ComfyUI Extension: ComfyUI Hallo
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Unofficial implementation of a/hallo for ComfyUI
README
ComfyUI Hallo (Unofficial Support)
Unofficial Hallo support for ComfyUI.
Important Updates
- 2024/07/30: Added support to ComfyUI's official AudioLoad Node
- 2024/06/26: Added ComfyUI nodes and workflow examples
Example Workflow
This workflow shows the example usage on making an image into a talking face video.

Installation
-
Install from ComfyUI Manager (search for
hallo, make sureffmpegis 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
Download Checkpoints
All models will be downloaded automatically to ComfyUI's model folder, just no wrries.
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.