Edit model card

Kandinsky 2.0

Kandinsky 2.0 β€” the first multilingual text2image model.

Open In Colab

GitHub repository

Habr post


UNet size: 1.2B parameters


It is a latent diffusion model with two multi-lingual text encoders:

  • mCLIP-XLMR (560M parameters)
  • mT5-encoder-small (146M parameters)

These encoders and multilingual training datasets unveil the real multilingual text2image generation experience!


How to use

pip install "git+https://github.com/ai-forever/Kandinsky-2.0.git"

from kandinsky2 import get_kandinsky2
model = get_kandinsky2('cuda', task_type='text2img')
images = model.generate_text2img('кошка в космосС', batch_size=4, h=512, w=512, num_steps=75, denoised_type='dynamic_threshold', dynamic_threshold_v=99.5, sampler='ddim_sampler', ddim_eta=0.01, guidance_scale=10)


Downloads last month


Downloads are not tracked for this model. How to track
Unable to determine this model's library. Check the docs .

Spaces using ai-forever/Kandinsky_2.0 8