[Feature Request]: add Kandinsky 2.0 - the first multilingual text2image model

[0-NiK-0]

Is there an existing issue for this?

• [X] I have searched the existing issues and checked the recent builds/commits

What would your feature do ?

Kandinsky 2.0 - the first multilingual text2image model. https://github.com/ai-forever/Kandinsky-2.0 https://huggingface.co/sberbank-ai/Kandinsky_2.0

Model architecture: It is a latent diffusion model with two multilingual text encoders:

mCLIP-XLMR 560M parameters mT5-encoder-small 146M parameters These encoders and multilingual training datasets unveil the real multilingual text-to-image generation experience!

Kandinsky 2.0 was trained on a large 1B multilingual set, including samples that we used to train Kandinsky.

In terms of diffusion architecture Kandinsky 2.0 implements UNet with 1.2B parameters.

Proposed workflow

Ability to write Prompt in more than 100 languages.

Additional information

No response

[user425846]

Is there any update on this?

[DenkingOfficial]

Is there any update on this?

No, as you can see last repo update was 3 weeks ago

[morizk]

anyone have a roadmap to do that? I can help.