Install Stable Diffusion Locally (In 3 minutes!!)

This tutorial guides you through installing Stable Diffusion locally on your computer. It begins with creating accounts on GitHub and Hugging Face, then downloading necessary programs such as Windows Subsystem for Linux (WSL), Python, and the Stable Diffusion model. The process includes cloning the web UI from GitHub, copying the link, and pasting it into Git Bash. It also involves downloading the GIFGAN Face Restoration add-on for character creation and placing the downloaded files in the appropriate folders. After installing Python and setting the environment, you can run the main web UI user batch file to start the software. The video provides troubleshooting tips for slow systems and offers a shortcut URL for accessing the Stable Diffusion interface, where users can input prompts and generate images with various settings. The summary also mentions checking the command prompt for generation status and saving images under the 'outputs' folder.

Takeaways

• 📌 Create an account on GitHub and Hugging Face, both are free.
• 💻 If you're using Windows, download and install Git from getforwindows.org.
• 📂 Create a new folder on your C drive named 'AI' for the Stable Diffusion files.
• 🔗 Copy the web UI link from the video description and clone the repository using Git Bash.
• 📚 Download the latest version of Stable Diffusion (v1.4 at the time of the video) from Hugging Face.
• 🧩 Download the GIGANT Face Restoration add-on to enhance character creation.
• 🐍 Install Python 3.10.6, which is the version that worked for the video creator.
• 📁 Move the downloaded GIGANT Face Restoration file into the Stable Diffusion folder.
• 🔄 After installing Python, run the main web UI user batch file to start the installation process.
• ⏱ Be patient during the installation as it may take between 20 to 40 minutes.
• 🖥️ If the installation stalls, try pressing Enter on the black screen to resume the process.
• 🌐 Once completed, a URL will be provided; copy and paste it into your browser to access Stable Diffusion.
• 🖼️ You can save generated images from the interface and find them in the 'outputs' and 'images' folder.
• 💡 If you encounter performance issues, you may need to adjust the batch file settings as suggested in the video.

Q & A

What is the main purpose of the tutorial?

The main purpose of the tutorial is to guide users on how to install Stable Diffusion locally on their computer.

Who helped the author to create this tutorial?

A dedicated member of the patron support squad, known as Penguin Dragon, helped the author by walking them through the process on Discord.

What are the two websites mentioned for creating an account?

The two websites mentioned for creating an account are GitHub and Hugging Face.

What is the recommended graphics card setup for this tutorial?

The tutorial specifically mentions that the author is using an Nvidia graphics card, and notes that the process might be different for an AMD setup.

What program do you need to download for Windows?

For Windows, you need to download a program from getforwindows.org.

How do you install the Get program on Windows?

You install the Get program by going to your downloads, double-clicking the installer, agreeing to the policy, and accepting all recommended settings.

What is the process to clone the Stable Diffusion repository?

To clone the Stable Diffusion repository, you go to your C drive, create a new folder called AI, copy the folder's address, open Git Bash, type 'get space clone', paste the copied link, and press enter.

What version of Stable Diffusion is mentioned in the script?

The script mentions downloading the latest version of Stable Diffusion, which at the time was version 1.4.

How long did it take to download the cktp file?

It took about 20 minutes to download the cktp file.

What is the recommended version of Python for this tutorial?

The recommended version of Python for this tutorial is 3.10.6.

How long does the installation process typically take?

The installation process is likely to take between 20 to 40 minutes.

What should you do if the installation process takes more than an hour without any screen change?

If there is no change after an hour, you should click anywhere in the black screen or press enter to resume the download.

How can you resolve issues if you have a less powerful computer?

You can resolve issues by editing the batch file and inserting a specific piece of code provided in the script, then saving and trying to run the software again.

Outlines

00:00

🚀 Installing Stable Diffusion Locally

This paragraph provides a step-by-step guide to installing Stable Diffusion locally on a Windows machine. It begins by acknowledging the contribution of a patron named Penguin Dragon who helped the author understand the process. The user is instructed to create accounts on GitHub and Hugging Face, download necessary programs like Git for Windows, and use Git Bash to clone a repository. The guide also covers downloading Stable Diffusion version 1.4 from Hugging Face and the GIF began face restoration add-on. It continues with the installation of Python 3.10.6 and concludes with instructions on how to start the Stable Diffusion web UI, troubleshoot potential issues, and access the generated images.

Keywords

Stable Diffusion

Stable Diffusion refers to a type of machine learning model used for generating images from textual descriptions. In the video, it is the main software being installed for local use, allowing users to create images based on prompts they provide.

Local Installation

Local installation means setting up and running software on a personal computer rather than using it through a web service. The video provides a step-by-step guide on how to install Stable Diffusion locally, which is beneficial for users who want to use the software without an internet connection or prefer offline access.

Nvidia Graphics Card

An Nvidia graphics card is a type of hardware used for rendering images, videos, and 3D animations. It is mentioned in the video as the type of graphics card the presenter is using, which could imply that the installation process might differ for users with an AMD setup.

GitHub

GitHub is a web-based platform for version control and collaboration that allows developers to work on projects together. In the context of the video, users are instructed to create an account on GitHub to access the Stable Diffusion repository and clone it for local installation.

Hugging Face

Hugging Face is a company that provides tools for natural language processing and machine learning. In the video, users are directed to create an account on Hugging Face and download the latest version of Stable Diffusion from their platform.

Git Bash

Git Bash is a software package that provides a Bash emulation used to run Git from the command line on Windows. It is used in the video to execute commands for cloning the Stable Diffusion repository from GitHub.

Web UI

Web UI stands for Web User Interface, which is the method used in the video to interact with the Stable Diffusion software through a browser. The presenter instructs viewers on how to access and use the Web UI after the software has been installed.

Python

Python is a high-level programming language widely used for general-purpose programming. In the video, it is one of the prerequisites for running Stable Diffusion, and the presenter specifies the version (3.10.6) that worked for them.

GIFGAN Face Restoration

GIFGAN Face Restoration is an add-on for Stable Diffusion that assists in enhancing the quality of generated character images. The video mentions downloading this add-on to improve the user experience when creating images.

CKTP File

A CKTP file is a specific type of file format associated with machine learning models. In the context of the video, it refers to the Stable Diffusion model file that needs to be downloaded and placed in the models directory for the software to function correctly.

Batch File

A batch file is a type of script file in DOS, OS/2 and Windows that consists of a series of commands to be executed by the command-line interpreter. In the video, the presenter instructs users to double-click a main web UI user batch file to start the installation process of additional components.

Prompt

In the context of Stable Diffusion, a prompt is a textual description that the user inputs to guide the image generation process. The video explains how users can type in their prompts and generate images based on those inputs.

Highlights

The tutorial provides a step-by-step guide to install Stable Diffusion locally.

A patron support member, Penguin Dragon, volunteered to guide through the process.

An Nvidia graphics card is mentioned as the setup used for the tutorial.

AMD setup users might experience different steps in the process.

Creating an account on GitHub and Hugging Face is required, both are free.

Downloading and installing 'getforwindows.org' is part of the setup process.

A new folder named 'AI' is created on the C drive for the installation.

The link for the web UI is obtained from the video description.

Git Bash is used to clone the Stable Diffusion repository.

The latest version of Stable Diffusion (1.4 at the time) is downloaded from Hugging Face.

The GIF began face restoration add-on is recommended for character creation.

Python 3.10.6 is the version used in the tutorial.

The GIF Gan face restoration file and cktp file are placed in specific folders.

The main web UI user batch file is used to start the installation of additional components.

The installation process can take between 20 to 40 minutes.

If the process stalls, clicking anywhere on the black screen can resume the download.

A URL is provided to access the Stable Diffusion interface in a web browser.

The interface allows users to input prompts and generate images with various settings.

Saved images can be found in the 'outputs' and 'images' directory.

The generation status can be checked via the command prompt.

For less powerful computers, a code snippet can be added to the batch file to resolve issues.