Hugging Face's logo

benjamin-paine
/
champ

Diffusers
Safetensors
CHAMPPipeline
Model card Files Community
champ / README.md
benjamin-paine's picture
benjamin-paine
Update README.md
03e71d4 verified
preview code
|
raw
history blame
10.9 kB
metadata
license: apache-2.0

This repository contains a pruned and partially reorganized version of AniPortrait.

@misc{wei2024aniportrait,
      title={AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animations}, 
      author={Huawei Wei and Zejun Yang and Zhisheng Wang},
      year={2024},
      eprint={2403.17694},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Usage

Installation

First, install the AniPortrait package into your python environment. If you're creating a new environment for AniPortrait, be sure you also specify the version of torch you want with CUDA support, or else this will try to run only on CPU.

pip install git+https://github.com/painebenjamin/aniportrait.git

Now, you can create the pipeline, automatically pulling the weights from this repository, either as individual models:

from aniportrait import AniPortraitPipeline
pipeline = AniPortraitPipeline.from_pretrained(
  "benjamin-paine/aniportrait",
  torch_dtype=torch.float16,
  variant="fp16",
  device="cuda"
).to("cuda", dtype=torch.float16)

Or, as a single file:

from aniportrait import AniPortraitPipeline
pipeline = AniPortraitPipeline.from_single_file(
  "benjamin-paine/aniportrait",
  torch_dtype=torch.float16,
  variant="fp16",
  device="cuda"
).to("cuda", dtype=torch.float16)

The AniPortraitPipeline is a mega pipeline, capable of instantiating and executing other pipelines. It provides the following functions:

Workflows

img2img 

pipeline.img2img(
    reference_image: PIL.Image.Image,
    pose_reference_image: PIL.Image.Image,
    num_inference_steps: int,
    guidance_scale: float,
    eta: float=0.0,
    reference_pose_image: Optional[Image.Image]=None,
    generation: Optional[Union[torch.Generator, List[torch.Generator]]]=None,
    output_type: Optional[str]="pil",
    return_dict: bool=True,
    callback: Optional[Callable[[int, int, torch.FloatTensor], None]]=None,
    callback_steps: Optional[int]=None,
    width: Optional[int]=None,
    height: Optional[int]=None,
    **kwargs: Any
) -> Pose2VideoPipelineOutput

Using a reference image (for structure) and a pose reference image (for pose), render an image of the former in the pose of the latter.

  • The pose reference image here is an unprocessed image, from which the face pose will be extracted.
  • Optionally pass reference_pose_image to designate the pose of reference_image. When not passed, the pose of reference_image is automatically detected.

vid2vid 

pipeline.vid2vid(
    reference_image: PIL.Image.Image,
    pose_reference_images: List[PIL.Image.Image],
    num_inference_steps: int,
    guidance_scale: float,
    eta: float=0.0,
    reference_pose_image: Optional[Image.Image]=None,
    generation: Optional[Union[torch.Generator, List[torch.Generator]]]=None,
    output_type: Optional[str]="pil",
    return_dict: bool=True,
    callback: Optional[Callable[[int, int, torch.FloatTensor], None]]=None,
    callback_steps: Optional[int]=None,
    width: Optional[int]=None,
    height: Optional[int]=None,
    video_length: Optional[int]=None,
    context_schedule: str="uniform",
    context_frames: int=16,
    context_overlap: int=4,
    context_batch_size: int=1,
    interpolation_factor: int=1,
    use_long_video: bool=True,
    **kwargs: Any
) -> Pose2VideoPipelineOutput

Using a reference image (for structure) and a sequence of pose reference images (for pose), render a video of the former in the poses of the latter, using context windowing for long-video generation when the poses are longer than 16 frames.

  • Optionally pass use_long_video = false to disable using the long video pipeline.
  • Optionally pass reference_pose_image to designate the pose of reference_image. When not passed, the pose of reference_image is automatically detected.
  • Optionally pass video_length to use this many frames. Default is the same as the length of the pose reference images.

audio2vid 

pipeline.audio2vid(
    audio: str,
    reference_image: PIL.Image.Image,
    num_inference_steps: int,
    guidance_scale: float,
    fps: int=30,
    eta: float=0.0,
    reference_pose_image: Optional[Image.Image]=None,
    pose_reference_images: Optional[List[PIL.Image.Image]]=None,
    generation: Optional[Union[torch.Generator, List[torch.Generator]]]=None,
    output_type: Optional[str]="pil",
    return_dict: bool=True,
    callback: Optional[Callable[[int, int, torch.FloatTensor], None]]=None,
    callback_steps: Optional[int]=None,
    width: Optional[int]=None,
    height: Optional[int]=None,
    video_length: Optional[int]=None,
    context_schedule: str="uniform",
    context_frames: int=16,
    context_overlap: int=4,
    context_batch_size: int=1,
    interpolation_factor: int=1,
    use_long_video: bool=True,
    **kwargs: Any
) -> Pose2VideoPipelineOutput

Using an audio file, draw fps face pose images per second for the duration of the audio. Then, using those face pose images, render a video.

  • Optionally include a list of images to extract the poses from prior to merging with audio-generated poses (in essence, pass a video here to control non-speech motion). The default is a moderately active loop of head movement.
  • Optionally pass width/height to modify the size. Defaults to reference image size.
  • Optionally pass use_long_video = false to disable using the long video pipeline.
  • Optionally pass reference_pose_image to designate the pose of reference_image. When not passed, the pose of reference_image is automatically detected.
  • Optionally pass video_length to use this many frames. Default is the same as the length of the pose reference images.

Internals/Helpers

img2pose 

pipeline.img2pose(
    reference_image: PIL.Image.Image,
    width: Optional[int]=None,
    height: Optional[int]=None
) -> PIL.Image.Image

Detects face landmarks in an image and draws a face pose image.

  • Optionally modify the original width and height.

vid2pose 

pipeline.vid2pose(
    reference_image: PIL.Image.Image,
    retarget_image: Optional[PIL.Image.Image],
    width: Optional[int]=None,
    height: Optional[int]=None
) -> List[PIL.Image.Image]

Detects face landmarks in a series of images and draws pose images.

  • Optionally modify the original width and height.
  • Optionally retarget to a different face position, useful for video-to-video tasks.

audio2pose 

pipeline.audio2pose(
    audio_path: str,
    fps: int=30,
    reference_image: Optional[PIL.Image.Image]=None,
    pose_reference_images: Optional[List[PIL.Image.Image]]=None,
    width: Optional[int]=None,
    height: Optional[int]=None
) -> List[PIL.Image.Image]

Using an audio file, draw fps face pose images per second for the duration of the audio.

  • Optionally include a reference image to extract the face shape and initial position from. Default has a generic androgynous face shape.
  • Optionally include a list of images to extract the poses from prior to merging with audio-generated poses (in essence, pass a video here to control non-speech motion). The default is a moderately active loop of head movement.
  • Optionally pass width/height to modify the size. Defaults to reference image size, then pose image sizes, then 256.

pose2img 

pipeline.pose2img(
    reference_image: PIL.Image.Image,
    pose_image: PIL.Image.Image,
    num_inference_steps: int,
    guidance_scale: float,
    eta: float=0.0,
    reference_pose_image: Optional[Image.Image]=None,
    generation: Optional[Union[torch.Generator, List[torch.Generator]]]=None,
    output_type: Optional[str]="pil",
    return_dict: bool=True,
    callback: Optional[Callable[[int, int, torch.FloatTensor], None]]=None,
    callback_steps: Optional[int]=None,
    width: Optional[int]=None,
    height: Optional[int]=None,
    **kwargs: Any
) -> Pose2VideoPipelineOutput

Using a reference image (for structure) and a pose image (for pose), render an image of the former in the pose of the latter.

  • The pose image here is a processed face pose. To pass a non-processed face pose, see img2img.
  • Optionally pass reference_pose_image to designate the pose of reference_image. When not passed, the pose of reference_image is automatically detected.

pose2vid 

pipeline.pose2vid(
    reference_image: PIL.Image.Image,
    pose_images: List[PIL.Image.Image],
    num_inference_steps: int,
    guidance_scale: float,
    eta: float=0.0,
    reference_pose_image: Optional[Image.Image]=None,
    generation: Optional[Union[torch.Generator, List[torch.Generator]]]=None,
    output_type: Optional[str]="pil",
    return_dict: bool=True,
    callback: Optional[Callable[[int, int, torch.FloatTensor], None]]=None,
    callback_steps: Optional[int]=None,
    width: Optional[int]=None,
    height: Optional[int]=None,
    video_length: Optional[int]=None,
    **kwargs: Any
) -> Pose2VideoPipelineOutput

Using a reference image (for structure) and pose images (for pose), render a video of the former in the poses of the latter.

  • The pose images here are a processed face poses. To non-processed face poses, see vid2vid.
  • Optionally pass reference_pose_image to designate the pose of reference_image. When not passed, the pose of reference_image is automatically detected.
  • Optionally pass video_length to use this many frames. Default is the same as the length of the pose images.

pose2vid_long 

pipeline.pose2vid_long(
    reference_image: PIL.Image.Image,
    pose_images: List[PIL.Image.Image],
    num_inference_steps: int,
    guidance_scale: float,
    eta: float=0.0,
    reference_pose_image: Optional[Image.Image]=None,
    generation: Optional[Union[torch.Generator, List[torch.Generator]]]=None,
    output_type: Optional[str]="pil",
    return_dict: bool=True,
    callback: Optional[Callable[[int, int, torch.FloatTensor], None]]=None,
    callback_steps: Optional[int]=None,
    width: Optional[int]=None,
    height: Optional[int]=None,
    video_length: Optional[int]=None,
    context_schedule: str="uniform",
    context_frames: int=16,
    context_overlap: int=4,
    context_batch_size: int=1,
    interpolation_factor: int=1,
    **kwargs: Any
) -> Pose2VideoPipelineOutput

Using a reference image (for structure) and pose images (for pose), render a video of the former in the poses of the latter, using context windowing for long-video generation.

  • The pose images here are a processed face poses. To non-processed face poses, see vid2vid.
  • Optionally pass reference_pose_image to designate the pose of reference_image. When not passed, the pose of reference_image is automatically detected.
  • Optionally pass video_length to use this many frames. Default is the same as the length of the pose images.