FireRedTeam/PhotoPoster

To support and further the research in the field of portrait animation , we are excited to launch PhotoPoster, an open project for pose-driven image generation.

29
/ 100
Experimental

Implements a two-stage diffusion pipeline combining pose-guided generation with specialized hand restoration using ControlNet inpainting, built on Stable Diffusion 1.5 and MMPose keypoint detection. Includes a FastAPI pose server for efficient keypoint extraction via RTMPose/DWPose and supports distributed inference across multiple GPUs for scalable batch processing. Integrates with Hugging Face model hub and plans ComfyUI support alongside a complementary image-to-video project (DynamicPose).

226 stars. No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

226

Forks

14

Language

Python

License

Last pushed

Aug 26, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/FireRedTeam/PhotoPoster"

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