Install Stable Diffusion Locally: A Complete Step by Step Guide for Archviz

We're learning how to install Stable Diffusion! Unlike other tools like Midjourney or DALL-E, installing Stable Diffusion on your local PC offers unrestricted creative freedom, allowing you to use custom-trained images or explore various AI models. This comprehensive tutorial will guide you through the steps of setting up Stable Diffusion on your computer, from creating necessary accounts to downloading software and running the application.
Discover how to download Stable Diffusion models from Hugging Face, set up your environment in Git Bash, and use the Automatic1111 user interface for an enhanced experience. Whether you're a digital artist, a 3D modeler, or simply curious about the capabilities of AI in creative processes, this tutorial is designed to get you started on generating your own AI-powered art.
github.com/AUTOMATIC1111/stab...
huggingface.co/CompVis/stable...
gitforwindows.org/
www.python.org/downloads/
🔥 What You'll Learn:
• How to create accounts on Hugging Face and GitHub for accessing Stable Diffusion.
• Step-by-step instructions on downloading and installing the necessary software.
• How to download Stable Diffusion models and set up your local environment for AI art generation.
• Tips on using the web UI for creating stunning AI-generated images with various customization options.
👉 This tutorial is perfect for anyone interested in AI art generation, digital artists looking to expand their toolset, and tech enthusiasts eager to explore the capabilities of Stable Diffusion.
_____________________________________________
00:00 Intro
00:05 Create Hugging Face and Github accounts
00:28 Download and Install Git for Windows
00:52 Install Stable Diffusion web UI
02:10 Download Stable Diffusion Models
02:50 Download and Install Python
03:30 Add Stable Diffusion Models to Folder
04:01 Run the WebUI
04:43 Generate your first image
05:54 Outro
_____________________________________________
Enjoyed the video? Comment below! 💬
⭑ Subscribe to Archviz Explained / archvizexplained
⭑ Enjoyed? Hit the like Button! 👍
_____________________________________________
#stablediffusion #AIartGeneration #digitalart #huggingface #github #archviz #CreativeAI #stablediffusionai #archviz

[@BrianAlmatti]

Finally, an actual tutorial that covers everything LOL.

[@ArchVizExplained]

Thank you for watching!

[@PriitKallas]

Thanks, it worked!

[@ArchVizExplained]

Glad it helped, Thank you for watching!

[@otheroption3182]

NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.

[@hammiirasekh4648]

Hi dear, thanks for the tutorial, but I did open the webui-user and wait until it finished It didn't give any web address.

[@AmilcarJoaquim-iz6db]

Hello. You can do this installation on a laptop with Intel(R) Core(TM) i7-3537U CPU @ 2.00GHz 2.50 GHz and 8 RAM. Thank you

[@MikaGrimGal]

When I attempt to use the python BAT file it comes up with this error. Installing torch and torchvision C:\Ai\stable-diffusion-webui\venv\Scripts\python.exe: No module named pip Traceback (most recent call last): File "C:\Ai\stable-diffusion-webui\launch.py", line 48, in main() File "C:\Ai\stable-diffusion-webui\launch.py", line 39, in main prepare_environment() File "C:\Ai\stable-diffusion-webui\modules\launch_utils.py", line 380, in prepare_environment run(f'"{python}" -m {torch_command}', "Installing torch and torchvision", "Couldn't install torch", live=True) File "C:\Ai\stable-diffusion-webui\modules\launch_utils.py", line 115, in run raise RuntimeError(" ".join(error_bits)) RuntimeError: Couldn't install torch. Command: "C:\Ai\stable-diffusion-webui\venv\Scripts\python.exe" -m pip install torch==2.1.2 torchvision==0.16.2 --extra-index-url download.pytorch.org/whl/cu121 Error code: 1 Press any key to continue . . .

[@riccardogaleazzi7915]

me too

[@penguinysquad]

what version of python do u have?

[@musiccalgary]

What if you don't want to install old python?

[@ArchVizExplained]

Hi @musiccalgary, the developers of Automatic1111 officially recommend using Python 3.10.6 for the most stable experience. This version has been thoroughly tested and is most likely to work without issues. You might be able to run Automatic1111 with a newer version of Python, but it's generally not recommended as you could find comparability problems with key libraries on newer versions of Phyton. Thank you for watching!

[@JpKCS]

You shouldn't set batch size to create multiple variations, you should use batch count instead - it's easier for your PC! 🚨

[@ArchVizExplained]

Hey @JpKCS Thanks for the tip! You’re absolutely right, using batch count instead of batch size is definitely easier on the PC. I appreciate you pointing that out. Thanks for helping out, and keep those awesome suggestions coming!

[@AmilcarJoaquim-iz6db]

Hello. You can do this installation on a laptop with Intel(R) Core(TM) i7-3537U CPU @ 2.00GHz 2.50 GHz and 8 RAM. Thank you

[@JpKCS]

to be fair - the most important is GPU if you don't have one it will most likely be unusable.