ControlNet is a neural network that controls image generation in Stable Diffusion by adding extra conditions. Details can be found in the article Adding Conditional Control to Text-to-Image Diffusion Models by Lvmin Zhang and coworkers. It is a game changer. You can use ControlNet to, to name a few, In this post, You will learn…
Blog
How to remove extra limbs with Stable Diffusion inpainting
A common issue in Stable Diffusion AI images is that limbs may not be generated quite right. Sometimes a person may have one more arm, and the other time one of his legs may be missing. Finally, we got 4 limbs but the anatomy is not quite correct. A reader suggested making a special tutorial…
Stable Diffusion prompt: a definitive guide
Developing a process to build good prompts is the first step every Stable Diffusion user tackles. This article summarizes the process and techniques developed through experimentations and other users’ inputs. The goal is to write down all I know about prompts so you can know them all in one place. Table of ContentsAnatomy of a…
Fantasy psychedelic portrait
This is mostly Josephine Wall style but mixed with Russ Mills. Portrait is a common subject for both, and they mixed pretty well. The incredible embellishments with flowers, leaves, vines and birds are fascinating to inspect. Fantasy is hardly an escape from reality. It’s a way of understanding it. Lloyd Alexander All images are generated…
Instruct Pix2Pix: Edit and stylize photos with text
Instruct Pix2Pix is a Stable Diffusion model that edits images with the user’s text instruction alone. We will go through how it works, what it can do, how to run it on the web and AUTOMATIC1111, and how to use it. Table of ContentsWhat can Instruct pix2pix do?How does Instruct pix2pix work?Model ArchitectureTrainingDifference from other…
Sharp blades
These swords were created using image-to-image. It did require more work but you would get images you would never be able to produce using text-to-image alone. Beauty is power; a smile is its sword. John Ray All images are generated with Colab notebook included in the Quick Start Guide. Prompt for sword: highly detailed pattern ornated…
How to use outpainting to extend images
Stable Diffusion can extend an image in any direction with outpainting. It can generate a coherent background that is outside of the view. In this article, you will learn how to perform outpainting step-by-step. Table of ContentsSoftwareStep-by-step guideStep 1: Upload the image to AUTOMATIC1111Step 2: Select an inpainting modelStep 3: Set outpainting parametersStep 4: Enable…
ChatGPT: How to generate prompts for Stable Diffusion
Can ChatGPT generate high-quality prompts for Stable Diffusion? The answer is yes. But you will need special methods to tease them out. Once you learn how to do it, the results will surprise you. In this article, I will show you how to do that step-by-step. Table of ContentsWhat is ChatGPT?How was ChatGPT trained?Does ChatGPT…
Flowery girl
A colorful illustration portrait with a lot of flowers and butterflies. Take time to smell the roses Proverb All images are generated with Colab notebook included in the Quick Start Guide. A colorful illustration portrait with a lot of flowers and butterflies. Take time to smell the roses Proverb All images are generated with Colab notebook…
How to run Stable Diffusion on Google Colab (AUTOMATIC1111)
This is a step-by-step guide for using the Google Colab notebook in the Quick Start Guide to run AUTOMATIC1111. This is one of the easiest ways to use AUTOMATIC1111 because you don’t need to deal with the installation. See installation instructions on Windows PC and Mac if you prefer to run locally. This notebook is…