ezStableDiffusion is a simple graphical user interface (GUI) built with tkinter and customtkinter, which allows users to easily generate images using the StableDiffusion pipeline.
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.
- Python 3.6 or later
tkinterandcustomtkinter(can be installed via pip)Pillow(can be installed via pip)torchandtorchvision(can be installed via pip)authtoken(should be provided by the developer)diffusers(should be provided by the developer)
- Clone the repository.
- Install the prerequisites via pip by running
pip install -r requirements.txt - Set the environment variable
cache_dirto the directory where the models will be stored. - Run the script
main.py
- Run the script
main.py - Type in the prompt the text you want to use as guidance for the image generation.
- Click on the "Generate" button.
- The generated image will be displayed and also saved as "generated.png" in the working directory.
- tkinter - Python's standard GUI package
- customtkinter - A wrapper for tkinter to make it easier to use
- Pillow - A python imaging library
- torch - PyTorch is an open source machine learning library
- diffusers - A library for image generation
- Developer - Initial work - Abdul Aziz
- The StableDiffusion pipeline is based on the paper "Stable Diffusion Generative Models" by Google Research
- The customtkinter library is based on the work of Jack Wilsdon