physical violence

weapon violence

wide hips

revealing clothes

thick thighs

downblouse

convenient censoring

huge breasts

pg-13

corpses

suggestive

oral invitation

pg13

sexy

sexual situations

male nudity

disturbing

male swimwear or underwear

female swimwear or underwear

partial nudity

undressed

female nudity

breasts out

exposed female nipple

breast out

lingerie

male underwear

hair over breasts

female swimwear

gigantic breasts

no panties

graphic violence or gore

covered nipples

huge butt

strapless leotard

sitting on face

emaciated bodies

one breast out

nsfw

female underwear

nude

graphic male nudity

adult toys

illustrated explicit nudity

nudity

graphic female nudity

hentai

futanari

porn

sexual intent

genitals

peeing

vore

oral

sexual activity

anal

blowjob

dildo riding

incest

hanging

hate symbols

nazi party

white supremacy

diapers

scat

self injury

hate speech

urine

extremist

child on child

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

A versatile model for creating icon art for computer games that works in multiple genres and at various levels of detail.I'm happy with where this is, so there won't be further updates until there's a new major version of Stable Diffusion.

VERY IMPORTANT: FOR THIS TO WORK WITH AUTOMATIC1111, BE SURE TO ALSO DOWNLOAD THE CONFIG FILE AND PLACE IT IN YOUR MODELS FOLDER ALONGSIDE THE MODEL. This may change in the future as automatic1111 support for 2.x matures.This is a finetune of Stable Diffusion 2.1 (as opposed to 1.4), and the results it produces are way more interesting. Click the 'i' icon on the example images of how to prompt it (negative prompt is important here). If you feel like it, please experiment and leave any interesting discoveries in the reviews.License: I don't believe models ought to be copyrightable, so you can do whatever you want with this, including uploading and redistributing it elsewhere, finetuning it, berrymixing it, etc. I do humbly request that you share any models that you make with this one, but you're free not to.This model was finetuned with <a href="https://github.com/devilismyfriend/StableTuner" rel="ugc" target="_blank">StableTuner</a> with a dataset of ~250 manually captioned images. Learning rate was 1e-6, 250 epochs, batch size of 24. Text learning cutoff was 75 epochs to prevent overfitting.Note: I've accidentally discovered that this model does some amazing non-icon art. See the cityscape picture for an example of another way to prompt it.

v4 SD 2.1

v2 was an overfitted mess, so I'm not bothering to post it here. :)This version produces more consistent, varied, higher quality output, and is a lot better at abstract ability icons. It also requires shorter prompts to produce good output. Click the 'i' icons on each image for prompt and settings.I find that experimenting with different artist names doesn't replicate those artists' style, but it can add more detail.For the next version of this, I may try finetuning Stable Diffusion 2.1 512x512 instead, to see if that helps it a bit with more complicated prompt comprehension.

It's pretty good at objects, but has trouble with abilities. I'm going to try and retrain it with some more ability icons added to the set. Works best if you append ", stylized game icon" to your prompt. See "i" icon on individual images for details. Examples are cherry picked from a larger set.Trained with <a href="https://github.com/devilismyfriend/StableTuner" rel="ugc" target="_blank">StableTuner</a>. This model is based on SD 1.4.

Stylized RPG game icons