Important :

Download this a Stable Diffusion checkpoint file v1-5-pruned-emaonly.ckpt ( https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/v1-5-pruned-emaonly.ckpt ) and then paste it inside the data folder with this name ( v1-5-pruned-emaonly.ckpt)

Simple Stable Diffusion Image Generator with Gradio

This is a simple image generator built using the Stable Diffusion model and the Gradio library for a user-friendly interface. It uses the DDPM sampler for image generation.

Features

• Text-to-Image Generation: Generate images from text prompts.
• Image-to-Image Generation: Modify existing images using text prompts.
• CFG Scale Control: Adjust the influence of the text prompt on the generated image.
• Inference Steps Control: Control the number of steps in the DDPM sampling process.
• Random Seed Generation: A new random seed is used for each image, ensuring diverse results.
• Negative Prompts: Refine image generation by specifying what you don't want to see in the image.

Requirements

• Python 3.7+
• PyTorch with cuda
• transformers
• pillow
• gradio
• A Stable Diffusion checkpoint file v1-5-pruned-emaonly.ckpt ( https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/v1-5-pruned-emaonly.ckpt )

You can install the required Python packages using:

python -m venv venv
venv/Scripts/Activate
pip install -r requirements.txt

To Run:
python gradio_app.py