Guide Installing Stable Diffusion Webui & Nudifying (Inpainting) Guide

  • Welcome to the Fakes / AI / Deepfakes category
    When posting AI generated content please include prompts used where possible.
Sort By Date Sort By Reaction Score
yemanongfr

yemanongfr

Lurker
Oct 20, 2023
1
0
4
0fya082315al84db03fa9bf467e3.png
kamikazenojihadist said:
Please, Log in or Register to view quotes
Click to expand...

in the stable-diffusion-webui folder where your "webui-user.bat" file is, right click webui-user.bat and click edit and it should open in notepad, should look something like this:

Code:
Please, Log in or Register to view codes content!

After "set COMMAND_LINE_ARGS=" add this " --no-half --precision full" should solve any problems you have.
Btw this is what the file should now look like:
Code:
Please, Log in or Register to view codes content!
 
Vorton

Vorton

Lurker
Apr 15, 2022
3
16
313
0fya082315al84db03fa9bf467e3.png
Ehno said:
Please, Log in or Register to view quotes
Click to expand...
Also depends on the GPU. I dunno if 8gb is enough or not. Honestly you could always just give it a try. No harm in trying. Rendering might just take a long ass time. There are some things you can do for low ram/vram could always look up some guides to see if you can get it going.
 
  • Like
Reactions: ChatSaturday
LinuxZDK

LinuxZDK

Superfan
Sep 24, 2023
12
558
387
0fya082315al84db03fa9bf467e3.png
[notice] A new release of pip available: 22.2.1 -> 23.3.2
[notice] To update, run: C:\SD-AMD\stable-diffusion-webui-directml\venv\Scripts\python.exe -m pip install --upgrade pip
Traceback (most recent call last):
File "C:\SD-AMD\stable-diffusion-webui-directml\launch.py", line 48, in <module>
main()
File "C:\SD-AMD\stable-diffusion-webui-directml\launch.py", line 39, in main
prepare_environment()
File "C:\SD-AMD\stable-diffusion-webui-directml\modules\launch_utils.py", line 560, in prepare_environment
raise RuntimeError(
RuntimeError: Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check
Press any key to continue. . .

I made the update that was requested,
but it still doesn't work without the command "--skip-torch-cuda-test to"
Stable Diffusion is not using the video card, it is using the processor and it takes a long time to generate the images
Does anyone know how to solve it? my video card is AMD
 
NathanDrake_97

NathanDrake_97

Tier 3 Sub
Mar 17, 2022
9
340
533
0fya082315al84db03fa9bf467e3.png
Hey guys, quick question, for some reason I had an error with my stable diffusion (I use Docker Desktop version) and I had to delete the whole thing and install it back but when I did it I had this error:

TypeError: AsyncConnectionPool.__init__() got an unexpected keyword argument 'socket_options'​

And with this my webui doesn't start, it closes like in 5 seconds

Anyone know what happened and how I can fix it?

PD. I know shit about python and that kind of stuff so I'd appreciate an easy explanation :)
 
  • Like
Reactions: verizonSXC
S

sinner18

Lurker
Nov 30, 2022
2
3
78
0fya082315al84db03fa9bf467e3.png
raikkonen11 said:
Please, Log in or Register to view quotes
Click to expand...
I reduced my doing time from 10 mins to 2 mins for a single image using the following settings:
-Sampling Method: DPM++ 2M Karras (one of the best methods that takes half the time compared to some other methods)
-Sampling Steps: 20 (higher steps don't improve results noticeably in my opinion)
-Batch count and Batch size: 1 (generates a single image. Takes less time and gives you quick results so you can make changes to your mask and/or prompt)
Also, when you start SD, it takes much longer to generate the first image. Subsequent images take significantly less time.
 
  • Like
Reactions: xsansx69x, Dolphin2ii and verizonSXC
You must log in or register to reply here.
Top Bottom