SandAI-org/MAGI-1
MAGI-1: Autoregressive Video Generation at Scale
MAGI-1 helps creative professionals generate high-quality videos from text descriptions. You provide a text prompt describing the desired scene or action, and it outputs a video that maintains consistent visuals over time. This tool is for video creators, marketers, and content producers who need to quickly prototype or produce video content.
3,663 stars. No commits in the last 6 months.
Use this if you need to generate realistic, temporally consistent videos from text prompts and want fine-grained control over scene transitions and long-duration sequences.
Not ideal if you're looking for a tool to edit existing videos or perform complex video post-production tasks.
Stars
3,663
Forks
235
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/SandAI-org/MAGI-1"
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