|
|
--- |
|
|
language: en |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- image-classification |
|
|
- ai-detection |
|
|
- sdxl |
|
|
- vision-transformer |
|
|
- fake-detection |
|
|
datasets: |
|
|
- huggan/wikiart |
|
|
- ash12321/sdxl-generated-10k |
|
|
metrics: |
|
|
- accuracy |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
model-index: |
|
|
- name: SDXL Detector ViT |
|
|
results: |
|
|
- task: |
|
|
type: image-classification |
|
|
name: AI Image Detection |
|
|
metrics: |
|
|
- type: accuracy |
|
|
value: 0.9960 |
|
|
name: Test Accuracy |
|
|
- type: f1 |
|
|
value: 0.9960 |
|
|
name: F1 Score |
|
|
--- |
|
|
|
|
|
# SDXL Detector - Vision Transformer |
|
|
|
|
|
## Model Description |
|
|
|
|
|
This model is a **specialized binary classifier** trained to detect images generated by **Stable Diffusion XL (SDXL)**. It achieves **99.60% accuracy** on held-out test data. |
|
|
|
|
|
### Key Features |
|
|
|
|
|
- 🎯 **Specialist Detector**: Optimized specifically for SDXL-generated images |
|
|
- 🚀 **High Accuracy**: 99.60% test accuracy |
|
|
- ⚡ **Fast Inference**: ~10ms per image on GPU |
|
|
- 🛡️ **Robust**: Trained with 6-layer overfitting prevention |
|
|
- 📊 **Well-Validated**: Separate train/val/test splits with no overlap |
|
|
|
|
|
### Performance |
|
|
|
|
|
``` |
|
|
Test Accuracy: 0.9960 |
|
|
Precision: 0.9930 |
|
|
Recall: 0.9990 |
|
|
F1 Score: 0.9960 |
|
|
AUC-ROC: 0.9999 |
|
|
|
|
|
False Positive Rate: 0.0070 |
|
|
False Negative Rate: 0.0010 |
|
|
``` |
|
|
|
|
|
## Quick Start |
|
|
|
|
|
```python |
|
|
import torch |
|
|
from PIL import Image |
|
|
from transformers import ViTForImageClassification, ViTImageProcessor |
|
|
|
|
|
# Load model and processor |
|
|
model = ViTForImageClassification.from_pretrained( |
|
|
"ash12321/sdxl-detector-vit" |
|
|
) |
|
|
processor = ViTImageProcessor.from_pretrained( |
|
|
"google/vit-base-patch16-224" |
|
|
) |
|
|
|
|
|
# Load image |
|
|
image = Image.open("test.jpg") |
|
|
inputs = processor(images=image, return_tensors="pt") |
|
|
|
|
|
# Get prediction |
|
|
model.eval() |
|
|
with torch.no_grad(): |
|
|
outputs = model(**inputs) |
|
|
probs = torch.softmax(outputs.logits, dim=1) |
|
|
|
|
|
if probs[0][1] > 0.5: |
|
|
print(f"SDXL-Generated ({probs[0][1]:.2%} confident)") |
|
|
else: |
|
|
print(f"Real Image ({probs[0][0]:.2%} confident)") |
|
|
``` |
|
|
|
|
|
## Using the model.py Helper |
|
|
|
|
|
```python |
|
|
from model import detect_image |
|
|
|
|
|
result = detect_image("test.jpg", model_path="ash12321/sdxl-detector-vit") |
|
|
print(f"Is Fake: {result['is_fake']}") |
|
|
print(f"Confidence: {result['confidence']:.2%}") |
|
|
``` |
|
|
|
|
|
## Files in this Repository |
|
|
|
|
|
- `pytorch_model.bin` - Model weights |
|
|
- `config.json` - Model configuration |
|
|
- `model.py` - Model architecture and helper functions |
|
|
- `README.md` - This documentation |
|
|
- `training_results.json` - Detailed training metrics |
|
|
- `training_curves.png` - Training visualization |
|
|
- `confusion_matrix.png` - Test set confusion matrix |
|
|
|
|
|
## Citation |
|
|
|
|
|
```bibtex |
|
|
@misc{sdxl-detector-vit, |
|
|
author = {ash12321}, |
|
|
title = {SDXL Detector - Vision Transformer}, |
|
|
year = {2024}, |
|
|
publisher = {HuggingFace}, |
|
|
howpublished = {\url{https://huggingface.co/ash12321/sdxl-detector-vit}}, |
|
|
} |
|
|
``` |
|
|
|
|
|
--- |
|
|
|
|
|
**License**: Apache 2.0 |
|
|
**Created**: 2025-12-31 |
|
|
|
