Name: Something Unlimited Style Lora
Rating: 5 (455 reviews)
Author: guy90

thick thighs

sexual situations

physical violence

disturbing

extremist

hanging

hate symbols

nazi party

breasts out

strapless leotard

revealing clothes

weapon violence

female swimwear or underwear

male swimwear or underwear

partial nudity

self injury

white supremacy

adult toys

graphic male nudity

illustrated explicit nudity

nudity

sexual activity

graphic violence or gore

graphic female nudity

vore

bestiality

corpses

breast out

one breast out

huge breasts

gigantic breasts

huge butt

wide hips

covered nipples

hair over breasts

no panties

sitting on face

convenient censoring

anal

dildo riding

downblouse

peeing

oral

oral invitation

emaciated bodies

hentai

porn

bukkake

cumshot

cumdrip

cum in pussy

cum on face

cum on hair

cum on body

cum on tongue

cum on hands

cum in mouth

cum on pussy

eat_cum

fellatio

implied fellatio

after fellatio

triple fellatio

autofellatio

pov fellatio

fucked silly

presenting ass

presenting pussy

spreading legs

spread legs

swimwear

lingerie

bikini

latex clothing

TRPCError

Something Unlimited Style Lora. I recommend using 0.8~1.0 strength.<ul><li>Trigger Word: somethingunlimited</li></ul>Please look at example images for helpI use additional tools for my generations so my images may be different from yours. If you want to know what I use, please look at <a target="_blank" rel="ugc" href="https://civitai.com/articles/759">my guide.</a><a target="_blank" rel="ugc" href="https://linktr.ee/guy907223982">My Socials </a>| Support me on <a target="_blank" rel="ugc" href="https://www.patreon.com/guy907223982">Patreon</a> or <a target="_blank" rel="ugc" href="https://ko-fi.com/guy907223982">Ko-fi</a> (If you want)

v4.0

With the same training method employed, I have utilized a different model that has yielded superior results. Notably, this new model exhibits reduced loss of detail during the generation process. It excels particularly in generating realistic faces and hands, showcasing a noticeable improvement over the previous model. Additionally, the variety of outputs has significantly increased.Furthermore, the color saturation issue observed in the previous model has been rectified in this new iteration. The generated images now possess a more balanced color representation, avoiding the excessive saturation of the previous version.While using this model, you may notice that the generated faces have a distinct "Anime" style rather than a Western one. If the Anime-style faces are not to your liking, I recommend utilizing Version 3.0 temporarily until I can refine the new model further. The primary difference lies in the appearance of the eyes, as they tend to resemble Anime eyes. However, generating images with black eyes should result in eyes that are closer to the Western style.

v3.0 (Anime)

Improved Version More images used, more flex ability in general.

v3.0

"Why did you skip so many versions" They didn't look good. *Fixes* -Higher Quality Generation -More Consistent generation -Background is easier to change (still defaults to gray background)

v2.1

Trained on 89 images with new training method.*I recommend using 0.9 strength if you are using it for general stuff. Combining with other loras use 0.5-0.6 strength. I personally like 0.6 and I tend to get better results.*

Type	LoRA
Stats	1,105 17,144
Reviews	Very Positive (119)
Published	Dec 18, 2023
Base Model	SD 1.5
Training	Epochs: 10
Usage Tips	Clip Skip: 2 Strength: 1
Trigger Words	somethingunlimited
Hash	AutoV2 1F39076BF2