Extensions/ComfyUI-AniPortrait
ComfyUI Extension

ComfyUI-AniPortrait

ComfyUI a/AniPortrait

By chaojie·Created 2 years ago·Updated 2 years ago· 251
chaojie/ComfyUI-AniPortrait
Nodes5
On cloudLocal install
CategoryAniPortrait
Stars251
Updated2 years ago

Nodes (5)

AniPortraitLoader

The loader that assembles an entire talking-head stack

AniPortrait
AniPortraitRun

This is where your portrait starts talking

AniPortrait
Box2Video

The crop-by-coordinates helper every AniPortrait workflow quietly depends on

AniPortrait
CoverVideo

The paste-back node that finishes every AniPortrait face-swap

AniPortrait
MaskList2Video

Turn any segmentation mask into a padded crop — and the box to paste it back

AniPortrait
Readme

ComfyUI-AniPortrait

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

  1. base workflow
<img src="wf.png" raw=true>

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:

  3. Enter the appropriate path in the node

AniPortrait