CSU-JPG/TextAtlas

A Large-scale Dataset for training and evaluating model's ability on Dense Text Image Generation

19
/ 100
Experimental

This project provides a large dataset and evaluation tools for assessing how well AI models generate images that include complex, readable text. It takes a model's generated image and a descriptive text prompt, then outputs performance metrics like text accuracy and legibility. It's designed for AI researchers and engineers who are developing or evaluating text-to-image models.

No commits in the last 6 months.

Use this if you are developing or benchmarking AI models that generate images containing dense and accurate text.

Not ideal if you are looking for an off-the-shelf tool to generate images with text, rather than a dataset for model training and evaluation.

AI-model-evaluation text-to-image-generation generative-AI deep-learning-datasets
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

87

Forks

Language

Python

License

Category

gan-based-t2i

Last pushed

Sep 27, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/CSU-JPG/TextAtlas"

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