We can put a face in Stable Diffusion using LoRA and dreambooth checkpoint models. But both require training a new model, which can be time-consuming. What if you can inject a face instantly at sampling without training? This ComfyUI workflow copies the face of a person from input images. It can be used like a…
Blog
What is CFG Scale in Stable Diffusion?
The Classifier-Free Guidance (CFG) scale controls how closely a prompt should be followed during sampling in Stable Diffusion. It is a setting available in nearly all Stable Diffusion AI image generators. This post will teach you everything about the CFG scale in Stable Diffusion. Table of ContentsWhat does the CFG scale do?CFG scale for LCM…
What is denoising strength?
Denoising strength determines how much noise is added to an image before the sampling steps. It is a common setting in image-to-image applications in Stable Diffusion. The value of denoising strength ranges from 0 to 1. 0 means no noise is added to the input image. 1 means the input image is completely replaced with…
Partially animate a still image (ComfyUI)
This ComfyUI workflow generates this partially animated with animateDiff and inpainting. The same workflow using AUTOMATIC1111 is available here. NOTE: You must be a member of this site to download the ComfyUI workflow. Table of ContentsSoftwareStable Diffusion GUIHow the workflow worksStep-by-step guideStep 0: Load the ComfyUI workflowStep 1: Add image and maskStep 2: Set checkpoint…
Negative image prompt for Stable Diffusion
Many AI image generators, including Stable Diffusion, can use an image as a prompt to generate a similar image. On the other hand, we use text prompts to describe what we want and negative prompts to describe what we don’t want. How about a negative image prompt? In this post, I will describe an implementation…
How to train SDXL LoRA models
You can train your own SDXL LoRA model with the Google Colab Notebook created by this site. The following instruction trains a LoRA model for a person’s face. Table of ContentsSoftwareOption 1: Become a memberOption 2: Purchase the notebookStep 1: Prepare training imagesStep 2: Come up with a good triggering keywordStep 3: Review the training…
Optical illusion art
This workflow creates optical illusion art in AUTOMATIC1111. The images look like these:
How to change clothes with AI (Inpaint Anything)
You can change clothes in an image with Stable Diffusion AI for free. You can specify the new clothes with: Here are some samples of AI-generated clothes. This tutorial will show you how. Table of ContentsSoftwareInpaint Anything extensionGoogle ColabWindows, Mac, or LinuxInpaint with Inpaint AnythingStep 1: Upload the imageStep 2: Run the segmentation modelStep 3:…
How to make a selfie image of a movie character
This workflow creates an AI-generated selfie image of a movie character (Lord Voldemort of Harry Potter in this example) in AUTOMATIC1111.
Fooocus: Stable Diffusion simplified
Fooocus is a free and open-source AI image generator based on Stable Diffusion. It attempts to combine the best of Stable Diffusion and Midjourney: open source, offline, free, and ease-of-use. Fooocus has optimized the Stable Diffusion pipeline to deliver excellent images. You can spend less time on tweaking the settings and more time on creating…