ai-forever
/

Kandinsky_2.0

latent diffusion

Model card Files Files and versions

sberbank-ai commited on Nov 23, 2022

Commit

cabdd47

·

1 Parent(s): 8571353

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -18,7 +18,7 @@ Kandinsky 2.0 — the first multilingual latent diffusion text2image model.
 ![NatallE.png](https://s3.amazonaws.com/moonup/production/uploads/1669132577749-5f91b1208a61a359f44e1851.png)
 It is a latent diffusion model with two multi-lingual text encoders:
-* mCLIP-XLMR (344M parameters)
 * mT5-small (300M parameters)

 ![NatallE.png](https://s3.amazonaws.com/moonup/production/uploads/1669132577749-5f91b1208a61a359f44e1851.png)
 It is a latent diffusion model with two multi-lingual text encoders:
+* mCLIP-XLMR (560M parameters)
 * mT5-small (300M parameters)