Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes
This repository contains the model presented in the paper Scaling Up AI-Generated Image Detection via Generator-Aware Prototypes.
GAPL proposes a novel framework to scale up AI-generated image (AIGI) detection by addressing data heterogeneity and model bottlenecks. It learns canonical forgery prototypes and employs a two-stage training scheme with Low-Rank Adaptation to achieve state-of-the-art performance across various GAN and diffusion-based generators.
For more details, including installation and training, please refer to the official GitHub repository.
Motivation
Figure 1: Overview of our proposed Generator-Aware Prototype Learning (GAPL) framework.
Quick Inference
To run inference on a single image to detect whether it is Real or Fake, use the following Python code:
python inference.py \
--model_path pretrained/checkpoint.pt \
--image_path assets/test_image.jpg \
--device cuda
Output Example:
[INFO] Loading model from pretrained/checkpoint.pt...
[RESULT] Image: assets/test_image.jpg
-> Prediction: Fake (AI-Generated)
-> Confidence: 99.8%
Citation
If you find our work useful in your research, please consider citing:
@article{qin2025Scaling,
title={Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes},
author={Qin, Ziheng and Ji, Yuheng and Tao, Renshuai and Tian, Yuxuan and Liu, Yuyang and Wang, Yipu and Zheng, Xiaolong},
journal={arXiv preprint arXiv:2512.12982},
year={2025}
}
Acknowledgements
Our code is developed based on the following excellent open-source repositories. We appreciate their excellent work and contributions to the community:
- CNNDetection
- Community Forensics We leverage the dataset and borrow some code from this codebase.