Views
No views yet
 |
 |
paper!inference code, config, and pretrained weights!
real-time and streamable diffusion framework capable of generating infinite-length portrait animations on a single 12GB GPU.# clone this repo
git clone https://github.com/GVCLab/PersonaLive
cd PersonaLive
# Create conda environment
conda create -n personalive python=3.10
conda activate personalive
# Install packages with pip
pip install -r requirements_base.txtpython tools/download_weights.py./pretrained_weights folder from one of the below URLs:
pretrained_weights
├── onnx
│ ├── unet_opt
│ │ ├── unet_opt.onnx
│ │ └── unet_opt.onnx.data
│ └── unet
├── personalive
│ ├── denoising_unet.pth
│ ├── motion_encoder.pth
│ ├── motion_extractor.pth
│ ├── pose_guider.pth
│ ├── reference_unet.pth
│ └── temporal_module.pth
├── sd-vae-ft-mse
│ ├── diffusion_pytorch_model.bin
│ └── config.json
├── sd-image-variations-diffusers
│ ├── image_encoder
│ │ ├── pytorch_model.bin
│ │ └── config.json
│ ├── unet
│ │ ├── diffusion_pytorch_model.bin
│ │ └── config.json
│ └── model_index.json
└── tensorrt
└── unet_work.enginepython inference_offline.pypython inference_offline.py --use_xformers False# install Node.js 18+
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.1/install.sh | bash
nvm install 18
cd webcam
source start.sh20 minutes depending on your device. Note that TensorRT optimizations may lead to slight variations or a small drop in output quality.pip install -r requirements_trt.txt
python torch2trt.pyH100. We recommend ALL users (including H100 users) re-run python torch2trt.py locally to ensure best compatibility.python inference_online.py --acceleration none (for RTX 50-Series) or xformers or tensorrthttp://0.0.0.0:7860 in your browser. (*If http://0.0.0.0:7860 does not work well, try http://localhost:7860)
num_frames_needed * 4 or higher) to better match your device's inference speed. https://github.com/GVCLab/PersonaLive/blob/6953d1a8b409f360a3ee1d7325093622b29f1e22/webcam/util.py#L731@article{li2025personalive,
2 title={PersonaLive! Expressive Portrait Image Animation for Live Streaming},
3 author={Li, Zhiyuan and Pun, Chi-Man and Fang, Chen and Wang, Jue and Cun, Xiaodong},
4 journal={arXiv preprint arXiv:2512.11253},
5 year={2025}
6}