also: if it does not work for you download the training data aka model.zip and choose an earlier version, or you're just a bad prompter like me XD
if you want good photos use this prompt and modify it to your needs:
masterpiece, best quality,<lora:last-000005:0.6>, yameroyandere, crazy eyes, yandere, red background, constricted pupils
negative:
lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, loli, chibi, female child, teeth, holding, lipstick, glowing eyes
Read this! Read this! Read this!:
if you don't want something, then just put it into the negative prompt.
also, LOOK AT THE TRIGGER WORDS!
Description
Credits:
some of the preview-images - Hatsu( UnstableDiffusion )
FAQ
Comments (4)
It's a locon or lora? Asking because of a big size
lora, it is so big because it was trained with around 500 images. and i wanted to let it capture the "style" perfectly!
Cool Lora, one of my favorites. Also the "dark" token does cool things
Hey, thank you so much for your comment. Do you have anything that could have been better? Dont hesitate to give some more feedback if you like. If you have any lora requests you can come to me and ill try!(for free ofc)