Welcome to Part 2 of our series on using ControlNet with ComfyUI. This section builds upon the foundation established in Part 1, assuming that you are already familiar with installing ComfyUI, generating images, and setting up ControlNet with a pre-created input image. If you need a refresher on these initial steps, please revisit How to …
How to use ControlNet with ComfyUI – Part 2, Preprocessor Read More »
Understanding ControlNet Integration with ComfyUI Before diving into the steps for using ControlNet with ComfyUI, let’s first revisit what ControlNet accomplishes. In the Stable Diffusion system, the UNet or Latent Diffusion Model leverages the encoded text output from the CLIP text encoder as a guide for image generation. ControlNet enhances this process by providing additional …
Overview of steps In ComfyUI, integrating LoRA into your workflow involves placing a Load LoRA node within your existing setup. Specifically, this node should be positioned between the Load Checkpoint and CLIP Text Encode nodes, as well as between the Load Checkpoint and KSampler nodes, as illustrated in the figure below. For those already using …
Problem to solve – Overview of Hires. fix To understand the necessity of a high-resolution fix (commonly known as Hires. fix or hires fix), consider the following example: In both images below, the main characters are set against a backdrop of sunflowers and the sky. Upon closer inspection, it becomes evident that the eyes of …
Overview Inpainting is a crucial tool for adding details or modifying specific parts of an image. Using Inpainting with ComfyUI is remarkably straightforward. In this tutorial, we’ll explore how to seamlessly add a puppy beside a lady on a bench, demonstrating the power and ease of inpainting in ComfyUI. As with our other lessons, we’ll …
Installation ComfyUI is a powerful and flexible package to unleash the power of Stable Diffusion. You can install from https://github.com/comfyanonymous/ComfyUI. The page has detailed instructions that you can follow. Basic Usage Once you follow the instructions, activate your virtual environment and type python main.py. You should see console output similar to below. It will start …
Installation Automatic1111 is a great and easy to use package to generate images using Stable Diffusion and offers various functionalities. You can install from https://github.com/AUTOMATIC1111/stable-diffusion-webui The page has detailed instructions that you can follow. Basic Usage Once you follow the instructions to install all required software and models, type ./webui.sh. You should see console output …
Have you ever seen a person in an old photo from a long time ago and wondered what the photo would have looked like if the image was captured in a digital camera? ControlNet Recolor model can satisfy your curiosity. Though you cannot really restore the original color, but it can show possible colors that …
IP-Adapter offers the innovative capability of using an image as a prompt to generate new images, in addition to the traditional text-based prompts. For example, if you wish to create a wood carving in the shape of an apple, you can input ‘wood carving’ as your text prompt and provide an image of an apple …
How to use IP-Adapter to Use an Image as a Prompt in Automatic1111 Read More »
What if you have generated an image and you want to generate very similar images to that one, however you don’t want the changes to be significant? This was a tough problem to solve in Stable Diffusion. For example, let’s see the image below. If you try to generate more images by increasing the batch …