A Flask-based web application that detects whether an image is AI-generated and identifies its source.
- Detect if an image is AI-generated
- Identify the source of AI-generated images (Midjourney, DALL-E, Stable Diffusion)
- Beautiful and responsive web interface
- Drag and drop image upload
- Real-time analysis results
- Clone the repository:
git clone <repository-url>
cd <repository-name>
- Create and activate a virtual environment:
python3 -m venv venv
source venv/bin/activate # On Windows, use: venv\Scripts\activate
- Install dependencies:
pip install -r requirements.txt
- Start the Flask application:
python app.py
- Open your web browser and navigate to:
http://localhost:5000
-
Upload an image by either:
- Dragging and dropping an image onto the drop zone
- Clicking "Select Image" and choosing a file
-
View the analysis results, which include:
- Whether the image is AI-generated
- Confidence level of the detection
- Source of the image (if AI-generated)
- Confidence level of the source detection
- JPEG (.jpg, .jpeg)
- PNG (.png)
The application uses:
- PyTorch for deep learning
- Hugging Face Transformers for the AI detection models
- Flask for the web server
- Tailwind CSS for the user interface
[Your License Here]