sahsaeedi/DCPO-T2I

[TMLR] Dual Caption Preference Optimization

21
/ 100
Experimental

This project helps AI researchers and practitioners improve the quality of text-to-image diffusion models. By feeding it datasets of preferred and less-preferred image-caption pairs, it trains a model that generates images more aligned with user preferences. This tool is for those who are fine-tuning or developing new image generation models.

No commits in the last 6 months.

Use this if you are developing or fine-tuning diffusion models and want to optimize them to produce images that better match human preferences for given captions.

Not ideal if you are an end-user simply looking to generate images; this is a tool for model developers, not a user-facing image generation application.

AI research diffusion models generative AI image generation model fine-tuning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

Python

License

MIT

Last pushed

Feb 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/sahsaeedi/DCPO-T2I"

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