Ghost in The Shell: Stand Alone Complex (2002) Style - -NOPE- v1.0
Highlighted images
Recommended Prompts
retro artstyle,anime coloring
masterpiece, best quality, absurdres, very aesthetic, high quality, highres, outdoors, night, city, 1girl, solo, <lora:ghostintheshell-standalonecomlpex:1> xgitsx
Recommended Negative Prompts
low quality, lowres, worst quality, watermark, patreon username, artist name, signature, text, web address, fewer digits
Recommended Parameters
samplers
steps
cfg
resolution
other models
Recommended Hires (High-Resolution) Parameters
denoising strength
Tips
Avoid using with heavily stylized checkpoints to prevent undesired deformities.
Use suggested checkpoint or any other flexible checkpoint for best results.
When combining with other character LoRAs, lower the weight of character or style to balance generation.
Example weighting: character 0.8 - style 1.0 adapts character to style; character 1.0 - style 0.8 adapts style to character.
Model trained on IL XL 0.1 to maintain compatibility across IL models.
This was the result of one of my friends asking if I can make characters in this style, I tried and no... so thats why I made this in the first place. (my friend doesn't know SH** about generative AI, I just send him a few surprise images here an there)
Trained on 160 images.
v2.0 Holy shit this style looks good when its made well!!! Redone the whole dataset, increased image count from 63 to 160, processed them juuust right! ...and a much more agressive training method, looks like it did the job.
Don't use it with heavily stylized checkpoints, theres no point really (and you'll turn gay). Why do you use that if you want to change the style anyway? Use suggested checkpoint or any other flexible checkpoint. For onsite genners I have no advice, never used it.
I can't speak on other's character loras because training methods vary, but if your using it with mine then I suggest lowering the weight of the character or the style, I set weights heavy on my characters training.
Example:
character 0.8 - style 1.0 - adapts the character to the style
character 1.0 - style 0.8 - vice versa, adapts the style to the character
(this is just an example, these weight can vary, and they should if you want to use it with more loras) -...as I often see some overloaded gens-
Recommended style reinforcement tag:
retro artstyle, anime coloringI train everything on IL XL 0.1 so it's compatible with any IL model, but the problem with most checkpoint is that they are leaning towards anime too much and cause the chin and eyes to deform regardless how hard I train it. Legends say it should be allright with NoobAI aswell, I dunno', never tried that, it's an anime wasteland I was told...
Model Details
Model type
Base model
Model version
Model hash
Trained words
Creator
Discussion
Please log in to leave a comment.
