Home Projects AdaIN-style
AdaIN-style
Lua

AdaIN-style

Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

by xunhuang1995 · GitHub
Stars
Forks
License
Created
Last commit
Language
deep-learninggenerative-artgenerative-modelMITLua
View on GitHub
In plain words

Transform a single image into an animated scene with zoom and pan effects in real-time.

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 →
AdaIN-style — GitHub preview card
📈 Star history
1 5671 566
2026-07-202026-08-31
📈 Track AdaIN-style

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

Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

AdaIN-style has 1.6k stars on GitHub. It has been forked 199 times. AdaIN-style is written mainly in Lua. It has been in active development since 2017. AdaIN-style is available under the MIT license. Its main topics are deep-learning, generative-art, generative-model, neural-style.

Frequently asked questions

What is AdaIN-style?

Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

Is AdaIN-style open source?

AdaIN-style is an open-source project. It is released under the MIT license.

Is AdaIN-style free?

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

What license does AdaIN-style use?

AdaIN-style is available under the MIT license.

What language is AdaIN-style written in?

AdaIN-style is written mainly in Lua.

🏅 Maintainer of this project?
olud.ai badge — AdaIN-style

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

[![olud.ai](https://olud.ai/badge.php?tool=xunhuang1995-adain-style)](https://olud.ai/project/xunhuang1995-adain-style.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

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