If you have a Windows pc and an Nvidia graphics card, the process of getting set up is even easier than the one shown in the YouTube video.

1. Download the sd.webui.zip from here, this package is from v1.0.0-pre we will update it to the latest webui version in step 3.
2. Extract the zip file at your desired location.
3. Double click the update.bat to update web UI to the latest version, wait till finish then close the window.
4. Double click the run.bat to launch web UI, during the first launch it will download large amounts of files. After everything has been downloaded and installed correctly, you should see a message “Running on local URL: http://127.0.0.1:7860”, opening the link will present you with the web UI interface.

I like this method because it’s all self-contained in a single folder on your computer, and you don’t even have to mess with git or python. You can even install it twice in two different folders if you want a “clean” copy for SFW creative work and an isolated “naughty” copy with all of your depraved fetish loras (loras are highly-focused training models for specific prompts).

Official Docs here: https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs

♥️

Correct. Thats why i post all my images as links to catbox.moe, which doesn’t touch jpg exif or png chunks.

I do post the first image as a jpg on lemmy so that it shows the thumbnail in the thread, but theres a duplicate link to the original png in the post body.

That’s one of the advantages of ControlNodes. You can maintain finger lengths and quantity with Open Pose wireframes or depth masks.

I’m digging the ‘straight to VHS softcore sci-fi’ vibe.

Appreciate the details. Some interesting models in here that I’ve not seen before. Will have to give them a spin.

I use 600x800 (or 800x600) and 50 steps when experimenting with prompts. Then when i get one i like, I lock the seed, maybe do a few .01-.03 variations. Then lock the variation seed and turn on 2x HighRes Fix. That outputs a 1200x1600 that very closely looks like what I expected. (I’m using a 3090 with 24GB vram)

In my experiments, i found that doing quick and smaller tests with a low number of steps, then increasing it for the highres would change the output too much. I settled on this so that theres less options to toggle back and forth.