UCSC-VLAA/story-iter

[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization

58
/ 100
Established

Implements a plug-and-play Global Reference Cross-Attention (GRCA) module that iteratively refines generated frames by incorporating all previous reference images during diffusion denoising, enabling semantic consistency across long sequences (up to 100 frames). Built on SDXL with IP-Adapter integration, the framework operates training-free and supports style control (comic, film, realistic) and ControlNet skeleton guidance for precise character pose management.

949 stars. Actively maintained with 6 commits in the last 30 days.

No Package No Dependents
Maintenance 17 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 22 / 25

How are scores calculated?

Stars

949

Forks

129

Language

Python

License

MIT

Last pushed

Feb 18, 2026

Commits (30d)

6

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/UCSC-VLAA/story-iter"

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