quaranji/ComfyUI-AniPortrait

ComfyUI-AniPortrait

Thanks to the contribution from WainWong, the support for the new version of diffusers is now available.

1. base workflow

https://github.com/chaojie/ComfyUI-AniPortrait/blob/main/wf.json

Installation

Build environment

We recommend a python version >=3.10 and cuda version =11.7. Then build environment as follows:

pip install -r requirements.txt

Download weights

1. Download our trained weights, which include five parts: denoising_unet.pth, reference_unet.pth, pose_guider.pth, motion_module.pth and audio2mesh.pt.

2. Download pretrained weight of based models and other components:

   • StableDiffusion V1.5
   • sd-vae-ft-mse
   • image_encoder
   • wav2vec2-base-960h

3. Enter the appropriate path in the node

AniPortrait