AI DetectionGPT-Image-2Dataset
GPT-Image-2 in the Wild: A Twitter Dataset of Self-Reported AI-Generated Images from the First Week of Deployment
Kidus Zewde, Simiao Ren, Xingyu Shen, Jenny Wu, Yuchen Zhou, Tommy Duong, Zikang Zhang, Ethan Traister
How to cite
@article{zewde2026gptimage2,
title={GPT-Image-2 in the Wild: A Twitter Dataset of Self-Reported AI-Generated Images from the First Week of Deployment},
author={Zewde, Kidus and Ren, Simiao and Shen, Xingyu and Wu, Jenny and Zhou, Yuchen and Duong, Tommy and Zhang, Zikang and Traister, Ethan},
journal={arXiv preprint arXiv:2604.25370},
year={2026}
}Associated datasets
GPT-Image-2 Twitter Dataset (GPT-image-2.0X)
Self-reported AI-generated images collected from Twitter during the first week of GPT-Image-2 deployment — captures real-world distribution shift.
More from AI-Generated Detection
Try it in production
Scam AI's Eva-v1 model applies this research at production scale — 98.2% accuracy, under 4 seconds, 200 free detections per month.