Install Stable Diffusion 3 Locally: Step-by-Step with StableSwarmUI & ComfyUI

13 Jun 202425:24

TLDRThis tutorial guides users through installing Stable Diffusion 3 locally on Windows using two interfaces: StableSwarmUI and ComfyUI. It covers prerequisites like installing git and .NET, downloading models from Hugging Face, and setting up the UIs with customization options. The video also demonstrates generating images with different models and settings, offering a comprehensive introduction to using Stable Diffusion 3 for both personal and commercial purposes, with a focus on workflow management and troubleshooting.


  • πŸ˜€ Stable Diffusion 3 has been released and this tutorial will guide you through its installation on two interfaces: StableSwarmUI and ComfyUI.
  • πŸ› οΈ To install StableSwarmUI on Windows, you may need to install Git and .NET 8 manually if you're using Windows 10, while Windows 11 handles this automatically.
  • πŸ”— Follow the provided links in the description to download necessary files and access the GitHub repository for StableSwarmUI.
  • πŸ“ Create a new folder outside of the program files directory for the installation process and ensure the downloaded .bat file is placed inside.
  • πŸ’Ύ The installation will download and install .NET 8, which is approximately 220 megabytes, and may take some time.
  • πŸ“ Read and agree to the MIT license terms for StableSwarmUI, noting that models like Stable Diffusion 3 are for personal use only, with commercial use requiring a license purchase.
  • 🎨 Choose customization settings during the installation process, such as theme selection, and proceed with the installation.
  • πŸ” After installation, you can update or launch the interface through the command window, and create shortcuts for easy access.
  • 🌐 Visit the Hugging Face website to download Stable Diffusion 3 models, agreeing to their non-commercial use terms.
  • πŸ–ΌοΈ Test the models in the Swarm UI by inputting prompts and generating images, noting the settings recommended for each model.
  • πŸ”„ For advanced users, the ComfyUI offers customization options and the ability to manage models, nodes, and workflows.
  • πŸ” Explore the Civit AI website for additional models and recommended settings to enhance your Stable Diffusion 3 experience.

Q & A

  • What is the title of the tutorial?

    -The title of the tutorial is 'Install Stable Diffusion 3 Locally: Step-by-Step with StableSwarmUI & ComfyUI'.

  • What are the two interfaces mentioned in the tutorial for using Stable Diffusion 3?

    -The two interfaces mentioned in the tutorial are StableSwarmUI and ComfyUI.

  • Is there a specific requirement for the operating system to install StableSwarmUI?

    -Yes, the tutorial demonstrates the installation on Windows, and it mentions that for Windows 10, you need to manually install git and .NET 8, while for Windows 11, the process is done automatically.

  • What is the purpose of the bat file provided in the tutorial?

    -The bat file is used to download and install the necessary components for StableSwarmUI, including .NET 8 and git, and to initiate the installation process.

  • What is the MIT license mentioned in the tutorial?

    -The MIT license is the license under which the StableSwarmUI is released. It allows for personal use but requires a commercial license for any commercial use.

  • How can you customize the installation of StableSwarmUI?

    -You can customize the installation of StableSwarmUI by choosing different themes and settings during the installation process.

  • What is the recommended model to download from the Hugging Face website for Stable Diffusion 3?

    -The tutorial recommends downloading the 'sd3 medium' model from the Hugging Face website.

  • What are the recommended settings for generating an image with the Stable Diffusion 3 model in the tutorial?

    -The recommended settings include using 28 steps for CFG scale, 4.5 for the CFG scale, enabling the sampler DPM Plus+ 2m, and selecting sgm uniform for the scheduler.

  • How can you update the StableSwarmUI after installation?

    -To update the StableSwarmUI, you can click on the 'update' option in the interface, which corresponds to your operating system.

  • What is the ComfyUI manager mentioned in the tutorial and what is its purpose?

    -The ComfyUI manager is a tool that helps to install custom nodes, update models, and manage workflows within the ComfyUI interface.

  • How can you access the recommended settings for each model on the CIVIT AI website?

    -You can access the recommended settings by navigating to the model's page on the CIVIT AI website and checking the information provided there.

  • What is the process for installing ComfyUI as described in the tutorial?

    -The process for installing ComfyUI involves downloading a zip file, extracting its contents, navigating to the new folder, and running the 'Run Nvidia GPU dobat' file to launch the interface.



πŸš€ Introduction to Installing Stable Diffusion 3

The video tutorial begins by introducing the release of Stable Diffusion 3 and the two interfaces available for use: Swarm UI and Comfy UI. The speaker opts to demonstrate the installation process on Windows, highlighting the prerequisites for Windows 10 and the automatic process for Windows 11. The audience is guided through downloading a batch file, setting up a new folder, and running the installer, which includes downloading .NET 8 and configuring Git. The tutorial also covers the Swarm UI's installation, customization options, and legal notices regarding the MIT license and personal use limitations.


πŸ“š Navigating Hugging Face and Model Installation

The script continues with instructions on how to access and download Stable Diffusion 3 models from the Hugging Face website. It details the process of creating an account, verifying email, and agreeing to terms for non-commercial use. The speaker then explains how to select and download specific models, such as the 'sd3 medium' version, and how to integrate these models into the Swarm UI by using the refresh button and model selection options. Additionally, the video demonstrates how to generate images using various settings, resolution options, and prompts, emphasizing the first-time download of necessary files and the use of text encoders.


πŸ–ΌοΈ Exploring Model Settings and Customization

This paragraph delves into the customization of model settings within the Swarm UI, discussing recommended configurations for different models like Juggernaut and sd3. It explains how to adjust steps, CFG scale, and sampling settings for optimal image generation. The tutorial also touches on the use of text encodings and the impact of RAM usage, suggesting the selection of appropriate options based on the capabilities of the user's video card. The process of saving generated images and accessing them in the output folder is also covered, along with the option to create shortcuts for easier access.


πŸ”§ Installing and Configuring Comfy UI

The script shifts focus to the installation of Comfy UI, providing a step-by-step guide for downloading, extracting, and launching the interface. It mentions the need for an Nvidia GPU and the use of a specific batch file to run the interface. The tutorial also introduces the Comfy UI manager for installing custom nodes, updating models, and managing the UI. The speaker demonstrates how to create a shortcut for Comfy UI, change its icon, and use it to launch the interface, highlighting the additional manager button for accessing advanced options.


🌐 Integrating Models and Workflows in Comfy UI

This section outlines the process of importing Stable Diffusion 3 models into Comfy UI, including the placement of models in the appropriate folders and the use of the manager to load and test models. The script discusses the use of workflows, the installation of missing nodes, and the customization of workflow settings for different models. It also shows how to save and organize workflows, troubleshoot node errors, and explore the workflow gallery for additional options. The tutorial emphasizes the importance of checking model compatibility and the potential for conflicts with custom nodes.


🎨 Testing Models and Workflows

The final paragraph demonstrates the testing of various models and workflows within Comfy UI, showcasing the generation of images using different prompts and settings. It highlights the ability to save generated images and the process of troubleshooting node errors by installing missing components. The script also encourages exploring the workflow gallery and customizing settings for optimal results. The tutorial concludes with an invitation to join a Discord server for further discussions and sharing of AI-generated images, and mentions an additional YouTube channel focused on AI experiments.

πŸ‘‹ Conclusion and Call for Engagement

In the concluding paragraph, the speaker thanks the audience for watching and encourages them to like the video if they found it useful. A piece of background music is also noted, signaling the end of the tutorial.



πŸ’‘Stable Diffusion 3

Stable Diffusion 3 is an advanced AI model for generating images from text prompts. It is a significant update from previous versions, offering enhanced capabilities and features. In the video, the tutorial focuses on installing this model locally, allowing users to utilize it through two different interfaces, demonstrating its importance as a core component of the video's content.


StableSwarmUI is one of the two interfaces introduced in the video for using Stable Diffusion 3. It is a user interface developed by Stability AI and is still in beta, as mentioned in the script. The tutorial provides a step-by-step guide on how to install and customize this interface on Windows operating systems, highlighting its role as a primary tool for interacting with the AI model.


ComfyUI is the second interface option presented in the video for working with Stable Diffusion 3. It offers a different set of features and customization options compared to StableSwarmUI. The script walks viewers through the process of installing ComfyUI, emphasizing its user-friendliness and the additional functionalities it provides for managing AI models and workflows.


Git is a version control system used for tracking changes in source code during software development. In the context of the video, git is required for the installation process of Stable Diffusion 3, as it is used to clone repositories and manage updates. The script instructs viewers on installing git if they are using Windows 10, showing its necessity for the setup.


.NET is a free, cross-platform, open-source developer platform for building all types of applications. The script mentions the need to install .NET 8 as part of the prerequisites for setting up Stable Diffusion 3 on Windows, underlining its role as a foundational component for running the AI model.

πŸ’‘Hugging Face

Hugging Face is a company that provides a platform for developers to share and collaborate on machine learning models. In the video, the Hugging Face website is the source for downloading Stable Diffusion 3 models, emphasizing its importance as a hub for accessing and utilizing AI models.


In the context of AI, models refer to the trained algorithms that perform specific tasks, such as image generation from text prompts. The script discusses various models like 'sd3 medium' and 'Juggernaut XL', detailing the process of downloading and integrating them into the user interfaces, which is central to the video's instructional theme.


A workflow in the video refers to a series of steps or processes that the AI follows to generate images based on user inputs. The script introduces the concept of workflows in ComfyUI, explaining how to load, save, and manage different workflows for various image generation tasks, showcasing the flexibility and customization available to users.

πŸ’‘Text Encoders

Text encoders are components of AI models that convert text prompts into a format that the model can understand and use to generate images. The video script mentions downloading 'clip G' and 'clip L' models as text encoders, which are essential for the Stable Diffusion 3 model to interpret user prompts correctly.

πŸ’‘Legal Notice

The legal notice mentioned in the script refers to the licensing terms and conditions associated with the use of Stable Diffusion 3 and the StableSwarmUI. It distinguishes between personal and commercial use, highlighting the importance of adhering to the MIT license for non-commercial purposes and purchasing a license for commercial applications.


The term 'generate' in the video script refers to the action of creating an image using the AI model based on the provided text prompts and selected settings. It is a key action within the user interfaces, as the script demonstrates the process of generating images with different models and settings, illustrating the practical application of the AI technology.


Stable Diffusion 3 has been released and is available for installation.

Two interfaces for using Stable Diffusion 3 are introduced: StableSwarmUI and ComfyUI.

StableSwarmUI is still in beta and can be installed on various operating systems.

Windows 10 users need to manually install git and .NET 8 for StableSwarmUI.

Windows 11 automates the installation of git and .NET 8.

A bat file is provided for downloading and installing StableSwarmUI.

Users should create a new folder outside of the program files for installation.

The installation process includes downloading .NET 8, which is around 220 megabytes.

A legal notice states that StableSwarmUI is under the MIT license for personal use only.

Commercial use of the models requires purchasing a license.

Customization options are available during the installation of StableSwarmUI.

Users can choose to download models during installation or do so separately.

The installation process concludes with the launch of the StableSwarmUI interface.

Instructions for updating and launching the interface are provided.

Hugging Face website is used to download Stable Diffusion 3 models.

Models are available in different sizes with the smallest being the sd3 medium.

The process of loading and using models in the StableSwarmUI interface is explained.

Settings and options for generating images with Stable Diffusion 3 are detailed.

The video provides a step-by-step guide to installing ComfyUI as an alternative interface.

ComfyUI offers a manager tool for installing custom nodes and models.

Workflows can be imported and customized within ComfyUI.

The video demonstrates generating images using different models and settings.

Troubleshooting tips for dealing with missing nodes and workflow errors are given.

The presenter invites viewers to join a Discord server for AI tool discussions and sharing.