baaivision/URSA
[ICLR 2026] 🐻 Uniform Discrete Diffusion with Metric Path for Video Generation
URSA helps creative professionals generate high-quality images and videos from text descriptions. You provide a prompt describing the visual content you want, and URSA outputs a corresponding image or a moving video clip. This tool is ideal for content creators, designers, and marketers who need to quickly produce visual assets without traditional filming or photography.
107 stars.
Use this if you need to rapidly create custom images or video footage based on textual descriptions for creative projects or marketing campaigns.
Not ideal if you require highly accurate, photorealistic depictions of real-world scenarios or extremely long, complex video sequences.
Stars
107
Forks
2
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 06, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/baaivision/URSA"
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