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

USE THE NEW EMBEDDING!!!<h3 id="heading-531">Completed.</h3>Although the model is far from perfect, this is where this particular experiment ends.I'll start over with a different training method.The final version can handle decently 1024x1024 resolution for most of its concepts.Right now I don't feel like posting the "keywords" the model was trained on, maybe I'll suffice later.

All sample images of this version are generated with Fooocus-MREWay too many concepts teached to be listed here, not only NSFW. Trained between 768 and 1024, depends on the concept you want to call.

v1.0_768x1024 Definitive

Overall improvement, overfitting in the characters it had learned about, I'll fix it later and provide the list of the characters.

V0.2_Gamma_(FasterLR)_512

Less underfit, remember to use the embeddings and if you are confused as to why it's 512 when it's listed 768, it's because I took a base 768 and fine-tuned on 512 ratio for speed.

V0.1_Beta_512

This version technically is 768x768 of 2.1, but it was heavily fine tuned on 512x512 ratio because I needed to work on it faster, because of this works best with hires fix, all listed images use the basic upscaler latent near-exact at 55% denoising

V0_Alpha_tunedAt512

AllWorkForkRowk_InProgress_(SD2.1)

Type	Checkpoint Trained
Stats	199
Reviews	Positive (20)
Published	Nov 21, 2023
Base Model	SD 2.1 768
Usage Tips	Clip Skip: 1
Hash	AutoV2 D662865FDE