README.md

metadata

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 by:

• Arseniy Shakhmatov
• Anton Razzhigaev
• Aleksandr Nikolich
• Igor Pavlov
• Andrey Kuznetsov
• Denis Dimitrov

Kandinsky 2.1

Kandinsky 2.1 includes three public checkpoints:

• Prior: A prior diffusion model mapping text embeddings to image embeddings
• Text-to-Image / Image-to-Image: A decoding diffusion model mapping image embeddings to images
• Inpainting: A decoding diffusion model mapping image embeddings and masked images to images

Kandinsky 2.2

Kandinsky 2.2 includes four public checkpoints:

• Prior: A prior diffusion model mapping text embeddings to image embeddings
• Text-to-Image / Image-to-Image: A decoding diffusion model mapping image embeddings to images
• Inpainting: A decoding diffusion model mapping image embeddings and masked images to images
• controlnet-depth: A decoding diffusion model mapping image embedding and additional depth condition to images