About this Tutorial

👋 G'Day

Thank you for your interest. This tutorial is geared toward beginners in ComfyUI, aiming to help everyone quickly get started with ComfyUI, as well as understand the basics of the Stable Diffusion model and ComfyUI.

Additionally, since we've developed an online version of ComfyUI, the tutorial will also include some operations specific to the online version. If you're just looking to learn the basics of ComfyUI, you can skip this part.

If you find this tutorial helpful, consider giving us a star on GitHub (opens in a new tab) or share it with your friends.

Also, you can subscribe to our newsletter (opens in a new tab), or join our Discord (opens in a new tab) to get the latest tutorials.

Target Audience for This Tutorial

This tutorial is aimed at:

  1. Designers & creators who want to learn AI image generation.
  2. Beginners with some foundation in AI image generation, or those who have used Midjourney or SD WebUI and want to learn ComfyUI.

If you're just looking to learn AI image generation for fun, I wouldn't recommend learning ComfyUI.

Learning Path

The tutorial is mainly divided into four modules, which you can study in order:

  1. Download and Installation. It mainly introduces the installation of ComfyUI, model downloading, plugin installation, etc. If you're using our cloud version, you can skip this part.
  2. Basics. It introduces the basic usage of ComfyUI and the fundamentals of the Stable Diffusion model. After completing this section, you can use ComfyUI to set up a basic Stable Diffusion and generate various images through text.
  3. Intermediate. After completing the basics, you might not be satisfied with the generated images, such as finding the resolution insufficient or wanting to modify certain parts of the images, or wanting more control over the generation process, like controlling the poses of characters in the images. The intermediate section will introduce more methods to help you resolve these issues.
  4. Advanced. The advanced section will teach you how to create more complex images by integrating what you've learned from the beginner and intermediate sections and how to operate video generation.

How to Learn

I believe the best way to learn is through practice.

  • If you're using our open-source local version or the cloud version (opens in a new tab), you can see all the workflows involved in this tutorial on the 'Templates' page within the product. You can directly open these workflows to try them out. Or you can follow the steps in the tutorial to build it step by step on your own.

  • The design of this tutorial focuses more on explaining the key technologies in AI image generation today, such as IPAdapter, ControlNet, and the basics of the Stable Diffusion model. This knowledge will also be helpful in learning other AI image generation tools. However, there is less emphasis on hands-on practice in the tutorial, so besides the tutorial, we also have a blog with more practical cases for reference:

Special Thanks

In the making of this tutorial, content and examples were referred to the following tutorials or documents: