Replies: 4 comments
-
|
Kandinsky 2.1 inherits best practicies from Dall-E 2 and Latent diffucion, 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: Text encoder (XLM-Roberta-Large-Vit-L-14) - 560M |
Beta Was this translation helpful? Give feedback.
-
Beta Was this translation helpful? Give feedback.
-
|
Is there a way to train it and anyone know if it would work with Loras? |
Beta Was this translation helpful? Give feedback.
-
|
Is there any update on this? |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
Ability to write Prompt in more than 100 languages.
Kandinsky 2.0
https://github.com/ai-forever/Kandinsky-2.0
https://huggingface.co/sberbank-ai/Kandinsky_2.0
https://fusionbrain.ai/diffusion
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.
Kandinsky 2.0 architecture overview:
Beta Was this translation helpful? Give feedback.
All reactions