Comfyui_Liveportrait_v3

🔥 Updates

We support image driven mode and regional control for Comfyui!!! Using a simple way to use an image as a driving signal to drive the source image or video!

Introduction

This repo, named Comfyui_Liveportrait_v3, thanks to paper LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control. We developed a custom_node for Liveportrait_v3 that enables flexible use on Comfyui to drive image-based emoji generation from photos.

Getting Started

1. Clone the code and prepare the environment

git clone https://github.com/VangengLab/Comfyui_Liveportrait_v3.git
cd Comfyui_Liveportrait_v3
pip install -r requirements.txt

Download pretrained weights

The easiest way to download the pretrained weights is from HuggingFace:

cd models/
huggingface-cli download KwaiVGI/LivePortrait --local-dir Liveportrait_v3 --exclude "*.git*" "README.md" "docs"

If you cannot access to Huggingface, you can use hf-mirror to download:

export HF_ENDPOINT=https://hf-mirror.com
huggingface-cli download KwaiVGI/LivePortrait --local-dir pretrained_weights --exclude "*.git*" "README.md" "docs"

You can also manually download the model to the folder from the URL: https://huggingface.co/KwaiVGI/LivePortrait/tree/main, and remember put them to models/Liveportrait_v3

​​

###maybe there will be some problem about locating models,please use the abusolte address,or tell me I will offer you help.