Richard
Richard Adjunct Assistant Professor, Department of Electrical Engineering, National Taiwan Ocean University, Taiwan.

LivePortrait

LivePortrait

LivePortrait 讓靜態人物照片具有生動表情

論文首頁

Paper: LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control

Pipeline of the first stage: base model training.
Pipeline of the second stage: stitching and retargeting modules training.

Github

1) 安裝與複製程式碼
sudo apt install ffmpeg

1
2
3
4
5
6
7
8
9

git clone https://github.com/KwaiVGI/LivePortrait
cd LivePortrait

# create env using conda
conda create -n LivePortrait 
conda activate LivePortrait

# install dependencies
pip install -r requirements.txt

2) 下載預訓練模型

1
2
3
4
5
6

# first, ensure git-lfs is installed, see: https://docs.github.com/en/repositories/working-with-files/managing-large-files/installing-git-large-file-storage
git lfs install
# clone and move the weights
git clone https://huggingface.co/KwaiVGI/LivePortrait temp_pretrained_weights
mv temp_pretrained_weights/* pretrained_weights/
rm -rf temp_pretrained_weights

3) 執行

  • 輸入來源是照片（512x512 大頭照）, 驅動短片是d0.mp4 (頭像與語音） 
    1

    python inference.py -s assets/examples/source/s9.jpg -d assets/examples/driving/d0.mp4
  • 輸入來源是影片, 驅動短片是d0.mp4 (頭像與語音） 
    1

    python inference.py -s assets/examples/source/s13.mp4 -d assets/examples/driving/d0.mp4

應用平台

python app.py

http://127.0.0.1:8890

展示影片

comments powered by Disqus