[CVPR2022] Thin-Plate Spline Motion Model for Image Animation Windows Installation

Source code of the CVPR'2022 paper "Thin-Plate Spline Motion Model for Image Animation"

Paper | Supp

Example animation

Installation

• Install Anaconda

• Open Anaconda Powershell Prompt

• Create Anaconda environment:

conda create --name thin-plate-spline python=3.9

• Download this git and place it anywhere you want on your drive, for exemple : S:\Python\Projects\thin-plate-spline

• Create a folder named checkpoints

• Download pretrained models (pick one link) -- Tsinghua Cloud -- Google Drive

• Unzip all files on your checkpoints directory, for exemple : S:\Python\Projects\thin-plate-spline\checkpoints

• On Anaconda console type :

cd S:\Python\Projects\thin-plate-spline

• To install the dependencies run:

pip install -r requirements.txt

Image animation demo

python demo.py --config config/vox-256.yaml --checkpoint checkpoints/vox.pth.tar --source_image assets/source.png --driving_video assets/driving.mp4

Acknowledgments

The main code is based upon FOMM and MRAA

Thanks for the excellent works!

And Thanks to:

• @chenxwh: Add Web Demo & Docker environment

• @TalkUHulk: The C++/Python demo is provided in Image-Animation-Turbo-Boost

• @AK391: Add huggingface web demo