Unofficial implementation of a/hallo for ComfyUI
Unofficial Hallo support for ComfyUI.
This workflow shows the example usage on making an image into a talking face video.
Install from ComfyUI Manager (search for hallo
, make sure ffmpeg
is installed)
Download or git clone this repository into the ComfyUI/custom_nodes/ directory and run:
sudo apt install ffmpeg
pip install -r requirements.txt
## insatll xformers match your torch, for torch==2.1.0+cu121
pip install xformers==0.0.22.post7
All models will be downloaded automatically to ComfyUI's model folder, just no wrries.