ai-forever
/

Kandinsky_2.0

latent diffusion

Model card Files Files and versions Community

Kandinsky_2.0 / README.md

sberbank-ai

Update README.md

0b06d3c over 1 year ago

|

raw history blame

No virus

1.22 kB

	---
	license: apache-2.0
	tags:
	- Kandinsky
	- text-image
	- text2image
	- diffusion
	- latent diffusion
	- mCLIP-XLMR
	- mT5
	---

	# Kandinsky 2.0
	Kandinsky 2.0 — the first multilingual latent diffusion text2image model.

	UNet size: 1.2B 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 (344M parameters)
	* mT5-small (300M parameters)


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

	![header.png](https://s3.amazonaws.com/moonup/production/uploads/1669132825912-5f91b1208a61a359f44e1851.png)

	# Authors

	+ Arseniy Shakhmatov: [Github](https://github.com/cene555), [Blog](https://t.me/gradientdip)
	+ Anton Razzhigaev: [Github](https://github.com/razzant), [Blog](https://t.me/abstractDL)
	+ Aleksandr Nikolich: [Github](https://github.com/AlexWortega)
	+ Vladimir Arkhipkin: [Github](https://github.com/oriBetelgeuse)
	+ Igor Pavlov: [Github](https://github.com/boomb0om)
	+ Andrey Kuznetsov: [Github](https://github.com/kuznetsoffandrey)
	+ Denis Dimitrov: [Github](https://github.com/denndimitrov)