Home Projects Kandinsky-2
Kandinsky-2
Jupyter Notebook

Kandinsky-2

Kandinsky 2 — multilingual text2image latent diffusion model

by ai-forever · GitHub
Stars
Forks
License
Created
Last commit
Category
diffusionimage-generationimage2imageApache-2.0Jupyter Notebook
View on GitHub
In plain words

Generate images from text descriptions using a model that understands multiple languages.

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 →
Kandinsky-2 — GitHub preview card
📈 Star history
2.82k2.81k
2026-07-072026-08-31
📈 Track Kandinsky-2

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

Kandinsky 2 — multilingual text2image latent diffusion model

Kandinsky-2 has 2.8k stars on GitHub. It has been forked 317 times. Kandinsky-2 is written mainly in Jupyter Notebook. It has been in active development since 2022. Kandinsky-2 is available under the Apache-2.0 license. Its main topics are diffusion, image-generation, image2image, inpainting.

Frequently asked questions

What is Kandinsky-2?

Kandinsky 2 — multilingual text2image latent diffusion model

Is Kandinsky-2 open source?

Kandinsky-2 is an open-source project. It is released under the Apache-2.0 license.

Is Kandinsky-2 free?

Yes. Kandinsky-2 is free and open source — you can use, modify and self-host it.

What license does Kandinsky-2 use?

Kandinsky-2 is available under the Apache-2.0 license.

What language is Kandinsky-2 written in?

Kandinsky-2 is written mainly in Jupyter Notebook.

🏅 Maintainer of this project?
olud.ai badge — Kandinsky-2

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

[![olud.ai](https://olud.ai/badge.php?tool=ai-forever-kandinsky-2)](https://olud.ai/project/ai-forever-kandinsky-2.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.