Skip to content

ConsisID

LoRA

Identity-Preserving Text-to-Video Generation by Frequency Decomposition from Peking University & University of Rochester & etc, by Shenghai Yuan, Jinfa Huang, Xianyi He, Yunyang Ge, Yujun Shi, Liuhan Chen, Jiebo Luo, Li Yuan.

The abstract from the paper is:

Identity-preserving text-to-video (IPT2V) generation aims to create high-fidelity videos with consistent human identity. It is an important task in video generation but remains an open problem for generative models. This paper pushes the technical frontier of IPT2V in two directions that have not been resolved in the literature: (1) A tuning-free pipeline without tedious case-by-case finetuning, and (2) A frequency-aware heuristic identity-preserving Diffusion Transformer (DiT)-based control scheme. To achieve these goals, we propose ConsisID, a tuning-free DiT-based controllable IPT2V model to keep human-id**entity **consis**tent in the generated video. Inspired by prior findings in frequency analysis of vision/diffusion transformers, it employs identity-control signals in the frequency domain, where facial features can be decomposed into low-frequency global features (e.g., profile, proportions) and high-frequency intrinsic features (e.g., identity markers that remain unaffected by pose changes). First, from a low-frequency perspective, we introduce a global facial extractor, which encodes the reference image and facial key points into a latent space, generating features enriched with low-frequency information. These features are then integrated into the shallow layers of the network to alleviate training challenges associated with DiT. Second, from a high-frequency perspective, we design a local facial extractor to capture high-frequency details and inject them into the transformer blocks, enhancing the model's ability to preserve fine-grained features. To leverage the frequency information for identity preservation, we propose a hierarchical training strategy, transforming a vanilla pre-trained video generation model into an IPT2V model. Extensive experiments demonstrate that our frequency-aware heuristic scheme provides an optimal control solution for DiT-based models. Thanks to this scheme, our **ConsisID achieves excellent results in generating high-quality, identity-preserving videos, making strides towards more effective IPT2V. The model weight of ConsID is publicly available at https://github.com/PKU-YuanGroup/ConsisID.

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.

This pipeline was contributed by SHYuanBest. The original codebase can be found here. The original weights can be found under hf.co/BestWishYsh.

There are two official ConsisID checkpoints for identity-preserving text-to-video.

checkpoints recommended inference dtype
BestWishYsh/ConsisID-preview mindspore.bfloat16
BestWishYsh/ConsisID-1.5 mindspore.bfloat16

Memory optimization

ConsisID requires about 44 GB of device memory to decode 49 frames (6 seconds of video at 8 FPS) with output resolution 720x480 (W x H). The following memory optimizations could be used to reduce the memory footprint. For replication, you can refer to this script.

Feature (overlay the previous) Max Memory Allocated Max Memory Reserved
- 37 GB 44 GB
enable_model_cpu_offload 22 GB 25 GB
enable_sequential_cpu_offload 16 GB 22 GB
vae.enable_slicing 16 GB 22 GB
vae.enable_tiling 5 GB 7 GB

mindone.diffusers.pipelines.consisid.ConsisIDPipeline

Bases: DiffusionPipeline, CogVideoXLoraLoaderMixin

Pipeline for image-to-video generation using ConsisID.

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

PARAMETER DESCRIPTION
vae

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

TYPE: [`AutoencoderKL`]

text_encoder

Frozen text-encoder. ConsisID uses T5; specifically the t5-v1_1-xxl variant.

TYPE: [`T5EncoderModel`]

tokenizer

Tokenizer of class T5Tokenizer.

TYPE: `T5Tokenizer`

transformer

A text conditioned ConsisIDTransformer3DModel to denoise the encoded video latents.

TYPE: [`ConsisIDTransformer3DModel`]

scheduler

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

TYPE: [`SchedulerMixin`]

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

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

    Args:
        vae ([`AutoencoderKL`]):
            Variational Auto-Encoder (VAE) Model to encode and decode videos to and from latent representations.
        text_encoder ([`T5EncoderModel`]):
            Frozen text-encoder. ConsisID uses
            [T5](https://huggingface.co/docs/transformers/model_doc/t5#transformers.T5EncoderModel); specifically the
            [t5-v1_1-xxl](https://huggingface.co/PixArt-alpha/PixArt-alpha/tree/main/t5-v1_1-xxl) variant.
        tokenizer (`T5Tokenizer`):
            Tokenizer of class
            [T5Tokenizer](https://huggingface.co/docs/transformers/model_doc/t5#transformers.T5Tokenizer).
        transformer ([`ConsisIDTransformer3DModel`]):
            A text conditioned `ConsisIDTransformer3DModel` to denoise the encoded video latents.
        scheduler ([`SchedulerMixin`]):
            A scheduler to be used in combination with `transformer` to denoise the encoded video latents.
    """

    _optional_components = []
    model_cpu_offload_seq = "text_encoder->transformer->vae"

    _callback_tensor_inputs = [
        "latents",
        "prompt_embeds",
        "negative_prompt_embeds",
    ]

    def __init__(
        self,
        tokenizer: T5Tokenizer,
        text_encoder: T5EncoderModel,
        vae: AutoencoderKLCogVideoX,
        transformer: ConsisIDTransformer3DModel,
        scheduler: CogVideoXDPMScheduler,
    ):
        super().__init__()

        self.register_modules(
            tokenizer=tokenizer,
            text_encoder=text_encoder,
            vae=vae,
            transformer=transformer,
            scheduler=scheduler,
        )
        self.vae_scale_factor_spatial = (
            2 ** (len(self.vae.config.block_out_channels) - 1) if hasattr(self, "vae") and self.vae is not None else 8
        )
        self.vae_scale_factor_temporal = (
            self.vae.config.temporal_compression_ratio if hasattr(self, "vae") and self.vae is not None else 4
        )
        self.vae_scaling_factor_image = (
            self.vae.config.scaling_factor if hasattr(self, "vae") and self.vae is not None else 0.7
        )

        self.video_processor = VideoProcessor(vae_scale_factor=self.vae_scale_factor_spatial)

    # Copied from diffusers.pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipeline._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
        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 = text_inputs.input_ids
        untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="np").input_ids

        if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not np.array_equal(
            text_input_ids, untruncated_ids
        ):
            removed_text = self.tokenizer.batch_decode(untruncated_ids[:, 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(ms.Tensor.from_numpy(text_input_ids))[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)

        return prompt_embeds

    # Copied 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,
        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*):
                torch 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 prepare_latents(
        self,
        image: ms.Tensor,
        batch_size: int = 1,
        num_channels_latents: int = 16,
        num_frames: int = 13,
        height: int = 60,
        width: int = 90,
        dtype: Optional[ms.Type] = None,
        generator: Optional[np.random.Generator] = None,
        latents: Optional[ms.Tensor] = None,
        kps_cond: 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_frames = (num_frames - 1) // self.vae_scale_factor_temporal + 1
        shape = (
            batch_size,
            num_frames,
            num_channels_latents,
            height // self.vae_scale_factor_spatial,
            width // self.vae_scale_factor_spatial,
        )

        image = image.unsqueeze(2)  # [B, C, F, H, W]

        if isinstance(generator, list):
            image_latents = [
                retrieve_latents(self.vae, self.vae.encode(image[i].unsqueeze(0))[0], generator[i])
                for i in range(batch_size)
            ]
            if kps_cond is not None:
                kps_cond = kps_cond.unsqueeze(2)
                kps_cond_latents = [
                    retrieve_latents(self.vae, self.vae.encode(kps_cond[i].unsqueeze(0))[0], generator[i])
                    for i in range(batch_size)
                ]
        else:
            image_latents = [
                retrieve_latents(self.vae, self.vae.encode(img.unsqueeze(0))[0], generator) for img in image
            ]
            if kps_cond is not None:
                kps_cond = kps_cond.unsqueeze(2)
                kps_cond_latents = [
                    retrieve_latents(self.vae, self.vae.encode(img.unsqueeze(0))[0], generator) for img in kps_cond
                ]

        image_latents = mint.cat(image_latents, dim=0).to(dtype).permute(0, 2, 1, 3, 4)  # [B, F, C, H, W]
        image_latents = self.vae_scaling_factor_image * image_latents

        if kps_cond is not None:
            kps_cond_latents = mint.cat(kps_cond_latents, dim=0).to(dtype).permute(0, 2, 1, 3, 4)  # [B, F, C, H, W]
            kps_cond_latents = self.vae_scaling_factor_image * kps_cond_latents

            padding_shape = (
                batch_size,
                num_frames - 2,
                num_channels_latents,
                height // self.vae_scale_factor_spatial,
                width // self.vae_scale_factor_spatial,
            )
        else:
            padding_shape = (
                batch_size,
                num_frames - 1,
                num_channels_latents,
                height // self.vae_scale_factor_spatial,
                width // self.vae_scale_factor_spatial,
            )

        latent_padding = mint.zeros(padding_shape, dtype=dtype)
        if kps_cond is not None:
            image_latents = mint.cat([image_latents, kps_cond_latents, latent_padding], dim=1)
        else:
            image_latents = mint.cat([image_latents, latent_padding], dim=1)

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

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

    # Copied from diffusers.pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipeline.decode_latents
    def decode_latents(self, latents: ms.Tensor) -> ms.Tensor:
        latents = latents.permute(0, 2, 1, 3, 4)  # [batch_size, num_channels, num_frames, height, width]
        latents = 1 / self.vae_scaling_factor_image * latents
        # vae decode only support pynative
        with pynative_context():
            frames = self.vae.decode(latents)[0]
        return frames

    # 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

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

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

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

    def check_inputs(
        self,
        image,
        prompt,
        height,
        width,
        negative_prompt,
        callback_on_step_end_tensor_inputs,
        latents=None,
        prompt_embeds=None,
        negative_prompt_embeds=None,
    ):
        if not isinstance(image, ms.Tensor) and not isinstance(image, PIL.Image.Image) and not isinstance(image, list):
            raise ValueError(
                "`image` has to be of type `ms.Tensor` or `PIL.Image.Image` or `List[PIL.Image.Image]` but is"
                f" {type(image)}"
            )

        if height % 8 != 0 or width % 8 != 0:
            raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")

        if callback_on_step_end_tensor_inputs is not None and not all(
            k in self._callback_tensor_inputs for k in callback_on_step_end_tensor_inputs
        ):
            raise ValueError(
                f"`callback_on_step_end_tensor_inputs` has to be in {self._callback_tensor_inputs}, but found {[k for k in callback_on_step_end_tensor_inputs if k not in self._callback_tensor_inputs]}"  # noqa: E501
            )
        if prompt is not None and prompt_embeds is not None:
            raise ValueError(
                f"Cannot forward both `prompt`: {prompt} and `prompt_embeds`: {prompt_embeds}. Please make sure to"
                " only forward one of the two."
            )
        elif prompt is None and prompt_embeds is None:
            raise ValueError(
                "Provide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined."
            )
        elif prompt is not None and (not isinstance(prompt, str) and not isinstance(prompt, list)):
            raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")

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

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

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

    def _prepare_rotary_positional_embeddings(
        self,
        height: int,
        width: int,
        num_frames: int,
    ) -> Tuple[ms.Tensor, ms.Tensor]:
        grid_height = height // (self.vae_scale_factor_spatial * self.transformer.config.patch_size)
        grid_width = width // (self.vae_scale_factor_spatial * self.transformer.config.patch_size)
        base_size_width = self.transformer.config.sample_width // self.transformer.config.patch_size
        base_size_height = self.transformer.config.sample_height // self.transformer.config.patch_size

        grid_crops_coords = get_resize_crop_region_for_grid(
            (grid_height, grid_width), base_size_width, base_size_height
        )
        freqs_cos, freqs_sin = get_3d_rotary_pos_embed(
            embed_dim=self.transformer.config.attention_head_dim,
            crops_coords=grid_crops_coords,
            grid_size=(grid_height, grid_width),
            temporal_size=num_frames,
        )

        return freqs_cos, freqs_sin

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

    @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,
        image: PipelineImageInput,
        prompt: Optional[Union[str, List[str]]] = None,
        negative_prompt: Optional[Union[str, List[str]]] = None,
        height: int = 480,
        width: int = 720,
        num_frames: int = 49,
        num_inference_steps: int = 50,
        guidance_scale: float = 6.0,
        use_dynamic_cfg: bool = False,
        num_videos_per_prompt: int = 1,
        eta: float = 0.0,
        generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
        latents: Optional[ms.Tensor] = None,
        prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        output_type: str = "pil",
        return_dict: bool = True,
        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 = 226,
        id_vit_hidden: Optional[ms.Tensor] = None,
        id_cond: Optional[ms.Tensor] = None,
        kps_cond: Optional[ms.Tensor] = None,
    ) -> Union[ConsisIDPipelineOutput, Tuple]:
        """
        Function invoked when calling 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`, *optional*, defaults to self.transformer.config.sample_height * self.vae_scale_factor_spatial):
                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.transformer.config.sample_height * self.vae_scale_factor_spatial):
                The width in pixels of the generated image. This is set to 720 by default for the best results.
            num_frames (`int`, defaults to `49`):
                Number of frames to generate. Must be divisible by self.vae_scale_factor_temporal. Generated video will
                contain 1 extra frame because ConsisID is conditioned with (num_seconds * fps + 1) frames where
                num_seconds is 6 and fps is 4. However, since videos can be saved at any fps, the only condition that
                needs to be satisfied is that of divisibility mentioned above.
            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.
            guidance_scale (`float`, *optional*, defaults to 6):
                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.
            use_dynamic_cfg (`bool`, *optional*, defaults to `False`):
                If True, dynamically adjusts the guidance scale during inference. This allows the model to use a
                progressive guidance scale, improving the balance between text-guided generation and image quality over
                the course of the inference steps. Typically, early inference steps use a higher guidance scale for
                more faithful image generation, while later steps reduce it for more diverse and natural results.
            num_videos_per_prompt (`int`, *optional*, defaults to 1):
                The number of videos to generate per prompt.
            generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                One or a list of [torch 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.
            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.
            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 `True`):
                Whether or not to return a [`~pipelines.stable_diffusion_xl.StableDiffusionXLPipelineOutput`] 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 `226`):
                Maximum sequence length in encoded prompt. Must be consistent with
                `self.transformer.config.max_text_seq_length` otherwise may lead to poor results.
            id_vit_hidden (`Optional[ms.Tensor]`, *optional*):
                The tensor representing the hidden features extracted from the face model, which are used to condition
                the local facial extractor. This is crucial for the model to obtain high-frequency information of the
                face. If not provided, the local facial extractor will not run normally.
            id_cond (`Optional[ms.Tensor]`, *optional*):
                The tensor representing the hidden features extracted from the clip model, which are used to condition
                the local facial extractor. This is crucial for the model to edit facial features If not provided, the
                local facial extractor will not run normally.
            kps_cond (`Optional[ms.Tensor]`, *optional*):
                A tensor that determines whether the global facial extractor use keypoint information for conditioning.
                If provided, this tensor controls whether facial keypoints such as eyes, nose, and mouth landmarks are
                used during the generation process. This helps ensure the model retains more facial low-frequency
                information.

        Examples:

        Returns:
            [`~pipelines.consisid.pipeline_output.ConsisIDPipelineOutput`] or `tuple`:
            [`~pipelines.consisid.pipeline_output.ConsisIDPipelineOutput`] if `return_dict` is True, otherwise a
            `tuple`. When returning a tuple, 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.transformer.config.sample_height * self.vae_scale_factor_spatial
        width = width or self.transformer.config.sample_width * self.vae_scale_factor_spatial
        num_frames = num_frames or self.transformer.config.sample_frames

        num_videos_per_prompt = 1

        # 1. Check inputs. Raise error if not correct
        self.check_inputs(
            image=image,
            prompt=prompt,
            height=height,
            width=width,
            negative_prompt=negative_prompt,
            callback_on_step_end_tensor_inputs=callback_on_step_end_tensor_inputs,
            latents=latents,
            prompt_embeds=prompt_embeds,
            negative_prompt_embeds=negative_prompt_embeds,
        )
        self._guidance_scale = guidance_scale
        self._attention_kwargs = attention_kwargs
        self._interrupt = False

        # 2. Default 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]

        # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
        # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
        # corresponds to doing no classifier free guidance.
        do_classifier_free_guidance = guidance_scale > 1.0

        # 3. Encode input prompt
        prompt_embeds, negative_prompt_embeds = self.encode_prompt(
            prompt=prompt,
            negative_prompt=negative_prompt,
            do_classifier_free_guidance=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,
        )
        if do_classifier_free_guidance:
            prompt_embeds = mint.cat([negative_prompt_embeds, prompt_embeds], dim=0)

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

        # 5. Prepare latents
        is_kps = getattr(self.transformer.config, "is_kps", False)
        kps_cond = kps_cond if is_kps else None
        if kps_cond is not None:
            kps_cond = draw_kps(image, kps_cond)
            kps_cond = self.video_processor.preprocess(kps_cond, height=height, width=width).to(
                dtype=prompt_embeds.dtype
            )

        image = self.video_processor.preprocess(image, height=height, width=width).to(dtype=prompt_embeds.dtype)

        latent_channels = self.transformer.config.in_channels // 2
        latents, image_latents = self.prepare_latents(
            image,
            batch_size * num_videos_per_prompt,
            latent_channels,
            num_frames,
            height,
            width,
            prompt_embeds.dtype,
            generator,
            latents,
            kps_cond,
        )

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

        # 7. Create rotary embeds if required
        image_rotary_emb = (
            self._prepare_rotary_positional_embeddings(height, width, latents.shape[1])
            if self.transformer.config.use_rotary_positional_embeddings
            else None
        )

        # 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)

        # 8. Denoising loop
        num_warmup_steps = max(len(timesteps) - num_inference_steps * self.scheduler.order, 0)

        with self.progress_bar(total=num_inference_steps) as progress_bar:
            # for DPM-solver++
            old_pred_original_sample = None
            for i, t in enumerate(timesteps):
                if self.interrupt:
                    continue

                latent_model_input = mint.cat([latents] * 2) if do_classifier_free_guidance else latents
                latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)

                latent_image_input = mint.cat([image_latents] * 2) if do_classifier_free_guidance else image_latents
                latent_model_input = mint.cat([latent_model_input, latent_image_input], dim=2)

                # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
                timestep = t.broadcast_to((latent_model_input.shape[0],))

                # predict noise model_output
                noise_pred = self.transformer(
                    hidden_states=latent_model_input,
                    encoder_hidden_states=prompt_embeds,
                    timestep=timestep,
                    image_rotary_emb=image_rotary_emb,
                    attention_kwargs=attention_kwargs,
                    return_dict=False,
                    id_vit_hidden=id_vit_hidden,
                    id_cond=id_cond,
                )[0]
                noise_pred = noise_pred.float()

                # perform guidance
                if use_dynamic_cfg:
                    self._guidance_scale = 1 + guidance_scale * (
                        (
                            1
                            - math.cos(
                                math.pi * ((num_inference_steps - timesteps[i].item()) / num_inference_steps) ** 5.0
                            )
                        )
                        / 2
                    )
                if 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
                if not isinstance(self.scheduler, CogVideoXDPMScheduler):
                    latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]
                else:
                    latents, old_pred_original_sample = self.scheduler.step(
                        noise_pred,
                        old_pred_original_sample,
                        t,
                        timesteps[i - 1] if i > 0 else None,
                        latents,
                        **extra_step_kwargs,
                        return_dict=False,
                    )
                latents = latents.to(prompt_embeds.dtype)

                # call the callback, if provided
                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)

                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 not output_type == "latent":
            video = self.decode_latents(latents)
            video = self.video_processor.postprocess_video(video=video, output_type=output_type)
        else:
            video = latents

        if not return_dict:
            return (video,)

        return ConsisIDPipelineOutput(frames=video)

mindone.diffusers.pipelines.consisid.ConsisIDPipeline.__call__(image, prompt=None, negative_prompt=None, height=480, width=720, num_frames=49, num_inference_steps=50, guidance_scale=6.0, use_dynamic_cfg=False, num_videos_per_prompt=1, eta=0.0, generator=None, latents=None, prompt_embeds=None, negative_prompt_embeds=None, output_type='pil', return_dict=True, attention_kwargs=None, callback_on_step_end=None, callback_on_step_end_tensor_inputs=['latents'], max_sequence_length=226, id_vit_hidden=None, id_cond=None, kps_cond=None)

Function invoked when calling 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 in pixels of the generated image. This is set to 480 by default for the best results.

TYPE: `int`, *optional*, defaults to self.transformer.config.sample_height * self.vae_scale_factor_spatial DEFAULT: 480

width

The width in pixels of the generated image. This is set to 720 by default for the best results.

TYPE: `int`, *optional*, defaults to self.transformer.config.sample_height * self.vae_scale_factor_spatial DEFAULT: 720

num_frames

Number of frames to generate. Must be divisible by self.vae_scale_factor_temporal. Generated video will contain 1 extra frame because ConsisID is conditioned with (num_seconds * fps + 1) frames where num_seconds is 6 and fps is 4. However, since videos can be saved at any fps, the only condition that needs to be satisfied is that of divisibility mentioned above.

TYPE: `int`, defaults to `49` DEFAULT: 49

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: 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`, *optional*, defaults to 6 DEFAULT: 6.0

use_dynamic_cfg

If True, dynamically adjusts the guidance scale during inference. This allows the model to use a progressive guidance scale, improving the balance between text-guided generation and image quality over the course of the inference steps. Typically, early inference steps use a higher guidance scale for more faithful image generation, while later steps reduce it for more diverse and natural results.

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

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 torch generator(s) to make generation deterministic.

TYPE: `torch.Generator` or `List[torch.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

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

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.stable_diffusion_xl.StableDiffusionXLPipelineOutput] instead of a plain tuple.

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

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 in encoded prompt. Must be consistent with self.transformer.config.max_text_seq_length otherwise may lead to poor results.

TYPE: `int`, defaults to `226` DEFAULT: 226

id_vit_hidden

The tensor representing the hidden features extracted from the face model, which are used to condition the local facial extractor. This is crucial for the model to obtain high-frequency information of the face. If not provided, the local facial extractor will not run normally.

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

id_cond

The tensor representing the hidden features extracted from the clip model, which are used to condition the local facial extractor. This is crucial for the model to edit facial features If not provided, the local facial extractor will not run normally.

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

kps_cond

A tensor that determines whether the global facial extractor use keypoint information for conditioning. If provided, this tensor controls whether facial keypoints such as eyes, nose, and mouth landmarks are used during the generation process. This helps ensure the model retains more facial low-frequency information.

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

RETURNS DESCRIPTION
Union[ConsisIDPipelineOutput, Tuple]

[~pipelines.consisid.pipeline_output.ConsisIDPipelineOutput] or tuple:

Union[ConsisIDPipelineOutput, Tuple]

[~pipelines.consisid.pipeline_output.ConsisIDPipelineOutput] if return_dict is True, otherwise a

Union[ConsisIDPipelineOutput, Tuple]

tuple. When returning a tuple, the first element is a list with the generated images.

Source code in mindone/diffusers/pipelines/consisid/pipeline_consisid.py
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
def __call__(
    self,
    image: PipelineImageInput,
    prompt: Optional[Union[str, List[str]]] = None,
    negative_prompt: Optional[Union[str, List[str]]] = None,
    height: int = 480,
    width: int = 720,
    num_frames: int = 49,
    num_inference_steps: int = 50,
    guidance_scale: float = 6.0,
    use_dynamic_cfg: bool = False,
    num_videos_per_prompt: int = 1,
    eta: float = 0.0,
    generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
    latents: Optional[ms.Tensor] = None,
    prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    output_type: str = "pil",
    return_dict: bool = True,
    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 = 226,
    id_vit_hidden: Optional[ms.Tensor] = None,
    id_cond: Optional[ms.Tensor] = None,
    kps_cond: Optional[ms.Tensor] = None,
) -> Union[ConsisIDPipelineOutput, Tuple]:
    """
    Function invoked when calling 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`, *optional*, defaults to self.transformer.config.sample_height * self.vae_scale_factor_spatial):
            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.transformer.config.sample_height * self.vae_scale_factor_spatial):
            The width in pixels of the generated image. This is set to 720 by default for the best results.
        num_frames (`int`, defaults to `49`):
            Number of frames to generate. Must be divisible by self.vae_scale_factor_temporal. Generated video will
            contain 1 extra frame because ConsisID is conditioned with (num_seconds * fps + 1) frames where
            num_seconds is 6 and fps is 4. However, since videos can be saved at any fps, the only condition that
            needs to be satisfied is that of divisibility mentioned above.
        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.
        guidance_scale (`float`, *optional*, defaults to 6):
            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.
        use_dynamic_cfg (`bool`, *optional*, defaults to `False`):
            If True, dynamically adjusts the guidance scale during inference. This allows the model to use a
            progressive guidance scale, improving the balance between text-guided generation and image quality over
            the course of the inference steps. Typically, early inference steps use a higher guidance scale for
            more faithful image generation, while later steps reduce it for more diverse and natural results.
        num_videos_per_prompt (`int`, *optional*, defaults to 1):
            The number of videos to generate per prompt.
        generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
            One or a list of [torch 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.
        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.
        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 `True`):
            Whether or not to return a [`~pipelines.stable_diffusion_xl.StableDiffusionXLPipelineOutput`] 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 `226`):
            Maximum sequence length in encoded prompt. Must be consistent with
            `self.transformer.config.max_text_seq_length` otherwise may lead to poor results.
        id_vit_hidden (`Optional[ms.Tensor]`, *optional*):
            The tensor representing the hidden features extracted from the face model, which are used to condition
            the local facial extractor. This is crucial for the model to obtain high-frequency information of the
            face. If not provided, the local facial extractor will not run normally.
        id_cond (`Optional[ms.Tensor]`, *optional*):
            The tensor representing the hidden features extracted from the clip model, which are used to condition
            the local facial extractor. This is crucial for the model to edit facial features If not provided, the
            local facial extractor will not run normally.
        kps_cond (`Optional[ms.Tensor]`, *optional*):
            A tensor that determines whether the global facial extractor use keypoint information for conditioning.
            If provided, this tensor controls whether facial keypoints such as eyes, nose, and mouth landmarks are
            used during the generation process. This helps ensure the model retains more facial low-frequency
            information.

    Examples:

    Returns:
        [`~pipelines.consisid.pipeline_output.ConsisIDPipelineOutput`] or `tuple`:
        [`~pipelines.consisid.pipeline_output.ConsisIDPipelineOutput`] if `return_dict` is True, otherwise a
        `tuple`. When returning a tuple, 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.transformer.config.sample_height * self.vae_scale_factor_spatial
    width = width or self.transformer.config.sample_width * self.vae_scale_factor_spatial
    num_frames = num_frames or self.transformer.config.sample_frames

    num_videos_per_prompt = 1

    # 1. Check inputs. Raise error if not correct
    self.check_inputs(
        image=image,
        prompt=prompt,
        height=height,
        width=width,
        negative_prompt=negative_prompt,
        callback_on_step_end_tensor_inputs=callback_on_step_end_tensor_inputs,
        latents=latents,
        prompt_embeds=prompt_embeds,
        negative_prompt_embeds=negative_prompt_embeds,
    )
    self._guidance_scale = guidance_scale
    self._attention_kwargs = attention_kwargs
    self._interrupt = False

    # 2. Default 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]

    # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
    # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
    # corresponds to doing no classifier free guidance.
    do_classifier_free_guidance = guidance_scale > 1.0

    # 3. Encode input prompt
    prompt_embeds, negative_prompt_embeds = self.encode_prompt(
        prompt=prompt,
        negative_prompt=negative_prompt,
        do_classifier_free_guidance=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,
    )
    if do_classifier_free_guidance:
        prompt_embeds = mint.cat([negative_prompt_embeds, prompt_embeds], dim=0)

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

    # 5. Prepare latents
    is_kps = getattr(self.transformer.config, "is_kps", False)
    kps_cond = kps_cond if is_kps else None
    if kps_cond is not None:
        kps_cond = draw_kps(image, kps_cond)
        kps_cond = self.video_processor.preprocess(kps_cond, height=height, width=width).to(
            dtype=prompt_embeds.dtype
        )

    image = self.video_processor.preprocess(image, height=height, width=width).to(dtype=prompt_embeds.dtype)

    latent_channels = self.transformer.config.in_channels // 2
    latents, image_latents = self.prepare_latents(
        image,
        batch_size * num_videos_per_prompt,
        latent_channels,
        num_frames,
        height,
        width,
        prompt_embeds.dtype,
        generator,
        latents,
        kps_cond,
    )

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

    # 7. Create rotary embeds if required
    image_rotary_emb = (
        self._prepare_rotary_positional_embeddings(height, width, latents.shape[1])
        if self.transformer.config.use_rotary_positional_embeddings
        else None
    )

    # 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)

    # 8. Denoising loop
    num_warmup_steps = max(len(timesteps) - num_inference_steps * self.scheduler.order, 0)

    with self.progress_bar(total=num_inference_steps) as progress_bar:
        # for DPM-solver++
        old_pred_original_sample = None
        for i, t in enumerate(timesteps):
            if self.interrupt:
                continue

            latent_model_input = mint.cat([latents] * 2) if do_classifier_free_guidance else latents
            latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)

            latent_image_input = mint.cat([image_latents] * 2) if do_classifier_free_guidance else image_latents
            latent_model_input = mint.cat([latent_model_input, latent_image_input], dim=2)

            # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
            timestep = t.broadcast_to((latent_model_input.shape[0],))

            # predict noise model_output
            noise_pred = self.transformer(
                hidden_states=latent_model_input,
                encoder_hidden_states=prompt_embeds,
                timestep=timestep,
                image_rotary_emb=image_rotary_emb,
                attention_kwargs=attention_kwargs,
                return_dict=False,
                id_vit_hidden=id_vit_hidden,
                id_cond=id_cond,
            )[0]
            noise_pred = noise_pred.float()

            # perform guidance
            if use_dynamic_cfg:
                self._guidance_scale = 1 + guidance_scale * (
                    (
                        1
                        - math.cos(
                            math.pi * ((num_inference_steps - timesteps[i].item()) / num_inference_steps) ** 5.0
                        )
                    )
                    / 2
                )
            if 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
            if not isinstance(self.scheduler, CogVideoXDPMScheduler):
                latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]
            else:
                latents, old_pred_original_sample = self.scheduler.step(
                    noise_pred,
                    old_pred_original_sample,
                    t,
                    timesteps[i - 1] if i > 0 else None,
                    latents,
                    **extra_step_kwargs,
                    return_dict=False,
                )
            latents = latents.to(prompt_embeds.dtype)

            # call the callback, if provided
            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)

            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 not output_type == "latent":
        video = self.decode_latents(latents)
        video = self.video_processor.postprocess_video(video=video, output_type=output_type)
    else:
        video = latents

    if not return_dict:
        return (video,)

    return ConsisIDPipelineOutput(frames=video)

mindone.diffusers.pipelines.consisid.ConsisIDPipeline.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): torch dtype

TYPE: Optional[Type] DEFAULT: None

Source code in mindone/diffusers/pipelines/consisid/pipeline_consisid.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
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*):
            torch 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.consisid.pipeline_output.ConsisIDPipelineOutput dataclass

Bases: BaseOutput

Output class for ConsisID 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: `torch.Tensor`, `np.ndarray`, or List[List[PIL.Image.Image]]

Source code in mindone/diffusers/pipelines/consisid/pipeline_output.py
 8
 9
10
11
12
13
14
15
16
17
18
19
20
@dataclass
class ConsisIDPipelineOutput(BaseOutput):
    r"""
    Output class for ConsisID pipelines.

    Args:
        frames (`torch.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