ali-vilab/IDEA-Bench

Official repository of IDEA-Bench

29
/ 100
Experimental

This project helps professional designers and graphic artists assess how well AI image generation models perform on real-world design tasks. It takes text prompts or existing images as input and evaluates the generated visuals based on criteria like aesthetic quality and contextual relevance, providing objective scores that show how close AI-generated designs are to professional standards.

No commits in the last 6 months.

Use this if you are a professional designer, graphic artist, or researcher who needs to rigorously evaluate and compare the performance of different AI image generation models for complex design workflows.

Not ideal if you are looking for an image generation tool to create designs directly, rather than a benchmark for evaluating AI models.

graphic-design digital-art AI-evaluation image-generation creative-workflow
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

39

Forks

2

Language

Python

License

Last pushed

Jan 24, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ali-vilab/IDEA-Bench"

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