Home Projects MagicTime
MagicTime
Python

MagicTime

[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

by PKU-YuanGroup · GitHub
Stars
Forks
License
Created
Last commit
Language
diffusion-modelslong-video-generationmetamorphic-video-generationApache-2.0Python
View on GitHub
In plain words

Generate time-lapse videos that simulate real-world scenarios based on your prompts.

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 →
MagicTime — GitHub preview card
📈 Star history
1 3411 340
2026-07-202026-08-31
📈 Track MagicTime

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

[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

MagicTime has 1.3k stars on GitHub. It has been forked 123 times. MagicTime is written mainly in Python. It has been in active development since 2024. MagicTime is available under the Apache-2.0 license. Its main topics are diffusion-models, long-video-generation, metamorphic-video-generation, open-sora-plan.

Frequently asked questions

What is MagicTime?

[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

Is MagicTime open source?

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

Is MagicTime free?

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

What license does MagicTime use?

MagicTime is available under the Apache-2.0 license.

What language is MagicTime written in?

MagicTime is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — MagicTime

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

[![olud.ai](https://olud.ai/badge.php?tool=pku-yuangroup-magictime)](https://olud.ai/project/pku-yuangroup-magictime.html)
More badge options →
🧬 Shares DNA with

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