2 Easier Image Generation with Stable Diffusion Webui
“Once men turned their thinking over to machines in the hope that this would set them free. But that only permitted other men with machines to enslave them.”
- Frank Herbert, Dune
This chapter covers
- Familiarizing yourself with AUTOMATIC1111’s Stable Diffusion Webui.
- Negative prompting and prompt attention.
- What the Classifier Free Guidance scale is and how to use it.
- How Sample steps change the final result.
- Recovering information you used to generate an image.
In this chapter we’ll be covering AUTOMATIC1111’s Stable Diffusion Webui, more commonly referred to as either AUTOMATIC1111 (after the username of its pseudonymous author), Webui (after the script used to run the program), or an abbreviated A1111. For this book we’ll refer to it as “A1111” to avoid confusion with other webuis that are starting to emerge and to save us from typing out the full name.. Using base Stable Diffusion in the last chapter involved heavy use of the command line, requiring understanding of a lot of specific arguments to make changes to our image generation process. A1111 provides a graphical interface to Stable Diffusion, as well as a variety of quality of life features and enhancements, that makes a dramatic improvement to the ease of working with and configuring Stable Diffusion.
To get started you’ll need to install A1111 on your local machine, Installation instructions can be found on the project’s github page: