yandex-research/swd

[ICLR'2026] Scale-wise Distillation of Diffusion Models

41
/ 100
Emerging

This project helps artists, designers, and marketers quickly generate high-quality images from text descriptions. It takes your text prompt, like "Cute winter dragon baby, kawaii, Pixar," and rapidly produces a matching image. The key benefit is speeding up image generation for creative professionals.

117 stars.

Use this if you need to generate realistic or stylized images from text prompts much faster than traditional methods, without sacrificing visual quality.

Not ideal if you require extremely precise control over every pixel or if your primary need is for fine-tuning existing images rather than generating new ones.

AI-art-generation digital-content-creation text-to-image creative-workflow image-synthesis
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

117

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/yandex-research/swd"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.