slicing()

mindone.diffusers.MochiPipeline.disable_vae_tiling()

Disable tiled VAE decoding. If enable_vae_tiling was previously enabled, this method will go back to computing decoding in one step.

Source code in mindone/diffusers/pipelines/mochi/pipeline_mochi.py
409
410
411
412
413
414
def disable_vae_tiling(self):
    r"""
    Disable tiled VAE decoding. If `enable_vae_tiling` was previously enabled, this method will go back to
    computing decoding in one step.
    """
    self.vae.disable_tiling()

mindone.diffusers.MochiPipeline.enable_vae_slicing()

Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to compute decoding in several steps. This is useful to save some memory and allow larger batch sizes.

Source code in mindone/diffusers/pipelines/mochi/pipeline_mochi.py
387
388
389
390
391
392
def enable_vae_slicing(self):
    r"""
    Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to
    compute decoding in several steps. This is useful to save some memory and allow larger batch sizes.
    """
    self.vae.enable_slicing()

mindone.diffusers.MochiPipeline.enable_vae_tiling()

Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and encoding in several steps. This is useful for saving a large amount of memory and to allow processing larger images.

Source code in mindone/diffusers/pipelines/mochi/pipeline_mochi.py
401
402
403
404
405
406
407
def enable_vae_tiling(self):
    r"""
    Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to
    compute decoding and encoding in several steps. This is useful for saving a large amount of memory and to allow
    processing larger images.
    """
    self.vae.enable_tiling()

mindone.diffusers.MochiPipeline.encode_prompt(prompt, negative_prompt=None, do_classifier_free_guidance=True, num_videos_per_prompt=1, prompt_embeds=None, negative_prompt_embeds=None, prompt_attention_mask=None, negative_prompt_attention_mask=None, max_sequence_length=256, 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. ms device to place the resulting embeddings on

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/mochi/pipeline_mochi.py
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
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,
    prompt_attention_mask: Optional[ms.Tensor] = None,
    negative_prompt_attention_mask: Optional[ms.Tensor] = None,
    max_sequence_length: int = 256,
    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. ms device to place the resulting embeddings on
        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, prompt_attention_mask = 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, negative_prompt_attention_mask = 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, prompt_attention_mask, negative_prompt_embeds, negative_prompt_attention_mask

mindone.diffusers.pipelines.mochi.pipeline_output.MochiPipelineOutput dataclass

Bases: BaseOutput

Output class for Mochi 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 Torch 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/mochi/pipeline_output.py
 8
 9
10
11
12
13
14
15
16
17
18
19
20
@dataclass
class MochiPipelineOutput(BaseOutput):
    r"""
    Output class for Mochi 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 Torch tensor of shape
            `(batch_size, num_frames, channels, height, width)`.
    """

    frames: ms.Tensor