ai-forever/ru-dalle

Generate images from texts. In Russian

41
/ 100
Emerging

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.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 22 / 25

How are scores calculated?

Stars

1,649

Forks

245

Language

Jupyter Notebook

License

Apache-2.0

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.