Home› Projects› MAGI-1
MAGI-1
Python

MAGI-1

MAGI-1: Autoregressive Video Generation at Scale

by SandAI-org · GitHub
Stars
Forks
License
Created
Last commit
Language
autoregressivediffusion-modelsvideo-generationApache-2.0Python
View on GitHub
In plain words

Generate videos automatically using advanced AI techniques for creative projects.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
MAGI-1 — GitHub preview card
📈 Star history
3.74k3.73k
2026-07-072026-08-31
📈 Track MAGI-1

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

MAGI-1: Autoregressive Video Generation at Scale

MAGI-1 has 3.7k stars on GitHub. It has been forked 238 times. MAGI-1 is written mainly in Python. It has been in active development since 2025. MAGI-1 is available under the Apache-2.0 license. Its main topics are autoregressive, diffusion-models, video-generation.

❓ Frequently asked questions

What is MAGI-1?

MAGI-1: Autoregressive Video Generation at Scale

Is MAGI-1 open source?

MAGI-1 is an open-source project. It is released under the Apache-2.0 license.

Is MAGI-1 free?

Yes. MAGI-1 is free and open source — you can use, modify and self-host it.

What license does MAGI-1 use?

MAGI-1 is available under the Apache-2.0 license.

What language is MAGI-1 written in?

MAGI-1 is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — MAGI-1

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=sandai-org-magi-1)](https://olud.ai/project/sandai-org-magi-1.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →
MimicMotion
High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance
★ 2.6k · diffusion-models
sharesvideo-generationdiffusion-models
PVDM
[CVPR'23] Video Probabilistic Diffusion Models in Projected Latent Space
★ 322 · diffusion-models
sharesvideo-generationdiffusion-models
Awesome-Video-World-Models-with-AR-Diffusion
A Curated List of Awesome Video World Models with AR Diffusion: Covering Algorithms, Applicatio…
★ 698 · ar-diffusion
sharesautoregressivevideo-generation
Pyramid-Flow
[ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling
★ 3.2k · diffusion-models
sharesvideo-generationdiffusion-models
HunyuanVideo
HunyuanVideo: A Systematic Framework For Large Video Generation Model
★ 12.3k · diffusion-models
sharesvideo-generationdiffusion-models
ControlVideo
[ICLR 2024] Official pytorch implementation of "ControlVideo: Training-free Controllable Text-t…
★ 863 · diffusion-models
sharesvideo-generationdiffusion-models
fantasy-portrait
FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusi…
★ 512 · diffusion-models
sharesvideo-generationdiffusion-models
videocomposer
Official repo for VideoComposer: Compositional Video Synthesis with Motion Controllability
★ 958 · diffusion-models
sharesvideo-generationdiffusion-models
OpenDWM
An open source code repository of driving world models, with training, inferencing, evaluation…
★ 405 · autonomous-driving
sharesvideo-generationdiffusion-models
Epona
Official Code for Epona: Autoregressive Diffusion World Model for Autonomous Driving (ICCV 2025…
★ 370 · autonomous-driving
sharesvideo-generationdiffusion-models

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.