sexual situations

physical violence

disturbing

male nudity

graphic female nudity

pg-13

convenient censoring

blowjob

female nudity

child on child

self injury

extremist

hate speech

diapers

urine

incest

weapon violence

female swimwear or underwear

male swimwear or underwear

partial nudity

white supremacy

adult toys

graphic male nudity

illustrated explicit nudity

nudity

corpses

wide hips

oral invitation

emaciated bodies

suggestive

scat

hanging

hate symbols

nazi party

revealing clothes

graphic violence or gore

peeing

exposed female nipple

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

sexy

nsfw

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

Cuz flux is just way 2 expensive XP<a target="_blank" rel="ugc" href="https://tensor.art/models/801919936881528603?source_id=kT63rlHllUC7rfAiaHfz8xcl">Also on Tensor.Art!</a>

Wow, and I thought the sheer accuracy of Illustrious model training was crazy enough... But damn, THIS is on another level.The great, GREAT majority of times it gets the text perfectly, many of them in the first generation... At this point I'm genuinely considering trying to train it with slightly different fonts n stuff...

Illustrious (Best ver)

For consistency, i kept all images with the same phrase, same formatting and same font. and even so it didnt turn out as good as i hoped...But hey, it does gets it right a good amount of times... and even when it doesnt, its still much more readableUPDATE: Turns out that, with the same dataset, the Illustrious version managed to do much, MUCH better. The pony one still frequently gets it right, but even so it doesnt compares to the Illustrious version.So, if possible, you really may want to try the Illustrious version instead. But if not, its no worries, Pony still manages really well.

Pony

(PD/IL)"I Need Buzz!" Sign

20250208_163537.jpg

Type	LoRA
Stats	551 25,416 9.7k
Reviews	Very Positive (464)
Published	Dec 29, 2024
Base Model	Illustrious
Training	Steps: 510 Epochs: 10
Usage Tips	Strength: 1
Trigger Words	need_buzz, holding sign
Hash	AutoV2 0A470669DA