SadTalker
Audio-driven talking head animation from a single image.
About
SadTalker generates a talking-head video from a single portrait image and an audio clip by predicting 3D motion coefficients that drive natural head movement and lip sync. Decoupling expression and pose from the audio improves realism over earlier single-image methods. The project provides a Colab notebook, a Hugging Face Space, and a Stable Diffusion WebUI extension. Developed at Xi'an Jiaotong University and released under the MIT license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- AI Animation & Motion
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Easy (2/5)
- License
- MIT
- Minimum VRAM
- 6 GB
- Added
- Apr 3, 2026
Related Tools
Real-time high-quality lip-sync model for audio-driven talking face generation.
Realistic human pose and facial expression transfer from video.
Hierarchical audio-driven visual synthesis for portrait animation.
Audio-driven portrait animation with lifelike expressions and head movements.
Virtual human pose generation and animation from images.
Efficient portrait animation framework for stitching and retargeting.