CSU-JPG/TextAtlas
A Large-scale Dataset for training and evaluating model's ability on Dense Text Image Generation
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.
Stars
87
Forks
—
Language
Python
License
—
Category
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.
Higher-rated alternatives
Yutong-Zhou-cv/Awesome-Text-to-Image
(ෆ`꒳´ෆ) A Survey on Text-to-Image Generation/Synthesis.
tobran/DF-GAN
[CVPR2022 oral] A Simple and Effective Baseline for Text-to-Image Synthesis
aelnouby/Text-to-Image-Synthesis
Pytorch implementation of Generative Adversarial Text-to-Image Synthesis paper
akanimax/T2F
T2F: text to face generation using Deep Learning
woozzu/tagan
An official PyTorch implementation of the paper "Text-Adaptive Generative Adversarial Networks:...