Overview In this tutorial, we will be discussing how to do Inpainting in Fooocus. Inpainting is a feature that allows the user to replace a part of the image with another image in a way that looks natural. In this tutorial, we will be using the below image. The goal is to put a wolf …
Overview There are cases when you want to have a control over the shape of the generated image. For example, if you want to generate an image of marble towers in the Medieval age, typing: Towers made of marble in a medieval city would get you something like below: Let’s say what you had in …
How to control the shape of the generated image in Fooocus Read More »
In this tutorial, we’ll explore how to transform the style of an image using Fooocus, specifically focusing on the ‘img2img’ feature. Our primary goal is to convert a photo-realistic image into an anime-style illustration. However, this technique isn’t limited to just anime styles; it can be applied to a variety of artistic transformations. Let’s dive …
How to change the style of an image using Fooocus (img2img) Read More »
In this tutorial, we will discuss how to upscale an image using Fooocus. We will be using the following prompt: Base model is juggernautXL_version6Rundiffusion.safetensors. Steps If you do not have an image that you want to upscale, the first step is to generate a photo. If you enter the prompt and press Generate, you should …
Welcome to the first episode of our Fooocus tutorial series! Fooocus boasts an elegantly designed user interface, streamlined for ease of use, allowing users to generate images without navigating through numerous options typically found in image generation software. Remarkably, this user-friendly approach is achieved without compromising image quality. Fooocus empowers users to effortlessly create stunning …
Tiled Diffusion & VAE has multiple nice features. One of them is Region Prompt Control. To understand what it does. Let’s take a look at the following prompt: The goal of the prompt is to have a panda standing next to a stream train on the beach on the tropical beach. However, if you generate …
How to use Tiled Diffusion’s Region Prompt Control in Automatic1111 Read More »
Bing Image Creator offers the capability to generate high-resolution images for free, demonstrating a considerable understanding of user prompts. However, when aiming for photorealistic outputs, it might not always meet expectations. For instance, when I used the following prompt with Bing Image Creator, it produced four images that contained people who did not look real: …
How to enhance images generated in Bing Image Creator using Automatic1111 Read More »
In this tutorial, we will discuss an example of how to generate a photo-realistic image from line art using ControlNet. I first generated an image using Stable Diffusion, Then using GIMP, I extracted edges and did some clean-up. It’s worth noting that the line drawing doesn’t need to be immaculate; a rough outline like the …
Installation InvokeAI offers a slick web user interface to generate images using Stable Diffusion and offers various functionalities. You can install from https://github.com/invoke-ai/InvokeAI. The page has detailed instructions that you can follow. One nice thing about Invoke AI’s installation process is that it offers you an option to download some models during the installation. Therefore …
This tutorial covers using multiple ControlNets. It builds upon the foundation established in Part 2 assuming that you are already familiar with how to use different preprocessors to generate different types of input images to control image generation. If you need a refresher on these steps, please revisit How to use ControlNet with Comfy UI …
How to use ControlNet with ComfyUI – Part 3, Using multiple ControlNets Read More »