Hugging Face's logo

ai-forever
/
Kandinsky_2.0

Kandinsky
text-image
text2image
diffusion
latent diffusion
mCLIP-XLMR
mT5
Model card Files Community
6
sberbank-ai commited on
Commit
5d023db
•
1 Parent(s): e9d14ad

Update README.md

Browse files

![NatallE.png](https://s3.amazonaws.com/moonup/production/uploads/1669132577749-5f91b1208a61a359f44e1851.png)

Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -14,7 +14,7 @@ tags:
14
  Kandinsky 2.0 - the first multilingual latent diffusion text2image model.
15
  *UNet size: 1.2B parameters*
16
 
17
- <img src="https://github.com/ai-forever/NATALLE/blob/main/content/NatallE.png"/>
18
 
19
  It is a latent diffusion model with two multi-lingual text encoders:
20
  * mCLIP-XLMR (344M parameters)
 
14
  Kandinsky 2.0 - the first multilingual latent diffusion text2image model.
15
  *UNet size: 1.2B parameters*
16
 
17
+ ![NatallE.png](https://s3.amazonaws.com/moonup/production/uploads/1669132577749-5f91b1208a61a359f44e1851.png)
18
 
19
  It is a latent diffusion model with two multi-lingual text encoders:
20
  * mCLIP-XLMR (344M parameters)