How to install Stable Diffusion WebUI AUTOMATIC1111 on Windows

Introduction

Stable Diffusion, a machine learning model that's open-source, has the ability to generate images from text, modify images based on text, or enhance low-resolution or low-detail images. It has been trained on billions of images and can produce results that are on par with those generated by DALL-E 2 and MidJourney.

Stable Diffusion web UI is A browser interface based on Gradio library for Stable Diffusion. We will go through how to install the popular Stable Diffusion software AUTOMATIC1111 on Windows step-by-step. After this tutorial, you can generate AI images on your own PC.

System Requirements

Windows 10, 11
Git,Conda, Python 3.10
16GB of RAM, 30G SSD Disk Space
Nvidia graphics card with at least 8GB of VRAM

Installation steps

Step 1. Install Chocolatey

Chocolatey is a machine-level, command-line package manager and installer for software on Microsoft Windows. We will use Chocolatey to install Git and Conda. First open powershell.exe as an administrator and execute the following code:
Set-ExecutionPolicy Bypass -Scope Process -Force; [System.Net.ServicePointManager]::SecurityProtocol = [System.Net.ServicePointManager]::SecurityProtocol -bor 3072; iex ((New-Object System.Net.WebClient).DownloadString('https://community.chocolatey.org/install.ps1'))
powershell install chocolatey

Step 2. Install Git and Conda

Now we can easily use choco to install git and conda tools, please execute the following command line:
# install git
choco install git
# install conda
choco install anaconda3
Note: You can also install Git and Conda manually without choco.

Step 3. Download Stable Diffusion Repository

Download the stable-diffusion-webui repository as .zip and extract or use git to clone.:
PS D:\github>git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
Cloning into 'stable-diffusion-webui'...
remote: Enumerating objects: 18979, done.
remote: Counting objects: 100% (573/573), done.
remote: Compressing objects: 100% (248/248), done.
remote: Total 18979 (delta 359), reused 480 (delta 325), pack-reused 18406
Receiving objects: 100% (18979/18979), 28.88 MiB | 9.87 MiB/s, done.
Resolving deltas: 100% (13233/13233), done.
Note: Some files exceed multiple gigabytes, make sure you have space first.

Step 4. Create Python 3.10.11 Environment

Open Anaconda Navigator, and create StableDiffusion Env like below:
conda create python 3.10 env
Open StableDiffusion Env Terminal:
conda open python 3.10 env
Note: You can also install Python 3.10.11 manually without Anaconda. Newer version of Python does not support torch, and checking "Add Python to PATH".

Step 5. Download Stable Diffusion Models

Models, sometimes called checkpoint files, are pre-trained Stable Diffusion weights intended for generating general or a particular genre of images. Go to CompVis or Stable Diffusion Art and download any model you like, for example 1.5 and put it to models directory.

(StableDiffusion) D:\github\stable-diffusion-webui\models\Stable-diffusion\
download sd models

Step 6. Start Up WebUI Server

(StableDiffusion) D:\github\stable-diffusion-webui>webui.bat --xformers
venv "D:\github\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.11 | packaged by Anaconda, Inc. | (main, Apr 20 2023, 18:56:50) [MSC v.1916 64 bit (AMD64)]
Commit hash: 5ab7f213bec2f816f9c5644becb32eb72c8ffb89
Installing xformers
Collecting xformers==0.0.17
  Downloading xformers-0.0.17-cp310-cp310-win_amd64.whl (112.6 MB)
……
Model loaded in 12.8s (calculate hash: 6.1s, load weights from disk: 0.3s, create model: 1.7s, apply weights to model: 1.1s, apply half(): 1.2s, move model to device: 1.0s, load textual inversion embeddings: 1.3s).
Running on local URL:  http://127.0.0.1:7860
start stable diffusion webui server

Make Your AI images.

Use your browser to open the local Stable Diffusion URL. At the field for Enter your prompt, type a description of the image you want to generate. Then click the Generate image button. Here are some Best Stable Diffusion 1.5 Prompts that you can refer to.

Prompt:
Pixar style little girl, 4k, 8k, unreal engine, octane render photorealistic by cosmicwonder, hdr, photography by cosmicwonder, high definition, symmetrical face, volumetric lighting, dusty haze, photo, octane render, 24mm, 4k, 24mm, DSLR, high quality, 60 fps, ultra realistic

use stable diffusion create a image

Prompt:
(masterpiece:1.0), (best quality:1.4), (ultra highres:1.2), (photorealistic:1.4), (8k, RAW photo:1.2), (soft focus:1.4), 1 woman, posh, (sharp focus:1.4), (korean:1.2), (american:1.1), detailed beautiful face, black hair, (detailed open blazer:1.4), tie, beautiful white shiny humid skin, smiling

Negative Prompt:
illustration, 3d, sepia, painting, cartoons, sketch, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, normal quality, ((monochrome)), ((grayscale:1.2)),newhalf, collapsed eyeshadow, multiple eyebrows, pink hair, analog, analogphoto

use stable diffusion create another image

Conclusion

Stable Diffusion stands out among AI art models because you can run it locally on your PC, allowing you to fine-tune the algorithm-generated art until you’re satisfied with the results. If you already have a powerful gaming pc or server, you’re only clicks away from making incredible art anywhere.

GPU Mart offers professional GPU hosting services that are optimized for high-performance computing projects. Here we recommend 4 server plans suitable for running stable diffusion. Please feel free to start your journey boldly, we are happy to help with any difficulties.

Advanced GPU-RTX 3060 Ti

209.00/m
1M3M12M24M
Order Now
  • 128GB RAM
  • Dual 12-Core E5-2697v2report
  • 240GB SSD + 2TB SSD
  • 100Mbps-1Gbpsreport
  • OS: Windows / Linux
  • GPU: Nvidia GeForce RTX 3060 Tireport
  • Microarchitecture: Ampere
  • Max GPUs: 2report
  • CUDA Cores: 4864
  • GPU Memory: 8GB GDDR6
  • FP32 Performance: 16.2 TFLOPSreport

Advanced GPU-A5000

269.00/m
1M3M12M24M
Order Now
  • 128GB RAM
  • Dual 12-Core E5-2697v2report
  • 240GB SSD + 2TB SSD
  • 100Mbps-1Gbpsreport
  • OS: Windows / Linux
  • GPU: Nvidia RTX A5000report
  • Microarchitecture: Ampere
  • Max GPUs: 2report
  • CUDA Cores: 8192
  • GPU Memory: 24GB GDDR6
  • FP32 Performance: 27.8 TFLOPSreport

Enterprise GPU-A40

369.00/m
1M3M12M24M
Order Now
  • 256GB RAM
  • Dual E5-2697v4report
  • 240GB SSD + 2TB SSD + 2TB NVMe
  • 100Mbps-1Gbpsreport
  • OS: Windows / Linux
  • GPU: Nvidia A40report
  • Microarchitecture: Ampere
  • Max GPUs: 1
  • CUDA Cores: 10,752
  • Tensor Cores: 336
  • GPU Memory: 48GB
  • FP32 Performance: 37.48 TFLOPSreport

Enterprise GPU-V100

369.00/m
1M3M12M24M
Order Now
  • 256GB RAM
  • Dual E5-2697v4report
  • 240GB SSD + 2TB SSD + 2TB NVMe
  • 100Mbps-1Gbpsreport
  • OS: Windows / Linux
  • GPU: Nvidia V100report
  • Microarchitecture: Volta
  • Max GPUs: 1
  • CUDA Cores: 5,120
  • Tensor Cores: 640
  • GPU Memory: 16GB
  • FP32 Performance: 14 TFLOPSreport
Contact Us and Get a 3-Day Trial Now!
Leave us a note when purchasing, or contact us to apply a trial GPU server. You have enough time to test the performance, network latency, compatibility, multiple instance capacity, etc.
Recommend Friends, Get Credits
$20 will be credited to your account once you recommend a new client to purchase servers. Rewards can be superimposed.
Hosted Nvidia GPU servers