RockeyCoss/SPO

[CVPR 2025] Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization

35
/ 100
Emerging

This project helps artists, designers, and content creators generate more visually appealing images from text prompts. It takes your existing text-to-image diffusion models, like Stable Diffusion, and fine-tunes them to produce higher-quality, aesthetically pleasing images without sacrificing what your text prompt described. The end result is a diffusion model that generates beautiful images more consistently.

265 stars. No commits in the last 6 months.

Use this if you are using text-to-image models and want to consistently generate images that are not just accurate to your prompt but also highly aesthetic and visually refined.

Not ideal if your primary concern is generating images with perfect layout or specific factual correctness rather than general aesthetic quality.

generative-art digital-design content-creation image-synthesis creative-imaging
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

265

Forks

11

Language

Python

License

MIT

Last pushed

Apr 07, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/RockeyCoss/SPO"

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