---
title: README
emoji: 🦀
colorFrom: green
colorTo: indigo
sdk: static
pinned: false
---

Welcome to Kandinsky, the multi-lingual image generation model!
Kandinsky was officially released as part of the [Kandinsky-2 repo](https://github.com/ai-forever/Kandinsky-2) by:

- [Arseniy Shakhmatov](https://github.com/cene555)
- [Anton Razzhigaev](https://github.com/razzant)
- [Aleksandr Nikolich](https://github.com/AlexWortega)
- [Igor Pavlov](https://github.com/boomb0om)
- [Andrey Kuznetsov](https://github.com/kuznetsoffandrey)
- [Denis Dimitrov](https://github.com/denndimitrov)

## Kandinsky 2.1

Kandinsky 2.1 includes **three** public checkpoints:

- [Prior](https://huggingface.co/kandinsky-community/kandinsky-2-1-prior): A prior diffusion model mapping text embeddings to image embeddings
- [Text-to-Image / Image-to-Image](https://huggingface.co/kandinsky-community/kandinsky-2-1): A decoding diffusion model mapping image embeddings to images
- [Inpainting](https://huggingface.co/kandinsky-community/kandinsky-2-1-inpaint): A decoding diffusion model mapping image embeddings and masked images to images

## Kandinsky 2.2

Kandinsky 2.2 includes **four** public checkpoints:
- [Prior](https://huggingface.co/kandinsky-community/kandinsky-2-2-prior): A prior diffusion model mapping text embeddings to image embeddings
- [Text-to-Image / Image-to-Image](https://huggingface.co/kandinsky-community/kandinsky-2-2-decoder): A decoding diffusion model mapping image embeddings to images
- [Inpainting](https://huggingface.co/kandinsky-community/kandinsky-2-2-decoder-inpaint): A decoding diffusion model mapping image embeddings and masked images to images
- [controlnet-depth](https://huggingface.co/kandinsky-community/kandinsky-2-2-controlnet-depth): A decoding diffusion model mapping image embedding and additional depth condition to images