Text to Image Generation Using Stable Diffusion Model

This is a self-learning hands-on GenAI project based on a tutorial. It uses Stable Diffusion model to generate image from user prompt and provide a simple yet user-friendly interface.

Features

• Built using PyTorch library
• SOTA model (Stable Diffusion v1.4) from Stability AI
• Integrated with Hugging Face Diffusers library
• GUI built with CustomTkinter
• Runs on CPU only

Setup Instructions

The GUI app requires a Hugging Face access token to run the model.

Running App Instructions

• Navigate to the folder where the project files are saved: E.g., cd C:\Users\User\stable-diffusion
• Type: python app.py