Tencent/MimicMotion

High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance

51
/ 100
Established

Leverages confidence-weighted pose estimation (DWPose) to guide diffusion-based video generation while mitigating artifacts through regional loss amplification, and implements progressive latent fusion to synthesize arbitrary-length videos (up to 72 frames) efficiently. Built on Stable Video Diffusion with a custom U-Net architecture, it targets PyTorch 2.x environments and integrates Hugging Face model checkpoints for streamlined deployment.

2,546 stars.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

2,546

Forks

227

Language

Python

License

Last pushed

Nov 18, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Tencent/MimicMotion"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.