sexual situations

physical violence

disturbing

male nudity

hanging

hate symbols

nazi party

revealing clothes

weapon violence

female swimwear or underwear

male swimwear or underwear

partial nudity

white supremacy

adult toys

graphic male nudity

illustrated explicit nudity

nudity

graphic violence or gore

pg-13

corpses

wide hips

peeing

oral invitation

sexual activity

sexual intent

undressed

male underwear

female swimwear

genitals

female underwear

thick thighs

breasts out

strapless leotard

vore

breast out

one breast out

huge breasts

gigantic breasts

huge butt

covered nipples

hair over breasts

no panties

sitting on face

anal

dildo riding

downblouse

oral

porn

futanari

hentai

nude

lingerie

nsfw

child on child

self injury

extremist

hate speech

diapers

urine

scat

graphic female nudity

convenient censoring

emaciated bodies

blowjob

suggestive

incest

sexy

exposed female nipple

female nudity

latex clothing

swimwear

bukkake

fellatio

cumshot

implied fellatio

eat_cum

cumdrip

cum in pussy

cum on face

after fellatio

cum on hair

cum on body

cum on tongue

cum on hands

cum in mouth

triple fellatio

autofellatio

fucked silly

cum on pussy

pov fellatio

Lovelive -- Hoshizora RinMy first Lora Model, which might still have some problem. I will keep tring to optimize and perfect this model.

完全重置版。素材重新收集，大多数使用了LLAS内的素材Totally remake. The training material was collected again, mostly using the pics in LLAS.训练分辨率为768*1024和1024*768The training resolution is 768*1024 and 1024*768仍然有过拟合的迹象，但是反复调试以后仍然决定发布这个版本，效果是最好的。可以搭配前几天发布的LLAS Style使用There are still signs of overfitting, but i still deciside to release this version after repeated debugging. It can be used with the LLAS Style released a few days ago.如果将他们一起使用，它们俩加起来的权重不能超过1If you used them together, the combined weight of these two cannot over 1.0

xkl_v30

First version. Trained by 15 pic.

HoshizoraRin v1.0

New version trained by 50 pictures, which include 20 3d-model pictures. With simple background, weight 0.6-0.8 will be fine (or using hoshizora_rin tag together with weight 0.4-0.6). With complex background, I recommand 0.4-0.6. Never use more than 0.8 weight which will cause terrible image. Next step I will try to use more transparent background picture to make this Lora more general.

HoshizoraRin v2.0

Lovelive - HoshizoraRin

Type	LoRA
Stats	661 652
Reviews	Very Positive (88)
Published	Jun 6, 2023
Base Model	SD 1.5
Training	Steps: 9,000 Epochs: 20
Trigger Words	xkl 1girl solo
Hash	AutoV2 EC650B5D8B