https://github.com/frankchieng/ComfyUI_Aniportrait
Unofficial implementation of AniPortrait custom node in ComfyUI
https://github.com/frankchieng/ComfyUI_Aniportrait
comfyui comfyui-nodes comfyui-workflow
Last synced: about 2 months ago
JSON representation
Unofficial implementation of AniPortrait custom node in ComfyUI
- Host: GitHub
- URL: https://github.com/frankchieng/ComfyUI_Aniportrait
- Owner: frankchieng
- Created: 2024-04-01T06:52:26.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-09-13T10:41:16.000Z (about 1 year ago)
- Last Synced: 2024-09-14T00:26:40.302Z (about 1 year ago)
- Topics: comfyui, comfyui-nodes, comfyui-workflow
- Language: Python
- Homepage:
- Size: 32.2 MB
- Stars: 51
- Watchers: 1
- Forks: 9
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-comfyui - **ComfyUI_Aniportrait** - Yang/AniPortrait) generating of videos, includes self driven, face reenacment and audio driven with a reference image (Workflows (3207) sorted by GitHub Stars)
- awesome-comfyui - **ComfyUI_Aniportrait** - Yang/AniPortrait) generating of videos, includes self driven, face reenacment and audio driven with a reference image (Workflows (2905) sorted by GitHub Stars)
- awesome-comfyui - **ComfyUI_Aniportrait** - Yang/AniPortrait) generating of videos, includes self driven, face reenacment and audio driven with a reference image (All Workflows Sorted by GitHub Stars)
README
#### Updates:
① Implement the frame_interpolation to speed up generation
② Modify the current code and support chain with the [VHS nodes](https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite), i just found that comfyUI IMAGE type requires the torch float32 datatype, and AniPortrait heavily used numpy of image unit8 datatype,so i just changed my mind from my own image/video upload and generation nodes to the prevelance SOTA VHS image/video upload and video combined nodes,it WYSIWYG and inteactive well and instantly render the result
- ✅ [2024/04/09] raw video to pose video with reference image(aka self-driven)
- ✅ [2024/04/09] audio driven
- ✅ [2024/04/09] face reenacment
- ✅ [2024/04/22] implement audio2pose model and [pre-trained weight](https://huggingface.co/ZJYang/AniPortrait/tree/main) for audio2video,the face reenacment and audio2video workflow has been modified, currently inference up to a maximum length of 10 seconds has been supported,you can experiment with the length hyperparameter.
U can contact me thr [twitter](https://twitter.com/kurtqian)  Weixin：GalaticKing
### audio driven combined with reference image and reference video
[audio2video workflow](https://github.com/frankchieng/ComfyUI_Aniportrait/blob/main/assets/audio2video_workflow.json)
### raw video to pose video with reference image
### face reenacment
[video2video workflow](https://github.com/frankchieng/ComfyUI_Aniportrait/blob/main/assets/face_reenacment_workflow.json)
This is unofficial implementation of AniPortrait in ComfyUI custom_node,cuz i have routine jobs,so i will update this project when i have time
> [Aniportrait_pose2video.json](https://github.com/frankchieng/ComfyUI_Aniportrait/blob/main/assets/pose2video_workflow.json)
> [Audio driven](https://github.com/frankchieng/ComfyUI_Aniportrait/blob/main/assets/audio2video_workflow.json)
> [face reenacment](https://github.com/frankchieng/ComfyUI_Aniportrait/blob/main/assets/face_reenacment_workflow.json)
you should run
```shell
git clone https://github.com/frankchieng/ComfyUI_Aniportrait.git
```
then run
```shell
pip install -r requirements.txt
```
download the pretrained models
> [StableDiffusion V1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5)
> [sd-vae-ft-mse](https://huggingface.co/stabilityai/sd-vae-ft-mse)
> [image_encoder](https://huggingface.co/lambdalabs/sd-image-variations-diffusers/tree/main/image_encoder)
> [wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h)
download the weights:
> [denoising_unet.pth](https://huggingface.co/ZJYang/AniPortrait/tree/main)
> [reference_unet.pth](https://huggingface.co/ZJYang/AniPortrait/tree/main)
> [pose_guider.pth](https://huggingface.co/ZJYang/AniPortrait/tree/main)
> [motion_module.pth](https://huggingface.co/ZJYang/AniPortrait/tree/main)
> [audio2mesh.pt](https://huggingface.co/ZJYang/AniPortrait/tree/main)
> [audio2pose.pt](https://huggingface.co/ZJYang/AniPortrait/tree/main)
> [film_net_fp16.pt](https://huggingface.co/ZJYang/AniPortrait/tree/main)
```text
./pretrained_model/
|-- image_encoder
| |-- config.json
| `-- pytorch_model.bin
|-- sd-vae-ft-mse
| |-- config.json
| |-- diffusion_pytorch_model.bin
| `-- diffusion_pytorch_model.safetensors
|-- stable-diffusion-v1-5
| |-- feature_extractor
| | `-- preprocessor_config.json
| |-- model_index.json
| |-- unet
| | |-- config.json
| | `-- diffusion_pytorch_model.bin
| `-- v1-inference.yaml
|-- wav2vec2-base-960h
| |-- config.json
| |-- feature_extractor_config.json
| |-- preprocessor_config.json
| |-- pytorch_model.bin
| |-- README.md
| |-- special_tokens_map.json
| |-- tokenizer_config.json
| `-- vocab.json
|-- audio2mesh.pt
|-- audio2pose.pt
|-- denoising_unet.pth
|-- motion_module.pth
|-- pose_guider.pth
|-- reference_unet.pth
|-- film_net_fp16.pt
```
Tips :
The intermediate audio file will be generated and deleted,the raw video to pose video with audio and pose2video mp4 file will be located in the output directory of ComfyUI
the original uploaded mp4 video requires square size like 512x512, otherwise the result will be weird
#### I've updated diffusers from 0.24.x to 0.26.2,so the diffusers/models/embeddings.py classname of PositionNet changed to GLIGENTextBoundingboxProjection and CaptionProjection changed to PixArtAlphaTextProjection,you should pay attention to it and modify the corresponding python files like src/models/transformer_2d.py if you installed the lower version of diffusers