rudalle-Malevich / README.md
ai-forever's picture
Create README.md
42dabc6
|
raw
history blame
1.19 kB
metadata
language:
  - ru
tags:
  - PyTorch
  - Transformers
thumbnail: https://github.com/sberbank-ai/ru-dalle

ruDALL-E Malevich (XL)

Generate images from text

* [Technical Report (Russian)](https://habr.ru/) * [Demo](https://rudalle.ru)

Model was trained by Sber AI and SberDevices teams.

  • Task: text2image generation
  • Type: encoder-decoder
  • Num Parameters: 1.3 B
  • Training Data Volume 120 million text-image pairs

Model Description

This is a 1.3 billion parameter model for Russian, recreating OpenAI's DALL·E, a model capable of generating arbitrary images from a text prompt that describes the desired result.

The generation pipeline includes ruDALL-E, ruCLIP for ranging results, and a superresolution model.

How to Use

The easiest way to get familiar with the code and the models is to follow the inference notebook we provide in our github repo.