This lora was trained on about 150 screenshots from the 1995 Ghost in the Shell movie. This is a lora to capture the artstyle of GITS, but you can prompt the major using "kusanagi motoko". I included "gits1995" as a tag but I don't believe it does anything special.

This lora was trained on Autism Pony. I haven't tested it with anything else.

To get the results you see in the images above, these are the settings I used.

Prompt: score_9, [your prompt]

Negatives: mosaic censoring,bar censor,censored,source_cartoon,source_pony,source_furry, simply background

Sample: Euler a

Steps: 33 (Whatever gives you the best results)

CFG Scale: 7

Highres Fix: 4x-UltraSharp + ADetailer

Hands can be pretty crummy in the lora, fyi. The source images I trained on didn't have too many good enough examples it seems.