Last Updated on June 12, 2023
Machine learning is about learning some properties of a data set and then testing those properties against another data set. A common practice in machine learning is to evaluate an algorithm by splitting a data set into two. We call one of those sets the training set, on which we learn some properties; we call the other set the testing set, on which we test the learned properties.
Stable Diffusion is a deep learning text-to-image diffusion model capable of generating photo-realistic images given any text input. In seconds you can create stunning artwork. Stable Diffusion uses a kind of diffusion model, called a latent diffusion model.
We recently published reviews of InvokeAI and Stable Diffusion web UI, Stable Diffusion toolkits, both offering straightforward installations of Stable Diffusion with attractive web user interfaces. As we you might expect, there are other projects pursuing similar lines.
Easy Diffusion offers a web user interface for Stable Diffusion. This is cross-platform open source software running on Linux, macOS, and Windows.
You’ll need curl installed.
$ sudo apt install curl
Many Machine Learning tools need knowledge of Anaconda or Docker to ensure that a system is not polluted. Easy Diffusion is different.
Easy Diffusion bills itself as a simple 1-click way to install and use Stable Diffusion without any technical knowledge.
We’ll use wget to download the zip file
$ wget https://github.com/cmdr2/stable-diffusion-ui/releases/download/v2.5.24/Easy-Diffusion-Linux.zip
Extract the .zip file with the command
$ unzip Easy-Diffusion-Linux.zip
This creates a stable-diffusion-ui directory. Change into that directory and run the start.sh shell script
$ cd easy-diffusion
The script does all the hard graft, including downloading and installing a raft of dependencies, cloning the Easy Diffusion GitHub repository, as well as downloading the data files (weights) for Stable Diffusion, as well as GFPGAN, ESRGAN, VAE, and more. The script doesn’t install xformers as it breaks some functionality, so don’t worry when you see that error message.