How to Use AUTOMATIC1111 WebUI – Full Beginners Guide

guide-to-automatic1111-feature-image

If you click on a link and make a purchase, I may receive a small commission. As an Amazon affiliate partner, I may earn from qualifying purchases.
Read our disclosure.

What Is AUTOMATIC1111?

AUTOMATIC1111 is a Stable Diffusion WebUI (Web User Interface) based on the Gradio library. You can run the Web UI on your web browser.

The AUTOMATIC WebUI has received over 105k stars on GitHub and has been forked over 21k times. The majority of the commits done on GitHub are from AUTOMATIC1111 and dfaker. Over the lifetime of its development, more than 480 people have contributed to creating and refining the WebUI.

AUTOMATIC1111 is considered one of the best WebUI for Stable Diffusion.

Installation And Configuration for Windows

To run AUTOMATIC1111’s WebUI and Stable Diffusion, you need the following files:

automatic1111-download-github
From the Code button, you can see the HTTPS address for the GitHub project.

Note:

  • When installing Git for Windows, use the default settings and options.
  • When installing Python, remember to select “Add python.exe to PATH” at the beginning of the installation.
  • Video tutorial for installing Stable Diffusion.

AUTOMATIC WebUI Installation

Create a folder for the C: drive. C:\Users\*\*\*\*\STABLE DIFFUSION\

When you’ve created the folder, go to the folder’s navigation bar and type cmd, this will open a cmd prompt for the folder you just created.

github-automatic1111-installation-clone
The GitHub clone command will pull the stable-diffusion-webui to your computer straight from GitHub.

Write to the cmd prompt: git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git

This will pull the stable-diffusion-webui project (files and folders) to your computer straight from GitHub.

AUTOMATIC1111 webui-user file settings

automatic1111-webui-user-batch-file-modification-location-how-to

To make sure the WebUI is always at the latest version, you can write git pull and pause (to be able to read the cmd screen when the update is in the process) to the webui-user.bat -file. You can do this by selecting the webui-user file (Windows Batch File), right-clicking the file, and selecting ‘Edit in Notepad’.

You can find the webui-user.bat file (Windows Batch File) in the following folder: C:****\STABLE DIFFUSION\stable-diffusion-webui

It’s also the same file you use to launch AUTOMATIC1111’s WebUI.

webui-user-bat-file-modification
webui-user-bat -file modification.

Additional parameters for various use cases (After COMMANDLINE_ARGS= (enter your desired parameters)):

  • Example: COMMANDLINE_ARGS=--medvram (check the image above for correct formatting).
  • If you have 4GB-6GB VRAM, use --medvram.
  • If you have 2GB VRAM, use --lowvram.
  • You can also try --xformers, as many users have seen great results with that, some reporting 4x faster results than with --medvram.
  • If you are getting ‘Out of memory’ errors on either of these, add --always-batch-cond-uncond to the other arguments.

Using the WebUI

automatic1111-webui-user-interface-how-it-looks
What the AUTOMATIC1111 user interface looks like.

You can launch AUTOMATIC1111’s WebUI by double-clicking the webui-user.bat -file. This will open a cmd (Command) window, and when the script has run, a web-based user interface will be automatically launched on your browser. Do not close the cmd windows, however, as AI image generation needs it to be open.

automatic1111-webui-collecting-pytorch

Note: If you see that the CMD is ‘Collecting torch,’ that is completely normal or that the program is installing stable-diffusion-v1-5 from huggingface website, that is normal too. It usually does this process only once. It will also download other needed resources which means that installing Stable Diffusion and AUTOMATIC1111 for the first time might take awhile.

automatic1111-webui-interface-guide
1. Choose which checkpoint model to use. 2. Normal (positive) text prompt. 3. Negative text prompt. 4. Settings for sampling method, sampling steps, resolution, etc. 5. Generate AI image.

Image generation settings

  • Stable Diffusion checkpoint: Select the model you wish to use for image creation.
  • txt2img (Text-to-image) positive text prompt: Text prompt that determines what you are trying to create.
  • txt2img (Text-to-image) negative text prompt: Determines what you don’t want to see in the image.
  • Sampling method: Which algorithm to use for image creation.
  • Sampling steps: How many times the AI generator improves the image. Lower values will give you bad results. Higher values take longer to produce.
  • Restore faces: Improves faces in pictures. Use the Settings tab to control the face restoration method. Settings -> Face Restoration.
  • Tiling: For creating seamless patterns
  • Hires. fix: Partially render your image at a lower resolution, upscale it, and then add details at a high resolution
  • Width and Height: Controls the image resolution. Higher values require more VRAM.
  • Batch count: How many images to create in one single generation run.
  • Batch size: How many images to create in a single batch. Increases VRAM usage.
  • CFG (Classifier Free Guidance) Scale: Controls how precisely the text prompt is used. Lower values put more emphasis on creativity.

You can read more about AUTOMATIC1111’s features from GitHub.

Using Models

Currently, the best source for Stable Diffusion models is Civitai. From the site, you can explore all sorts of models, Checkpoints, LoRAs, Hypernetworks, Textual Inversions (embeddings), etc. Download the model you are most interested in and place it in the appropriate folder:

ModelDirectory/FolderFile typesHow to use in prompt
Checkpoints*\stable-diffusion-webui\models\Stable-diffusion*.ckpt, *.safetensors(select a checkpoint model from the upper left-hand corner of the Web UI)
Hypernetworks*\stable-diffusion-webui\models\hypernetworks*.pt, *.ckpt, *.safetensors<hypernet:filename:multiplier>
LoRA*\stable-diffusion-webui\models\Lora*.pt<lora:filename:multiplier>
Textual Inversion*\stable-diffusion-webui\embeddings*.pt, *.safetensors, imagesembedding’s filename
ControlNet Models (preprocessor)*\stable-diffusion-webui\extensions\sd-webui-controlnet\models*.pth, *.yamlSelect from the WebUI
Wildcards*stable-diffusion-webui\extensions\sd-dynamic-prompts\wildcards*.safetensorsWrite a normal prompt using words related to the wildcard
Table showing models, where to copy them, and how to use them.

Check out: The best Stable Diffusion models

Using Extensions

You can download extensions straight from AUTOMATIC1111’s WebUI. Useful extensions to try out are Dreambooth, Wildcards, and ControlNet.

automatic1111-webui-extensions-how-to

You can find extensions from the WebUI: Extensions -> Available -> Load from: https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui-extensions/master/index.json

After installing an extension, you should completely restart the WebUI. From the ‘Installed’ tab, you can check which extensions you’ve installed and can already use with the WebUI.

automatic1111-controlnet-extension-installation

Note: When installing an extension, you might get a white overlay screen. If you scroll up the browser screen, you will see a small download countdown timer as a grey text. Wait for it to finalize for the white overlay screen to go away.

Troubleshooting And Known Issues

Hardware Requirements For Running Stable Diffusion

Minimum hardware requirements for using Stable Diffusion:

Running AUTOMATIC1111 In Different Operating Systems

You can run Stable Diffusion on Mac, Windows, and Linux.

Stable Diffusion installation guides for different operating systems:

How to Run AUTOMATIC1111 WebUI in the Cloud

rundiffusion-automatic1111-in-cloud
RunDiffusion’s homepage.

RunDiffusion is a comprehensive cloud-based service that offers Stable Diffusion and AUTOMATIC1111 WebUI to run through a cloud service. It provides a fully managed environment in the cloud, allowing you to focus on your work without the hassle of running code, installing packages, or dealing with errors.

With RunDiffusion, you can launch sessions in just 90 seconds and enjoy a seamless experience. The service offers Automatic1111 and InvokeAI WebUI software, ensuring that sessions always start with the latest bleeding-edge technology.

Pricing starts at $0.50/hr (15 minutes free), offering 60+ top AI art models (continuously adding more as per customer demand).

Check out: Available models in RunDiffusion

Templates are readily available, enabling you to quickly start creating without any setup delays.

Privacy and security are prioritized in RunDiffusion. Private sessions are available, ensuring that users have exclusive access to their workspaces without sharing space with others. Encryption and integrated file browsing further enhance the security and control over files and data.

The service offers real-time trading capabilities, allowing you to download entire directories and save images effortlessly. A smart timer feature helps you manage costs effectively by setting session durations and avoiding expensive overcharges. Unused time is credited back to your balance if a session is ended early.

By subscribing to the Creator’s Club, you gain exclusive access to Dreambooth, which enables the injection of captivating elements into custom models, and model merging capabilities for creating hybrid models. Advanced training like Textual Inversion, LoRA, and Hypernetworks are also available.

RunDiffusions proprietary AI art models:

Feature image credits.

Search
artist-profile-picture-avatar

Okuha

Digital Artist

I’m a digital artist who is passionate about anime and manga art. My true artist journey pretty much started with CTRL+Z. When I experienced that and the limitless color choices and the number of tools I could use with art software, I was sold. Drawing digital anime art is the thing that makes me happy among eating cheeseburgers in between veggie meals.

More Posts

Thank You!

Thank you for visiting the page! If you want to build your next creative product business, I suggest you check out Kittl!