muzishen/RCDMs

[AAAI 2025] 🎬RCDMs🎬: Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models. RCDMs improve story generation with strong semantic and temporal consistency, integrating rich contextual conditions and enabling one-pass inference for enhanced coherence.

25
/ 100
Experimental

This project helps creators like game developers or comic artists generate consistent visual stories. You provide a series of text descriptions (captions) and possibly some reference images for an initial scene. It then outputs a sequence of images that depict the narrative, maintaining both semantic meaning and visual style across all frames. This tool is for anyone who needs to quickly visualize a multi-scene narrative while ensuring visual coherence.

120 stars. No commits in the last 6 months.

Use this if you need to create a visual sequence from text descriptions where maintaining consistent characters, styles, and environments across multiple frames is crucial.

Not ideal if you only need to generate single, standalone images from text, or if you require extremely precise control over every minute detail of each frame.

game-development comic-drawing storytelling visual-narrative content-creation
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

120

Forks

3

Language

Python

License

Last pushed

Sep 30, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/muzishen/RCDMs"

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