- Fix frame shape bug in inference.py line 216 (use ori_frame instead of frame)
- Adjust upper_boundary_ratio from 0.5 to 0.4 for better facial blending
- Add MuseTalk API server with multiple versions
- Add inference configs and helper scripts
- Update .gitignore for conda environments
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
feat: data preprocessing and training (#294)
Zhizhou Zhong
Unverified signature
f0d6854
* docs: update readme
* docs: update readme
* feat: training codes
* feat: data preprocess
* docs: release training