Awesome
AdvancedLivePortrait-WebUI
Dedicated gradio based WebUI started from ComfyUI-AdvancedLivePortrait. <br>You can edit the facial expression from the image.
https://github.com/user-attachments/assets/cce42397-e898-4efb-9de8-735e050a10ce
Notebook
You can try it in Colab
Installation And Running
Prerequisite
3.9
<=python
<=3.12
: https://www.python.org/downloads/release/python-3110/- (Opitonal, only if you're using Nvidia GPU) CUDA 12.4 : https://developer.nvidia.com/cuda-12-4-0-download-archive?target_os=Windows
- (Optional, only needed if you use Video Driven)
FFmpeg
: https://ffmpeg.org/download.html <br> After installingFFmpeg
, make sure to add the FFmpeg/bin folder to your system PATH!
Run Locally
- git clone this repository
git clone https://github.com/jhj0517/AdvancedLivePortrait-WebUI.git
- Install dependencies ( Use
requirements-cpu.txt
if you're not using Nvidia GPU. )
pip install -r requirements.txt
- Run app
python app.py
Run with PowerShell
There're PowerShell scripts for each purpose : Install.ps1
, Start-WebUI.ps1
and Update.ps1
.
<br> They do the same things as above with venv
, creating, activating venv
and running the app etc.
If you're using Windows, right-click the script and then click on Run with PowerShell.
Run with Docker
- git clone this repository
git clone https://github.com/jhj0517/AdvancedLivePortrait-WebUI.git
- Build the image
docker compose -f docker/docker-compose.yaml build
- Run the container
docker compose -f docker/docker-compose.yaml up
- Connect to
http://localhost:7860/
in browser.
Update the docker-compose.yaml
to match your environment if you're not using an Nvidia GPU.
🌐 Translation
Any PRs for language translation for translation.yaml
would be greatly appreciated!
❤️ Acknowledgement
- LivePortrait paper comes from
@article{guo2024liveportrait,
title = {LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control},
author = {Guo, Jianzhu and Zhang, Dingyun and Liu, Xiaoqiang and Zhong, Zhizhou and Zhang, Yuan and Wan, Pengfei and Zhang, Di},
journal = {arXiv preprint arXiv:2407.03168},
year = {2024}
}
- The models are safetensors that have been converted by kijai. : https://github.com/kijai/ComfyUI-LivePortraitKJ
- ultralytics is used to detect the face.
- This WebUI is started from ComfyUI-AdvancedLivePortrait, various facial expressions like AAA, EEE, Eyebrow, Wink are found by PowerHouseMan.
- RealESRGAN is used for image restoration.