|
--- |
|
language: |
|
- ru |
|
- en |
|
pipeline_tag: text-to-image |
|
tags: |
|
- PyTorch |
|
- Transformers |
|
thumbnail: "https://github.com/sberbank-ai/ru-dalle" |
|
|
|
--- |
|
# ruDALL-E Malevich (XL) |
|
## Generate images from text |
|
|
|
<img style="text-align:center; display:block;" src="https://huggingface.co/sberbank-ai/rudalle-Malevich/resolve/main/dalle-malevich.jpg" width="200"> |
|
"Avocado painting in the style of Malevich" |
|
|
|
* [Technical Report (Russian)](https://habr.com/ru/company/sberbank/blog/586926) |
|
* [Demo](https://rudalle.ru) |
|
|
|
Model was trained by [Sber AI](https://github.com/sberbank-ai) and [SberDevices](https://sberdevices.ru/) 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](https://openai.com/blog/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. |
|
You can use automatic translation into Russian to create desired images with ruDALL-E. |
|
|
|
### 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](https://huggingface.co/sberbank-ai/rudalle-Malevich). |
|
|
|
|
