fairlight1337/stable-diffusion-server repository overview

This repository houses a minimalist web server implementation to allow entering a text prompt, and sending it to a Stable Diffusion network. The resulting image is presented to the user in the browser.

This work is based on the Stable Diffusion model contained in KerasCV: https://keras.io/guides/keras_cv/generate_images_with_stable_diffusion/⁠

Download the image, start the container, and access http://127.0.0.1:5000⁠. You can enter your text prompt there. The model is already downloaded into the docker image, so no need for waiting for the download. For the first image generated there is some more internal initialization, but after that it should be quicker.