​Stable Diffusion WebUI Series Part 1: How to Install? Step-by-Step Guide.

1. Download Stable Diffusion WebUI

This tutorial was originally written in 2023 when Stable Diffusion WebUI was gaining popularity. Looking back today, installing and using Stable Diffusion WebUI has become much simpler, with many third-party teams offering out-of-the-box packages. Nevertheless, I’ve kept this guide here, some users might still find it useful.

Here are two methods. If you don’t have reliable network or do not know how to use git, I recommend the second option.

 

1.1 Method 1: Download via Git

 

1. Ope na Git CMD. Enter and execute the following command
2. git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
3. Expected output

4. Cloning into 'stable-diffusion-webui'...
   
   remote: Enumerating objects: 33286, done.
   
   remote: Counting objects: 100% (68/68), done.
   
   remote: Compressing objects: 100% (49/49), done.
   
   remote: Total 33286 (delta 36), reused 35 (delta 16), pack-reused 33218
   
   Receiving objects: 100% (33286/33286), 34.62 MiB | 2.21 MiB/s, done.
   
   Resolving deltas: 100% (23307/23307), done.

 

1.2 Method 2: Direct Download via URL

1. https://github.com/AUTOMATIC1111/stable-diffusion-webui
2. 

2. Setting Up the Environment with Anaconda

 

2.1 Create a Conda Environment

1. Create a dedicated environment named env_sdw2 using Python 3.10.6
2. Press Y to confirm when prompted.

3. conda create -n env_sdw2 python=3.10.6

   1. 

 

2.2 Activate Conda Environment

1. Navigate to the project’s root folder.
2. cd C:WorkstationPythonAIstable-diffusion-webui
3. open cmd
4. Activate the Conda environment via this command

5. conda activate env_sdw2

 

3. Launching the Installation

1. Run the WebUI launcher script：webui-user.bat
2. 
3. First-time setup may take a while—be patient as dependencies download and install.
4. 

 

 

 

4. ​Stable Diffusion WebUI vs ComfyUI?

I know ComfyUI is all the rage now, and I use it too. But I’ve stuck with Stable Diffusion WebUI because back in 2023, I generated some truly amazing images with it.

I’ve tried replicating those results in ComfyUI using identical parameters and settings, but they just fall short of expectations.

Has anyone else encountered this issue? If so, I’d greatly appreciate any insights or suggestions!