How To Install ComfyUI And The ComfyUI Manager

Monzon Media
29 Aug 202312:06

TLDRThis video script offers a comprehensive guide on installing Comfy UI, a user interface for stable diffusion, along with necessary plugins. It begins with downloading and installing Git, which is used to pull files from GitHub. The script then walks through the process of downloading and extracting Comfy UI, setting up the installation directory, and configuring the Nvidia GPU bat file for easy access. It proceeds to explain the installation of xformers and PyTorch for faster generation times, and the selection of a model from sources like Hugging Face or Civit AI. The script also details the testing of the UI and the diffusion process, highlighting the role of text encoders and the denoising sampler. Additionally, it covers the installation of the plugins manager and custom nodes for further customization. The video concludes with tips on organizing the workspace and redirecting models to Comfy UI from other platforms.


  • πŸ“‚ Git is essential for pulling files from GitHub, which is a primary source for stable diffusion materials.
  • πŸ’» Installation of Git is straightforward and involves downloading the appropriate version and following the installation prompts.
  • πŸ“¦ 7-Zip is required to extract the Comfy UI files and should be downloaded if not already present on the system.
  • 🏠 Comfy UI should be extracted to a chosen directory, with the default being the C drive.
  • πŸ–₯️ Running the Nvidia GPU bat file sends it to the desktop for easy access and startup of Comfy UI.
  • πŸ”„ Installation of xformers and PyTorch is necessary for speeding up generation time and running Comfy UI effectively.
  • πŸ–ΌοΈ Downloading a model, such as the standard stable diffusion model from Hugging Face or Civit AI, is crucial for image generation.
  • πŸ“± The Comfy UI interface allows for zooming and navigation, with the model and checkpoints already loaded for immediate use.
  • 🎨 Custom models from Civit AI are recommended for users seeking more advanced options.
  • πŸ”§ The Plugins Manager is introduced for future use and can be installed by downloading a specific file into the Comfy UI directory.
  • πŸ”„ The SNAP to grid feature helps in organizing the workspace by snapping elements to a grid for a tidy arrangement.

Q & A

  • What is the primary function of Git mentioned in the script?

    -Git is used to pull files from GitHub, which is a central site for many resources related to stable diffusion.

  • How does the installation process of Git initiate?

    -The installation process of Git begins by downloading the appropriate version from the official website and then following the installation prompts.

  • What is 7-Zip and why is it used in this context?

    -7-Zip is a file manager used to extract the Comfy UI files that are downloaded in the form of an archive.

  • Where should the extracted Comfy UI files be located?

    -The extracted Comfy UI files should be placed in a chosen directory, with the example given being the C drive.

  • How does one make the Nvidia GPU bat file accessible on the desktop?

    -By right-clicking the Nvidia GPU bat icon, selecting 'Send to', and then choosing 'Desktop (create shortcut)'.

  • What are xformers and Pi torch, and why are they installed?

    -Xformers and Pi torch are software packages that are installed to help speed up generation time and are necessary to run Comfy UI.

  • What type of model is recommended for beginners starting with stable diffusion?

    -For beginners, the standard stable diffusion model from Hugging Face or Civit AI is recommended as a good starting point.

  • How does the diffusion process work in creating an image?

    -The diffusion process involves creating layers of noise and then using a sampler process to denoise and refine the image, ultimately converting the data back into pixels.

  • What is the purpose of the plugins manager and how is it installed?

    -The plugins manager is used to extend the functionality of Comfy UI by adding custom nodes. It is installed by downloading a specific file into the Comfy UI directory and running the installation.

  • How can one redirect models from a platform like Automatic 1111 to Comfy UI?

    -Models from platforms like Automatic 1111 can be redirected to Comfy UI by copying the model's address and pasting it into the 'extra_model_paths.yaml' file in the Comfy UI folder.

  • What is the benefit of using the 'Snap to grid' feature in Comfy UI?

    -The 'Snap to grid' feature helps keep the workspace organized by aligning elements to a grid, making it easier to manage connections and maintain a tidy interface.



πŸš€ Installing Comfy UI and Essential Plugins

This paragraph outlines the initial steps for installing Comfy UI, a user interface for stable diffusion, and necessary plugins. It begins with the installation of Git, which is used to pull files from GitHub, and details the process of downloading and installing Git on your system. The script then guides the user through the download and extraction of Comfy UI, emphasizing the need for 7-Zip to extract the files. The user is instructed to choose an installation location and extract the files there. The paragraph also covers the installation of additional components like xformers and PyTorch, which are vital for the functioning of Comfy UI. It concludes with the guidance on downloading a model for stable diffusion, either from Hugging Face or Civit AI, and setting up the environment for the first use of Comfy UI.


🎨 Understanding Comfy UI Interface and Installing Plugins

The second paragraph delves into the Comfy UI interface, explaining its basic setup and functionality. It describes how models are loaded and used to create images using data from text encoders. The paragraph further elucidates the diffusion process and the role of the VA decode in generating the final image. The user is introduced to the Plugins Manager and its installation method, which is crucial for future videos. The script provides instructions on customizing the UI, such as saving menu positions, inverting menu scrolling, and selecting color palettes. It also guides the user on installing custom nodes like 'Fail Fast Comfy UI Extensions' and 'Comfy UI Impact Pack' and demonstrates how to organize the workspace using the 'Snap to Grid' feature.


πŸ”„ Redirecting Models to Comfy UI and Preparing for Future Workflows

The final paragraph focuses on redirecting models from other platforms like Automatic 1111 to Comfy UI. It explains the process of copying model addresses and pasting them into the 'extra_model_paths.yaml' file within the Comfy UI directory. This allows users to access their models directly within Comfy UI. The paragraph also mentions the upcoming video content, which will cover building a workflow from scratch and using custom nodes for further customization. The user is encouraged to check out the next video for more detailed instructions and exploration of Comfy UI's capabilities.



πŸ’‘Comfy UI

Comfy UI is a user interface designed for interacting with stable diffusion models. It is the main focus of the video, as the narrator guides the viewer through its installation and setup process. The UI is described as a way to access the 'under the hood' functionalities of AI image generation, allowing users more control and customization over the models they use.


Git is a version control system that allows users to manage and track changes to files and code. In the context of the video, Git is used to pull files from GitHub, which is essential for obtaining the Comfy UI and other necessary components. It is a crucial first step in the installation process.


GitHub is a web-based platform that hosts and version-controls files, often used by developers for collaborative projects. In the video, GitHub is the source from which the Comfy UI and its plugins are downloaded. It is a key platform in the development community for sharing and maintaining open-source projects.


7-Zip is a free and open-source file archiver that can extract and compress files in various formats. In the video, it is used to extract the Comfy UI files after they have been downloaded. It is a valuable tool for handling different file compression types.

πŸ’‘Stable Diffusion

Stable Diffusion is a term used to describe a type of AI model that generates images from textual descriptions. The video is centered around setting up an environment to work with stable diffusion models, using Comfy UI as the interface. It is a key component in the creative process of AI-generated imagery.

πŸ’‘Nvidia GPU

Nvidia GPU refers to the Graphics Processing Unit manufactured by Nvidia, a company known for its high-performance GPUs used in gaming, professional visualization, and AI computations. In the video, the narrator instructs users with Nvidia GPUs on how to make their Comfy UI setup more accessible and efficient for running stable diffusion models.

πŸ’‘xformers and PiTorch

xformers and PiTorch are software libraries used in AI and machine learning. xformers is a library that helps with tasks like text classification and language modeling, while PiTorch, a misspelling of PyTorch, is an open-source machine learning library based on the Torch library. In the video, these libraries are installed to speed up generation time and are necessary for running Comfy UI.

πŸ’‘Model Download

Model Download refers to the process of obtaining AI models from platforms like Hugging Face or Civit AI. These models are essential for the functionality of Comfy UI, as they contain the data and algorithms needed to generate images from text prompts. The video instructs viewers on how to download a specific model and where to save it within the Comfy UI directory structure.

πŸ’‘Custom Nodes

Custom Nodes refer to additional functionalities or extensions that can be installed into Comfy UI to enhance its capabilities. These nodes are created by third-party developers and can be used to improve the organization, speed, or creative potential of the UI. The video discusses the installation of custom nodes and how they can be utilized within the Comfy UI environment.

πŸ’‘Plugins Manager

The Plugins Manager is a component of Comfy UI that allows users to manage and install additional features or customizations. It is an essential part of expanding the functionality of the UI beyond its basic setup. The video provides a step-by-step guide on how to install the Plugins Manager and use it to add new nodes to Comfy UI.

πŸ’‘Stable Diffusion Models

Stable Diffusion Models are AI models specifically designed for generating images from textual descriptions. These models are at the heart of the video's content, as the entire setup process for Comfy UI is aimed at preparing the environment for these models to function. The video discusses the download and installation of these models, as well as how to redirect models from other platforms to work within Comfy UI.


The introduction of git as a fundamental tool for pulling files from GitHub, which is a central platform for various applications related to stable diffusion.

The ease of installing git by downloading the appropriate version and following simple installation prompts.

The necessity of 7-Zip for extracting the comfy UI files, depending on the system's architecture.

The process of selecting the desired installation location for comfy UI and the extraction of files to that location.

The importance of running the Nvidia GPU bat file to make the comfy UI startup more accessible.

Instructions for installing xformers and Pi torch through the command window to optimize generation time and run comfy UI.

The recommendation to download a starting model from hugging face or civet AI for new users.

The detailed guide on testing the installation by opening the comfy UI interface and navigating through its default settings.

The explanation of the comfy UI interface, including the model loading, text encoders for prompts, and the diffusion process to create images.

The installation and usage of the plugins manager for additional functionality in comfy UI.

Customization options available in the plugins manager, such as menu position, invert menu scrolling, and color palette selection.

The process of installing custom nodes like fail fast comfy UI extensions and comfy UI impact pack for workflow organization and further customization.

The demonstration of snapping to grid feature for organizing nodes in the comfy UI workspace.

Instructions on redirecting models from platforms like automatic 1111 to comfy UI for a seamless workflow transition.

The guidance on editing the extra model paths yaml file to include personal model directories for use in comfy UI.

The promise of a future video tutorial on building a custom workflow from scratch and utilizing custom nodes for further customization.