UCSC-VLAA/story-iter

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

65
/ 100
Established

This tool helps creative professionals like animators, content creators, or marketers transform long textual narratives into sequences of images. You provide a story broken down into individual text prompts (like scene descriptions), and it generates a series of coherent images or a GIF. This is ideal for anyone needing to visualize stories of up to 100 frames with consistent characters and fine-grained interactions.

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

Use this if you need to create a visual representation of a long story from text, ensuring characters and scenes remain consistent across many frames.

Not ideal if you're looking for a simple, single-image generation from a short prompt or if you're not comfortable with command-line interfaces.

storytelling animation content-creation visual-narrative creative-production
No Package No Dependents
Maintenance 17 / 25
Adoption 10 / 25
Maturity 16 / 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.