DWPose
Effective whole-body pose estimation with few-shot keypoint detection.
About
DWPose is a whole-body pose estimation model that detects body, hand, and face keypoints using a two-stage distillation approach for accuracy at a small size. It builds on MMPose and is frequently used as a conditioning signal for ControlNet-driven image and animation generation. Several model sizes from tiny to large are released. Distributed under the Apache 2.0 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
- Apache-2.0
- Minimum VRAM
- 4 GB
- Added
- Apr 3, 2026
Related Tools
Realistic human pose and facial expression transfer from video.
Real-time high-quality lip-sync model for audio-driven talking face generation.
Audio-driven talking head animation from a single image.
Audio-driven portrait animation with lifelike expressions and head movements.
Hierarchical audio-driven visual synthesis for portrait animation.
Accurately lip-sync videos to any audio using a pre-trained model.