✨ GAN Image Generator is a web application built using Streamlit that allows users to generate AI-powered images using a Generative Adversarial Network (GAN). This project leverages a pre-trained generator model to create realistic images based on random noise input.
- User-friendly interface to specify the number of images to generate.
- Displays generated images in a grid format.
- Information about Generative Adversarial Networks (GANs) and useful resources for further learning.
To run this project, you need to have the following installed:
- Python 3.6 or higher
- Streamlit
- TensorFlow
- NumPy
- Matplotlib
You can install the required packages using pip:
pip install -r requirements.txt-
Clone the repository:
git clone https://github.com/ArpitKadam/GAN-Image-Generator.git cd GAN-Image-Generator -
Download the pre-trained generator model and save it as
generator_model.kerasin the project directory. (Make sure to replace this with your actual model file.) -
Run the Streamlit app:
streamlit run app.py
-
Open your web browser and go to
http://localhost:8501to access the application.
- Use the slider in the sidebar to select the number of images you want to generate (between 1 and 100).
- Click the "Generate Images 🚀" button to create the images.
- The generated images will be displayed below the button.
Generative Adversarial Networks (GANs) are a type of artificial intelligence model used to generate realistic images, videos, and even music. They work by training two neural networks – a generator and a discriminator – in a competitive process. The generator tries to create realistic data, while the discriminator tries to differentiate real from fake data.
- 📜 Original Paper (Goodfellow et al., 2014): Generative Adversarial Networks
- 📖 GANs Explained: A Beginner’s Guide
- 🎥 Video Tutorial: GANs Explained Visually
- 🛠 Hands-on Tutorial: Train Your Own GAN
Contributions are welcome! If you have suggestions for improvements or new features, feel free to open an issue or submit a pull request.
This project is licensed under the MIT License - see the LICENSE file for details.
🚀 Explore, learn, and start generating your own AI-powered images!