Stable Diffusion Ultimate Guide pt. 4: Inpainting

Umberto Grando
9 min readApr 1, 2023

Hello World!

In the last 3 parts of my guide, we’ve seen:

  • How to set up the Automatic1111 SD GUI
  • How to write effective prompts for a specific model
  • The workflow to create sharp high resolution pictures.

Today we are going to have a look at how to inpaint a picture to change a specific part. This is a fundamental step in generating high quality images without having to generate thousands of them.

The model we are going to use for this example is my latest:

Requirements

To follow this example, you’ll need:

  • The Automatic1111 Stable Diffusion UI. If you don’t know how to install it, check out the first part of this series here: https://medium.com/p/bd7dbcd5ce4b
  • A GPU that can handle images of 768x1152 size. I’m using a RTX 4080 with 16 GB of RAM. In case you have access to less VRAM, you’ll probably be able to work with a lower resolution.

--

--

Umberto Grando

I’m Umberto Grando, an IoT Specialist with a passion for programming, gaming and technology in general.