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 it. The one you've been waiting for. We've retrained SDXL with 1.3M professional and amateur pornographic images. This model does softcore, hardcore, and everything in-between.The model seems to do best with resolutions 832x1216 or 1216x832. My settings:<ul><li>Sampler: dpmpp_2m_sde</li><li>Scheduler: Karras</li><li>Steps: 30</li><li>CFG: 7</li></ul> The model isn't perfect. You'll get some strange anatomy at times. Experimentation says this is the result of TE2, which was likely trained without much NSFW content. Still, you can get great results with a bit of cherry-picking.Recipe:In each step, TE weights were frozen - this model modifies only the unet. Machine captioned images were used until the last step.<ol><li>Retrained SDXL 1.0 on 1.3M images for eight epochsbs=80, lr=1e-05, optimizer=AdamW8Bit, EMA=0.95</li><li>Finetuned on 50k images for ten epochs to help do some rebalancingbs=80, lr=2e-06, optimizer=AdamW8Bit, EMA=0.95</li><li>Aesthetic training on 30k images for 14 epochsbs=1, lr=1e-05, optimizer=Adafactor, no EMA</li><li>Final alignment using 600 hand-selected and captioned imagesbs=1, lr=1e-05, optimizer=Adafactor, EMA=0.95</li></ol>Feel free to make your own merges and finetunes based on this checkpoint for non-commercial purposes. I ask that, if you do, you include a recipe with a similar level of detail as what I provided above. There's too much secrecy around this topic.I have made checkpoints from step 2 &amp; 3 in the recipe above available. These are not recommended for general use - they do not make good images out of the box. They may be useful for model mergers and finetuners.

v1.0

This is the version that corresponds to step 3 in the recipe. It does not have the final alignment and is not recommended for most users. It's available here for model mergers and trainers in case they want to do their own refining.

v0.9 - Unrefined

This raw version represents step 2 in the recipe. It is not meant for general use - you will be disappointed in its generations. It is here for tuners and mergers who may find it interesting.

v0.8 - Raw

Anteros XXXL