- Updated the base image to NVIDIA CUDA 12.0.1 and installed essential system packages.
- Upgraded pip and installed required Python libraries from requirements.txt.
- Set the Asia/Tokyo timezone and specified the working directory to /LivePortrait.
- Enhanced the README with Docker Compose setup instructions and added a link to the Japanese documentation, improving accessibility and usability for both English and Japanese speaking users.
- Detailed the LivePortrait project's features, setup instructions, and recent updates in Japanese to provide guidance and context to the Japanese-speaking users.
- Listed all necessary Python libraries including PyTorch, OpenCV, and other multimedia and data processing libraries to ensure compatibility and functionality of the LivePortrait project.
- Introduced a Dockerfile based on NVIDIA CUDA and Ubuntu with essential packages and Python dependencies for the LivePortrait application. Ensured the system is prepared for high-performance operations with GPU support.
- Configured Docker Compose with NVIDIA GPU support and necessary resources. Deployed a Python application, exposing it on port 8890. This allows for easy setup and scalability of the LivePortrait project.
The crop configuration parameters in `crop_config.py` have been updated. The changes include:
- Updating the paths for insightface_root and landmark_ckpt_path
These changes aim to improve the cropping functionality of the application.
