Kandinsky 3.0

[trouble-maker007]

Model/Pipeline/Scheduler description

Kandinsky 3.0 is an open-source text-to-image diffusion model built upon the Kandinsky2-x model family.

Open source status

• The model implementation is available.
• The model weights are available (Only relevant if addition is not a scheduler).

Provide useful links for the implementation

github:https://github.com/ai-forever/Kandinsky-3
model weights:https://huggingface.co/kandinsky-community/kandinsky-3

[shauray8]

#5913

[sayakpaul]

Closing because of #5913