ai-forever/ru-dalle
Generate images from texts. In Russian
Implements a two-stage diffusion architecture with discrete VAE tokenization and autoregressive transformer decoding, optimized for Russian language prompts with multiple model variants (Malevich XL, Emojich, Surrealist, Kandinsky XXL) available on Hugging Face. Includes integrated pipelines for image generation, CLIP-based quality filtering via ruCLIP, super-resolution upscaling, and image-prompt conditioning—all compatible with low-VRAM inference (~3.5GB) and fine-tuning workflows.
1,649 stars. No commits in the last 6 months.
Stars
1,649
Forks
245
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Jan 10, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ai-forever/ru-dalle"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
KR-HappyFace/KoDALLE
🇰🇷 Text to Image in Korean
olaviinha/NeuralTextToImage
Colabs for text prompt steered image generators
j-min/DallEval
DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models (ICCV 2023)
kevinhermawan/Canvas
DALL·E playground for the Mac
simonsanvil/DALL-E-Explained
Description and applications of OpenAI's paper about DALL-E (2021) and implementation of other...