Loading…
Loading…
A specialized deep learning model for detecting images generated by Stable Diffusion XL (SDXL) 1.0 at 1024×1024 resolution.
Architecture: ResNet-50 (pretrained on ImageNet, fine-tuned for SDXL detection)
Training Date: December 30, 2025
Purpose: This is a specialist model designed specifically for SDXL 1.0 detection. For general AI image detection across multiple generators, use this as part of an ensemble with other specialist models.
| Metric | Score |
|---|---|
| Accuracy | 99.75% |
| F1 Score | 99.77% |
| Precision | 99.61% |
| Recall | 99.93% |
| AUC-ROC | 0.9999 |
| Average Precision | 0.9999 |
precision recall f1-score support
Real 99.92% 99.55% 99.73% 1,320
Fake 99.61% 99.93% 99.77% 1,536
Out of 2,856 test images:
Detecting images generated by Stable Diffusion XL (SDXL) 1.0 at 1024×1024 resolution.
✅ Detect SDXL 1.0 generated images with 99.75% accuracy
✅ Identify SDXL-specific generation patterns and artifacts
✅ Work with 1024×1024 SDXL outputs
❌ Detect images from other generators (Midjourney, DALL-E, Flux, etc.)
❌ Work reliably on non-1024×1024 resolutions
❌ Detect other Stable Diffusion versions (1.5, 2.1, etc.)
Note: For comprehensive AI image detection across multiple generators, this model should be used as part of an ensemble with other specialist detectors.
All real images were resized to 1024×1024 to match SDXL output dimensions.
Base Model: ResNet-50 (pretrained on ImageNet)
Custom Classifier Head:
Sequential(
Dropout(p=0.3),
Linear(2048 → 512),
BatchNorm1d(512),
ReLU(),
Dropout(p=0.15),
Linear(512 → 2)
)
Input: RGB images resized to 224×224
Output: Binary classification (Real vs SDXL-generated)
pip install torch torchvision pillow huggingface_hub
import torch
from torchvision import transforms
from PIL import Image
from huggingface_hub import hf_hub_download
# Download model
model_path = hf_hub_download(
repo_id="ash12321/sdxl-detector-resnet50",
filename="best.pth"
)
# Load model
checkpoint = torch.load(model_path, map_location='cpu')
# Create model architecture
import torchvision.models as models
import torch.nn as nn
class SDXLDetector(nn.Module):
def __init__(self):
super().__init__()
self.backbone = models.resnet50(pretrained=False)
num_features = self.backbone.fc.in_features
self.backbone.fc = nn.Sequential(
nn.Dropout(p=0.3),
nn.Linear(num_features, 512),
nn.BatchNorm1d(512),
nn.ReLU(inplace=True),
nn.Dropout(p=0.15),
nn.Linear(512, 2)
)
def forward(self, x):
return self.backbone(x)
# Initialize and load weights
model = SDXLDetector()
model.load_state_dict(checkpoint['model_state_dict'])
model.eval()
# Preprocessing
transform = transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize(
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]
)
])
# Predict
image = Image.open("test_image.jpg").convert('RGB')
input_tensor = transform(image).unsqueeze(0)
with torch.no_grad():
outputs = model(input_tensor)
probs = torch.softmax(outputs, dim=1)
prediction = torch.argmax(probs, dim=1).item()
confidence = probs[0][prediction].item()
# Results
labels = ['Real', 'SDXL-generated']
print(f"Prediction: {labels[prediction]}")
print(f"Confidence: {confidence*100:.2f}%")
from torch.utils.data import DataLoader, Dataset
class ImageDataset(Dataset):
def __init__(self, image_paths, transform):
self.image_paths = image_paths
self.transform = transform
def __len__(self):
return len(self.image_paths)
def __getitem__(self, idx):
image = Image.open(self.image_paths[idx]).convert('RGB')
return self.transform(image)
# Create dataset and loader
image_paths = ['image1.jpg', 'image2.jpg', ...]
dataset = ImageDataset(image_paths, transform)
loader = DataLoader(dataset, batch_size=32, num_workers=4)
# Batch inference
predictions = []
confidences = []
model.eval()
with torch.no_grad():
for batch in loader:
outputs = model(batch)
probs = torch.softmax(outputs, dim=1)
preds = torch.argmax(probs, dim=1)
confs = torch.max(probs, dim=1)[0]
predictions.extend(preds.cpu().numpy())
confidences.extend(confs.cpu().numpy())
Generator-Specific: Only trained on SDXL 1.0. Will not reliably detect:
Resolution-Specific: Optimized for 1024×1024 SDXL images. Performance may degrade on:
Dataset Bias: Trained on specific real image categories (food, animals, vehicles, etc.). May perform differently on:
Adversarial Attacks: Not hardened against adversarial perturbations
✅ Content moderation
✅ Academic research
✅ Digital forensics
✅ Media verification
❌ Surveillance without consent
❌ Discrimination or profiling
❌ Bypassing content policies
False Positives (0.45%): Real images misclassified as SDXL-generated
False Negatives (0.07%): SDXL images misclassified as real
This model should be deployed with clear communication to users about:
If you use this model in your research, please cite:
@misc{sdxl_detector_2024,
author = {Your Name},
title = {SDXL Detector: ResNet-50 Fine-tuned for SDXL Detection},
year = {2024},
publisher = {HuggingFace},
howpublished = {\url{https://huggingface.co/ash12321/sdxl-detector-resnet50}},
}
ash12321
For questions or issues, please open an issue on the model repository.
MIT License
Keywords: SDXL detection, AI image detection, fake image detection, deepfake detection, ResNet-50, image classification, computer vision