COMPLETE CRASH COURSE | Install + Guide | Stable Diffusion AUTOMATIC1111 SDUI

Stable Diffusion AUTOMATIC1111 SDUI is a powerful tool. This complete crash course shows you how to install and use most of the features available in the tool. Get from nothing to a power user in no time!

Sorry about the noise in the background near the start. Super annoying.

Arguments: --autolaunch --update-check
VRAM Arguments: --medvram OR --lowvram

Timestamps:
0:00 - Intro/Explanation
0:30 - Requirements
0:46 - Download Python
1:18 - Download Git
1:50 - Download AUTOMATIC1111 SDUI
3:04 - Launch Arguments
4:03 - Manually updating SDUI
4:20 - Installing AUTOMATIC1111 SDUI
5:35 - GPU VRAM & other Launch Arguments/Optimization
7:27 - Generating an image (txt2img) Crash Course
8:13 - Textual Inversion, Hypernetworks, Checkpoints, Lora
8:35 - Style Transfer/Inpainting (img2img) Crash Course
10:03 - Upscaling (Extras)
11:33 - Hires Fix (Upscaling when generating)
12:40 - PNG Info (get prompts from images_)
13:35 - Checkpoint Merger
14:24 - Checkpoint (ckpt) vs Safetensors
15:15 - Train tab
15:45 - Settings
16:04 - Extensions
16:48 - Final notes + Cloud-based SDUI
17:50 - Downloading Models, Loras, and more
19:12 - xformers for extra performance!

#StableDiffusion #SDUI #AI
-----------------------------
-----------------------------
-----------------------------
🖥️ My Current Hardware (Links here are affiliate links. If you click one, I'll receive a small commission at no extra cost to you):
🎙️ My Current Mic/Recording Gear:

Everything in this video is my personal opinion and experience and should not be considered professional advice. Always do your own research and ensure what you're doing is safe.

[JoseProducts]

I do not know how you do it (not easy!) but you are good.

I have spent at least 10 hours looking for a good tutorial on how to install stable diffussion automatic1111. Yours is the best. And only 20 minutes long!!

Thanks

[Comenta-san]

Thanks a lot man. I stopped playing with image generation for a few months, but just installed this new A1111 and I'm having more fun than ever with it. A lot of improvements since I stopped.
It's crazy that you don't even need the hardware anymore

[mrdupeep]

Best SD setup tut I've found thus far, so to say- it worked perfect for me!

[iesdise]

My NVMe crashed a few weeks back, taking anything AI related with it. I've postponed the re-installation of everything, because it's that tedious.
I wasn't even looking for this guide in particular, but it's miles better than what I found before. Thanks for the great video, literally perfect.

[thefigureshow]

for anyone who had issues with download within the venv folder make sure in the scripts it says activate if not just try to redownload the program or manually reinstall the venv folder ( just saw he mentioned it)

[ondrej_]

Very informative and underrated video, thanks

[gabrielgennari]

Good morning! I am trying to install Automatic1111 and I can't get it to work at all. I'm getting the error "exit code 1."

Is there any way you can help me? Maybe a Zoom call or something like that?

I've tried everything and I can't make it work... Thank you!

[dziku]

Not working, endless stuck on installing requirements.

[ceciliaamita]

Thanks for the awesome video! Unfortunately I always get an error message if I try to create an image:

"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.
"
No matter what I do, the fault stays. Any idea how to fix this?

edit: switching to --lowvram (for 8gb of video memory) and using an other sdxl model fixed this for now.

[YJR]

ERROR: Could not find a version that satisfies the requirement torch==2.1.2 (from versions: 2.2.0, 2.2.0+cu121, 2.2.1, 2.2.1+cu121, 2.2.2, 2.2.2+cu121, 2.3.0, 2.3.0+cu121, 2.3.1, 2.3.1+cu121)
ERROR: No matching distribution found for torch==2.1.2 is there a fix pls??

[OolTube]

How do you know the installation in the command window is done? Is there a DOS prompt at the end?

[sircasino]

Oh I see... hack the pentagon, find bigfoot, solve world hunger, then maybe you can generate an image. Whatever happened to press install?

[ujjawaltyagi]

Can you make a guide on how to train your own lora on local pc using a set of images collected from internet

[pheiyaa]

Thank you it worked! But I dont understand how to open it again? It opened after installatiion and thats it

[VertCPU]

The install didn't give me a .git repository... What do I do?

[WhoIsJohnblack]

Guys I am new around here, I just installed SD, its up to date and no matter what model or whatever prompt i choose, only a solid grey square appears. Can someone please help!!!

[sircasino]

7:28 Woah woah woah woah.... where did that window come from? How do I know the cmd.exe is done? Where do I go to get this window? I did the autolaunch and nothing happened. Edit: Ugh, so here's the thing, if you're working off an external drive it will refuse to work for you without a million issues resolved. I personally have no free space on the desktop, so I'm just screwed I guess.

[walrusmcgee]

At first it was saying git is not recognized, now it is saying "clone is not recognized as an internal or external command", starting to think this is more frustration than it's worth

[Lofi.Beats.]

i have this error " JSONDecodeError: Expecting value: line 1 column 1 (char 0)"
someone can help me :(

[brazzilianboy]

any error with torch, just uninstall latest python and go for Python 3.10.9