README.md

---
license: mit
pipeline_tag: image-classification
---

# 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](https://huggingface.co/papers/2512.12982).

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](https://github.com/UltraCapture/GAPL).

## Motivation

![Motivation Framework](https://github.com/UltraCapture/GAPL/raw/main/assets/overview.jpg)
<p align="center"><em>Figure 1: Overview of our proposed Generator-Aware Prototype Learning (GAPL) framework.</em></p>

## Quick Inference

To run inference on a single image to detect whether it is **Real** or **Fake**, use the following Python code:

```python
python inference.py \
  --model_path pretrained/checkpoint.pt \
  --image_path assets/test_image.jpg \
  --device cuda
```

**Output Example:**

```text
[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:

```bibtex
@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](https://github.com/peterwang512/CNNDetection)**
- **[Community Forensics](https://github.com/JeongsooP/Community-Forensics)** We leverage the dataset and borrow some code from this codebase.