Ai Image Detector

🚀 AI Image Detector

This AI Image Detector is a powerful tool designed to distinguish between real and AI - generated images. It leverages the Vision Transformer (ViT) architecture to offer accurate classification results.

🚀 Quick Start

The AI Image Detector can quickly and accurately classify whether an image is real or AI - generated. You can use the provided Python code to start detecting images right away.

✨ Features

• Accurate Classification: Utilizes the Vision Transformer (ViT) architecture for precise image classification.
• Binary Classification: Classifies images into two clear - cut categories: real and AI - generated.
• Confidence Score: Provides a confidence score for each prediction.

💻 Usage Examples

Basic Usage

from transformers import ViTImageProcessor, ViTForImageClassification
from PIL import Image
import torch

# Load the model and processor
processor = ViTImageProcessor.from_pretrained("C:/Users/SUPREME TECH/Desktop/SAM3/ai-image-detector")
model = ViTForImageClassification.from_pretrained("C:/Users/SUPREME TECH/Desktop/SAM3/ai-image-detector")

def detect_image(image_path):
    # Open and prepare the image
    image = Image.open(image_path)
    if image.mode != 'RGB':
        image = image.convert('RGB')
    
    # Process the image
    inputs = processor(images=image, return_tensors="pt")
    
    # Get the predictions
    with torch.no_grad():
        outputs = model(**inputs)
        predictions = outputs.logits.softmax(dim=-1)
    
    # Analyze the results
    scores = predictions[0].tolist()
    results = [
        {"label": "REAL", "score": scores[0]},
        {"label": "FAKE", "score": scores[1]}
    ]
    
    # Sort the results by confidence
    results.sort(key=lambda x: x["score"], reverse=True)
    
    return {
        "prediction": results[0]["label"],
        "confidence": f"{results[0]['score']*100:.2f}%",
        "detailed_scores": [
            f"{r['label']}: {r['score']*100:.2f}%" 
            for r in results
        ]
    }

# Test code
if __name__ == "__main__":
    # You can change the image path here
    image_path = "path/to/your/image.jpg"
    
    try:
        result = detect_image(image_path)
        print("\nImage analysis results:")
        print(f"Classification: {result['prediction']}")
        print(f"Confidence: {result['confidence']}")
        print("\nDetails:")
        for score in result['detailed_scores']:
            print(f"- {score}")
            
    except Exception as e:
        print(f"An error occurred: {str(e)}")

Advanced Usage

async function detectImage(imageFile) {
  const formData = new FormData();
  formData.append('image', imageFile);

  const response = await fetch('YOUR_API_ENDPOINT', {
    method: 'POST',
    body: formData
  });

  return await response.json();
}

📚 Documentation

The model classifies images into two categories:

• Real Image (0): The image is real and not AI - generated.
• AI Generated (1): The image is generated by AI.

🔧 Technical Details

📦 Installation

To use this model, you need to install the following dependencies:

• transformers>=4.30.0
• torch>=2.0.0
• Pillow>=9.0.0

⚠️ Limitations

• Image Quality: The model performs best with clear, high - quality images.
• Edited Photos: Accuracy may be reduced for heavily edited photos.
• General Purpose: It is designed for general image detection.

📄 License

• Created by: yaya36095
• License: MIT
• Repository: https://huggingface.co/yaya36095/ai-image-detector