X-GenGroup/PaCo-RL

Official Implementation for *PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling*

18
/ 100
Experimental

This project helps content creators and designers generate sequences of images that maintain consistent identities, styles, and logical flow for storytelling or character design. You input a series of prompts, and it generates multiple images that look cohesive and related, rather than disjointed. This is for digital artists, animators, marketers, and storytellers who rely on AI for visual content creation.

Use this if you need to generate a series of images (like for a comic, animation storyboard, or product line) where characters, objects, or styles must remain consistent across all images.

Not ideal if you only need to generate single, standalone images or if you prefer a simpler, less customizable image generation process.

digital-art character-design visual-storytelling content-creation animation-preproduction
No License No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 5 / 25
Community 0 / 25

How are scores calculated?

Stars

32

Forks

Language

Python

License

Last pushed

Dec 13, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/X-GenGroup/PaCo-RL"

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