mit-han-lab/radial-attention
[NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation
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.
Stars
587
Forks
33
Language
Python
License
Apache-2.0
Category
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.
Higher-rated alternatives
hao-ai-lab/FastVideo
A unified inference and post-training framework for accelerated video generation.
ModelTC/LightX2V
Light Image Video Generation Inference Framework
thu-ml/TurboDiffusion
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
PKU-YuanGroup/Helios
Helios: Real Real-Time Long Video Generation Model
PKU-YuanGroup/MagicTime
[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators