Kandinsky text-image text2image diffusion latent diffusion mCLIP-XLMR mT5

Kandinsky 2.1

Open In Colab

GitHub repository

Habr post

Demo

Architecture

Kandinsky 2.1 inherits best practicies from Dall-E 2 and Latent diffusion, while introducing some new ideas.

As text and image encoder it uses CLIP model and diffusion image prior (mapping) between latent spaces of CLIP modalities. This approach increases the visual performance of the model and unveils new horizons in blending images and text-guided image manipulation.

For diffusion mapping of latent spaces we use transformer with num_layers=20, num_heads=32 and hidden_size=2048.

Other architecture parts:

Authors