How to Install & Use Stable Diffusion on Windows in 2024 (Easy Way)

AI Andy
7 Feb 202413:07

TLDRThe video script provides a step-by-step guide on installing and using stable diffusion models through Comfy UI, an easier alternative to the traditional Python method. It covers the installation of Comfy UI, downloading and placement of necessary files, generating images using stable diffusion, and enhancing the process with custom nodes and models from Civit AI. The guide aims to help users achieve high-quality image generation with minimal technical expertise.


  • πŸ”§ Installation of Comfy UI is recommended for easier and more accessible use of Stable Diffusion models, as opposed to the traditional Python installation method.
  • πŸ’» Comfy UI can be found by searching its name on Google and downloading it through the provided links in the video description.
  • πŸ“‚ After downloading, it's advised to extract the ZIP file and move the folder to a suitable location, such as a newly created 'AI' folder in Documents.
  • πŸ–₯️ Users should choose the appropriate executable file (CPU or Nvidia GPU) based on their system specifications, ensuring they meet the required VRAM for the model.
  • πŸ”„ The video emphasizes checking VRAM capacity by using the Windows 'DXDiag' tool, which is crucial for running the Nvidia GPU executable.
  • πŸš€ To generate images with Stable Diffusion, users need to download the necessary model files, such as the base model, refiner, and checkpoint files, and place them in the correct folders.
  • 🎨 The script explains the process of generating images using the Stable Diffusion interface, including setting up prompts, image dimensions, and sampler settings.
  • 🌐 Comfy UI Manager can be used to install additional custom nodes and enhance the functionality of the interface by following instructions on the GitHub page.
  • πŸ” Users can search for and install various custom nodes to perform specific tasks, such as face swapping or character pose rendering.
  • πŸ† Civit AI is highlighted as a platform for downloading high-quality custom models, with the option to test models before downloading them for better image output.
  • πŸŽ₯ The video serves as a comprehensive tutorial for users interested in leveraging Stable Diffusion technology for image generation, providing step-by-step guidance and resources.

Q & A

  • What are the two methods mentioned in the script for installing and using Stable Diffusion?

    -The two methods mentioned are installing through Python, which is considered the hard way, and using Comfy UI, which is presented as the easier way for users with lower technical knowledge.

  • Why is Comfy UI recommended over the traditional Python installation method?

    -Comfy UI is recommended because it simplifies the installation process, making it more accessible for users without advanced technical skills. It allows users to download necessary components and have Stable Diffusion up and running with minimal effort.

  • What is the first step in installing Stable Diffusion using the Comfy UI method?

    -The first step is to search for 'Comfy UI' on Google and download it by clicking the first link provided, which leads to the direct download link.

  • What are the system requirements for running the Stable Diffusion model mentioned in the script?

    -The model requires around 8 GB of VRAM. For users with an Nvidia graphics card or an M1 or M2 chip Mac, the script provides instructions on how to check the VRAM and download a compatible version of the model.

  • How does one determine the amount of VRAM their system has?

    -To check VRAM, users can open the command prompt on Windows by pressing 'Windows R', typing 'dxdiag', clicking 'OK', and then looking at the 'Display' tab to see the VRAM information.

  • What are the key components that need to be downloaded for Stable Diffusion using the Comfy UI method?

    -The key components include the Stable Diffusion XL base model, the Stable Diffusion refiner, and the SDXL V model. These components are downloaded from the provided links in the script description.

  • Where should the downloaded model files be placed for the Stable Diffusion setup?

    -The downloaded model files should be placed in the 'models' folder within the 'AI' directory that the user creates in their 'Documents' folder.

  • How does the script guide users in generating an image with Stable Diffusion?

    -Users are guided to run the Nvidia GPU executable, navigate to the model folder, and use the provided checkpoints. They then enter a prompt describing the desired image, set the image parameters, and use the K sampler to generate the image.

  • What is the role of the Comfy UI manager in enhancing Stable Diffusion functionality?

    -The Comfy UI manager allows users to install custom nodes and add-ons that can enhance the functionality of Stable Diffusion. These nodes can be used for various tasks, such as face swapping or applying poses to characters.

  • How can users find and test custom models for Stable Diffusion without downloading them?

    -Users can visit, navigate to the 'Models' tab, and filter by highest rated or most downloaded models. They can then use the built-in image generator to test the models with their prompts before deciding to download them.

  • What is the recommended approach for generating higher quality images with Stable Diffusion?

    -The script suggests using custom models available on for higher quality images. Users can test these models directly on the website and download the ones that meet their requirements.



πŸ“ Introduction to Installing Stable Diffusion with Comfy UI

This paragraph introduces the process of installing Stable Diffusion using Comfy UI, an easier alternative to the traditional Python installation method. It emphasizes the simplicity of the Comfy UI, which is accessible even to those with low technical knowledge. The speaker outlines the steps to install Comfy UI, download the Stable Diffusion models, and set up the necessary files in the correct directories. The paragraph also mentions the importance of checking one's GPU capabilities and provides a link for Mac users. Additionally, it introduces the use of TLD DV for meeting summaries, highlighting its compatibility with Zoom, Google Meet, and teams.


πŸ”§ Downloading and Setting Up Stable Diffusion Models

The second paragraph delves into the specifics of downloading and setting up the Stable Diffusion models, including the Stable Diffusion XL base and refiner models. It provides instructions on where to place the downloaded files within the AI documents folder and emphasizes the need for patience due to the large file sizes and potential download times. The paragraph also introduces the process of generating images using the installed models and outlines the steps to access the Comfy UI manager for further customizations.


πŸš€ Enhancing Stable Diffusion with Custom Nodes and Civit AI

The final paragraph focuses on enhancing the Stable Diffusion experience by installing custom nodes through the Comfy UI manager and using Civit AI to download high-quality models. It explains how to install additional nodes for various functions and provides an example of a face swap extension. The paragraph also suggests testing models on Civit AI before downloading to ensure quality and offers a recommended model link for further exploration. The speaker concludes by encouraging users to follow the provided links in the description for more information and concludes the tutorial.



πŸ’‘Stable Diffusion

Stable Diffusion is a type of artificial intelligence model used for generating images from textual descriptions. It is a core component of the video's content, as the tutorial focuses on installing and using this model to create images. The script mentions downloading and utilizing Stable Diffusion models to enhance the capabilities of the AI system.

πŸ’‘Comfy UI

Comfy UI is a user interface that simplifies the process of using Stable Diffusion models. It is presented as an easier alternative to installing the models through Python and is central to the tutorial, guiding users on how to navigate and operate the system to generate images. The script emphasizes the ease of use and the straightforward installation process of Comfy UI.


Installation refers to the process of setting up and preparing software or programs for use. In the context of the video, it involves downloading and configuring Stable Diffusion models and Comfy UI on a user's computer. The script outlines the steps required to install these components, which is essential for users to start generating images with the AI system.

πŸ’‘Nvidia GPU

Nvidia GPU refers to a Graphics Processing Unit manufactured by Nvidia, a company known for its graphics and AI technologies. In the video, it is mentioned as a requirement for running the Stable Diffusion model, indicating that a certain level of computational power is necessary for efficient image generation. Users with Nvidia GPUs can utilize the 'run Nvidia GPU' option for optimal performance.


Checkpoints in the context of AI models refer to saved states of the model that can be loaded to continue training or to generate outputs. The video script mentions loading checkpoints as part of the process of using Stable Diffusion to generate images, indicating that these checkpoints are essential for the model to function and produce the desired outputs.


Prompts are textual inputs provided to the AI model to guide the generation of specific images. In the video, prompts are used to tell the Stable Diffusion model what kind of image the user wants to create. The script explains how to use positive and negative prompts to refine the output and get the desired results from the AI system.

πŸ’‘Custom Nodes

Custom nodes are additional functionalities or extensions that can be installed in the Comfy UI to enhance the capabilities of the AI system. These nodes can perform various tasks, such as face swapping or applying poses to characters, as mentioned in the video. The script guides users on how to install these nodes to achieve more advanced and personalized outputs from the AI.


Video RAM (VRAM) is the memory used to store image data for the GPU to process. In the context of the video, VRAM is crucial as it determines the capacity of the GPU to handle the computational demands of running AI models like Stable Diffusion. The script instructs users on how to check their VRAM to ensure their hardware meets the requirements for the AI system.

πŸ’‘Image Generation

Image generation is the process of creating visual content using AI models, such as Stable Diffusion. It involves inputting textual prompts and utilizing the AI's capabilities to produce corresponding images. The video script focuses on teaching users how to generate images through the installation and use of Stable Diffusion and Comfy UI.

πŸ’‘Civit AI

Civit AI is a platform mentioned in the video that offers a variety of custom models for users to download and use. It provides a selection of high-quality models that can be tested and installed to improve the performance and output of the AI system. The script encourages users to explore Civit AI for additional models and to test them before installation.

πŸ’‘Model Refiner

A Model Refiner is a component used to enhance or refine the output of AI models. In the context of the video, the Stable Diffusion refiner is downloaded and used alongside the base model to improve the quality of the generated images. The script details the process of downloading and utilizing the refiner as part of the overall setup.


The introduction of an easy method to install and use stable, diffusion models through a comfortable UI, making it accessible to individuals with low technical knowledge.

The comparison between the hard way of installing stable, diffusion through Python and the easy way using the comfy UI, emphasizing the simplicity and user-friendliness of the latter.

A step-by-step tutorial on how to install Comfy UI, including searching on Google, downloading, and extracting the ZIP file.

The recommendation to create a dedicated folder for AI within the documents to keep the setup organized and easily accessible.

The distinction between running the application on CPU and using an Nvidia GPU, with specific requirements for VRAM and guidance for Mac users with M1 chips.

The process of checking VRAM capacity using Windows R and DXDAG, ensuring users have the necessary hardware to run the models.

The mention of TLD DV, an AI tool that can summarize meetings and generate reports, highlighting its compatibility with Zoom, Google Meet, and Microsoft Teams.

A detailed explanation of downloading and installing the stable diffusion base model, refiner, and the sdxl V model, including file sizes and download times.

Instructions on where to place the downloaded models within the AI documents folder for proper integration with the comfy UI.

A guide on generating images using the stable diffusion model, including setting up the prompt, negative prompt, and configuring image parameters.

The process of installing custom nodes through the Comfy UI manager and the potential to enhance the functionality of the stable diffusion model with additional features.

The demonstration of using custom nodes for specific tasks, such as face swapping and character pose rendering.

The recommendation to test custom models on Civit AI before downloading them to ensure they meet the desired quality standards.

The mention of Civit AI as a platform to download a variety of custom models, allowing users to filter by ratings and downloads.

The final step of installing high-quality models like the Think Diffusion XL for superior image generation capabilities.

The overall summary of the tutorial, emphasizing the ease of installation and use of stable diffusion models through the comfy UI and the availability of resources in the video description.