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.
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.
Stars
226
Forks
14
Language
Python
License
—
Category
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.
Related models
vuongkiranocode2004/ai-blog-poster
This repo provides a RESTful API for automatically generating SEO-optimized blog posts and...
JuniorTorresMTJ/memorybook
memorybook
open-kbs/ai-banner-maker
AI assistant for creating HTML banners
majestikmagik/Automation_Create_post_Instagram_Facebook
This Make.com scenario automates social media posts by pulling prompts from Google Sheets to...
sk-dev-hub/social-content-generator
AI-генератор постов для соцсетей на Python + Hugging Face