mit-han-lab/radial-attention

[NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation

45
/ 100
Emerging

This project helps video creators and AI artists generate longer, high-fidelity videos more quickly and efficiently. It takes existing text-to-video models and your prompts, producing extended video sequences. If you work with AI-powered video creation and need to produce longer clips without sacrificing quality or breaking the bank, this tool is designed for you.

587 stars.

Use this if you need to generate high-quality videos that are up to four times longer than what your current text-to-video AI models typically produce, while significantly reducing generation time and computational costs.

Not ideal if your primary need is for short video clips or if you are not currently working with AI-based video generation models.

video-generation AI-art creative-production digital-media content-creation
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 14 / 25

How are scores calculated?

Stars

587

Forks

33

Language

Python

License

Apache-2.0

Last pushed

Nov 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/mit-han-lab/radial-attention"

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