lcysyzxdxc/AGIQA-3k-Database

[IEEE TCSVT2023] A Fine-grained Subjective Perception & Alignment Database for AI Generated Image Quality Assessment

28
/ 100
Experimental

This project helps researchers and developers evaluate the quality of AI-generated images (AGIs). It provides a comprehensive database of AGIs, along with subjective quality scores from human perception and how well the images align with their original text prompts. The end-user is typically someone who designs or works with AI image generation models and needs to benchmark their output against human judgment.

No commits in the last 6 months.

Use this if you are developing or evaluating text-to-image generative AI models and need a robust dataset of human-rated image quality and prompt alignment to improve your models.

Not ideal if you are a casual user looking for a simple tool to rate individual AI-generated images without needing extensive research data.

AI image generation image quality assessment model evaluation generative AI research text-to-image alignment
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

69

Forks

2

Language

License

MIT

Last pushed

Oct 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/lcysyzxdxc/AGIQA-3k-Database"

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