ConsisID¶
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:
|
text_encoder
|
Frozen text-encoder. ConsisID uses T5; specifically the t5-v1_1-xxl variant.
TYPE:
|
tokenizer
|
Tokenizer of class T5Tokenizer.
TYPE:
|
transformer
|
A text conditioned
TYPE:
|
scheduler
|
A scheduler to be used in combination with
TYPE:
|
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 |
|
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
TYPE:
|
prompt
|
The prompt or prompts to guide the image generation. If not defined, one has to pass
TYPE:
|
negative_prompt
|
The prompt or prompts not to guide the image generation. If not defined, one has to pass
TYPE:
|
height
|
The height in pixels of the generated image. This is set to 480 by default for the best results.
TYPE:
|
width
|
The width in pixels of the generated image. This is set to 720 by default for the best results.
TYPE:
|
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:
|
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:
|
guidance_scale
|
Guidance scale as defined in Classifier-Free Diffusion Guidance.
TYPE:
|
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:
|
num_videos_per_prompt
|
The number of videos to generate per prompt.
TYPE:
|
generator
|
One or a list of torch generator(s) to make generation deterministic.
TYPE:
|
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
TYPE:
|
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
TYPE:
|
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
TYPE:
|
output_type
|
The output format of the generate image. Choose between
PIL:
TYPE:
|
return_dict
|
Whether or not to return a [
TYPE:
|
attention_kwargs
|
A kwargs dictionary that if specified is passed along to the
TYPE:
|
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:
TYPE:
|
callback_on_step_end_tensor_inputs
|
The list of tensor inputs for the
TYPE:
|
max_sequence_length
|
Maximum sequence length in encoded prompt. Must be consistent with
TYPE:
|
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:
|
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:
|
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:
|
RETURNS | DESCRIPTION |
---|---|
Union[ConsisIDPipelineOutput, Tuple]
|
[ |
Union[ConsisIDPipelineOutput, Tuple]
|
[ |
Union[ConsisIDPipelineOutput, Tuple]
|
|
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 |
|
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:
|
negative_prompt
|
The prompt or prompts not to guide the image generation. If not defined, one has to pass
TYPE:
|
do_classifier_free_guidance
|
Whether to use classifier free guidance or not.
TYPE:
|
num_videos_per_prompt
|
Number of videos that should be generated per prompt.
TYPE:
|
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
TYPE:
|
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
TYPE:
|
dtype
|
(
TYPE:
|
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 |
|
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
TYPE:
|
Source code in mindone/diffusers/pipelines/consisid/pipeline_output.py
8 9 10 11 12 13 14 15 16 17 18 19 20 |
|