Stable Diffusion Image Generator

A simple web application that generates images from text prompts using Stable Diffusion v1.5, built with Gradio.

Features

• Generate high-quality images from text descriptions
• User-friendly web interface
• Powered by Stable Diffusion v1.5 model
• GPU acceleration support

Requirements

• Python 3.8+
• CUDA-compatible GPU (recommended for faster generation)
• At least 8GB VRAM for GPU acceleration

Installation

1. Clone this repository:

git clone <your-repo-url>
cd stable-diffusion-generator

2. Install the required dependencies:

pip install -r requirements.txt

Usage

1. Run the application:

python app.py

2. Open your web browser and navigate to the URL shown in the terminal (usually http://127.0.0.1:7860)

3. Enter your text prompt in the input box and click "Submit" to generate an image

Example Prompts

• "A beautiful sunset over mountains"
• "A futuristic city at night"
• "A cat wearing sunglasses"

Dependencies

• diffusers==0.27.2 - Hugging Face Diffusers library
• transformers==4.33.3 - Transformers library
• accelerate==0.21.0 - Acceleration library for faster inference
• torch==1.13.1 - PyTorch
• gradio==3.39.0 - Web UI framework
• Pillow==9.5.0 - Image processing library

Model

This application uses the Stable Diffusion v1.5 model from Hugging Face (sd-legacy/stable-diffusion-v1-5).

License

[Add your license here]

Contributing

[Add contribution guidelines here]