sexual situations

physical violence

disturbing

male nudity

extremist

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

self injury

graphic violence or gore

graphic female nudity

corpses

wide hips

convenient censoring

peeing

oral invitation

emaciated bodies

exposed female nipple

blowjob

female nudity

sexual activity

sexual intent

undressed

male underwear

female swimwear

genitals

female underwear

thick thighs

breasts out

strapless leotard

vore

bestiality

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

suggestive

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

This is a test LoRA of my bottomheavy dataset, but trained on SDXL. I wanted to see how SDXL would handle the same data/config as my last released model. The results came out better than I expected and it was pretty quick to train compared to SD1, so I'm uploading it just for fun. Still, don't expect to much from this LoRA. This was a low effort training attempt. And I have no idea how to prompt for SDXL yet, so keep that in mind. See Training Data for tags list<h3 id="heading-1191"> Training Findings:</h3><ul><li>It seems that SDXL does learn the concept faster than SD1, my last bottomheavy model trained way longer with similar config. 16 epocs vs 160 epocs (but this model is under trained probably)</li><li>A lower network_dim seems to work fine, I will probably try even lower than 16 later.</li><li>Training per iteration is about ~2-3x slower on SDXL than it was for SD1, but the speed that SDXL learns the concept makes it somewhat competitive.</li><li>Didn't necessarily need text encoder training to get decent results. On SD1 I would have to train for much, much longer if I did not use text encoder training. Here it learned the concept pretty well without.</li></ul>

This is a test of SDXL's ability to learn far fetched concepts. This is not up to par with most of my other models, but still wanted to show off what SDXL was capable of learning.Training Details:<ul><li>~400 images</li><li>14 epocs</li><li>batch 2</li><li>gradient accumulation 4</li><li>learning rate 2e-4</li></ul><ul><li>No text encoder</li><li>base model SDXL</li><li>clip skip 1</li><li>random flip</li><li>shuffle captions</li><li>tag drop chance 0.1</li><li>network dropout 0.4</li><li>bucketing at 1024</li><li>dim 16</li><li>alpha 8</li><li>conv_dim 8</li><li>conv_alpha 4</li><li>cosine with restarts</li><li>scale weight norm 1</li></ul>

v1.0

hyper bottm heavy SDXL