About this tutorial

About This Tutorial


This tutorial is an introductory course to ComfyUI. It is designed to assist everyone in quickly becoming proficient in ComfyUI. As well as in understanding the basic principles of the Stable Diffusion model and ComfyUI.

This tutorial is primarily divided into four modules:

⏳ | PreparationMainly introduces the installation of ComfyUI, model downloads, plugin installation, etc.
🏎️ | BasicsIntroduces the basic usage of ComfyUI, and the basic principle of Stable Diffusion model. Upon completing this foundation, you can use ComfyUI to build basic Stable Diffusion and output various charts using Text-to-Chart method. Moreover:
  1. Understand ComfyUI's various basic operations and hotkeys.
  2. Understand how to write Stable Diffusion prompts.
  3. Understand the knowledge related to LoRA.
Additionally, this module features elective content, including model recommendation, advanced prompts, and LoRA recommendations. Upon completing the Basics, you can essentially use ComfyUI to generate images of multiple styles.
🛩️ | AdvancedAfter completing the fundamentals, you may be dissatisfied with the generated images. For example, you might find:
  1. The resolution of the generated images is insufficient.
  2. Part of the content of the generated images is not satisfactory, and you want to modify it.
  3. You might want enhanced control over the generation process, such as controlling the poses of characters in the images, etc.
The Advanced level will introduce more methods to help you overcome these issues.Upon completing the Advanced level, it means you'll be able to control model outputs relatively accurately.
🚀 | ExpertThe Expert level teaches you to integrate what you've learned in the beginner and Advanced levels to create more complex images, as well as how to operate with Text-to-Video related functions. For example:
  1. Use multiple models simultaneously to generate images.
  2. Link multiple workflows together to achieve better results.
  3. Master how to use ComfyUI to build a Text-to-Animated Image and Text-to-Video workflow.
Upon completing the Expert level, it means you'll be able to generate satisfactory images and videos with ease.
Subscribe for free to receive new posts and support my work. Or join our Discord.

Target Audience

This tutorial is intended for:

  1. Designers & creators who are interested in learning AI image generation.
  2. Beginners who have a basic foundation in AI image generation, or have used Midjourney or SD WebUI, and want to learn ComfyUI.

If you just want to learn how to generate images through AI for fun, I do not recommend you to learn ComfyUI.

Update Plan

Currently, the tutorial is still being updated. You're welcome to subscribe to our newsletter (opens in a new tab), to receive the latest tutorials. Or join us on Discord (opens in a new tab) for discussions. Here's the update progress & plan for this tutorial:

⏳ | Preparation1. Installing ComfyUI
2. Downloading & Importing Models
3. Installing Plugins
4. Cloud Installation
🏎️ | Basics1. Stable Diffusion Basics
2. ComfyUI Basics ①
3. ComfyUI Basics ②
4. SD Prompt Basics
5. Embedding
6. LoRA
7. Model Recommend🚧 Under construction
8. Advanced Prompt🚧 Under construction
9. LoRA Recommend🚧 Under construction
🛩️ | Advanced1. Image-to-Image
2. Upscale
3. In/Outpainting
4. ControlNet
5. Advanced Stable Diffusion
6. Advanced Image-to-Image🚧 Under construction
7. Advanced Upscale🚧 Under construction
8. Advanced ControlNet
🚀 | Expert1. Stable Cascade
2. Model Merging🚧 Under construction
3. Text2Video🚧 Under construction
....❤️‍🩹 To be continued

Special Thanks

During the production of this tutorial, the content and examples were referenced from the following tutorials or documents:

Subscribe for free to receive new posts and support my work. Or join our Discord.