ruDALL-E: Russian Text-to-Image Generation

Category: Computer Vision

License: Apache-2.0

Model Type: Image Generation

ruDALL-E is an open-source text-to-image generation model tailored for the Russian language. It enables users to generate images from Russian text prompts, supporting various model variants and offering capabilities like image upscaling and video generation.

Key Features

Generates images from Russian text prompts.
Supports multiple model variants, including Malevich (XL), Emojich (XL), and Surrealist (XL).
Offers image upscaling and video generation capabilities.
Provides pre-trained models for immediate use.
Compatible with Python and PyTorch frameworks