sexual situations

physical violence

disturbing

male nudity

graphic female nudity

corpses

suggestive

child on child

hanging

hate symbols

nazi party

weapon violence

female swimwear or underwear

male swimwear or underwear

graphic violence or gore

wide hips

convenient censoring

peeing

oral invitation

exposed female nipple

blowjob

sexual activity

sexual intent

bestiality

self injury

extremist

hate speech

diapers

urine

menstruation

scat

incest

revealing clothes

partial nudity

white supremacy

adult toys

graphic male nudity

illustrated explicit nudity

nudity

emaciated bodies

female nudity

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

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

V4 - a much needed update to my first ever model 🥰Prompt: axolotl<hr /><ul><li>Clip Skip: 2</li><li>Strength: 1</li><li>CFG: 4-7 </li></ul>

v4.0

What I've been working up to! Better quality! Less mistakes! More consistent head frillies (they're external gills)! Happy with the results. This version plays much better with other loras compared to previous versions. I'm using a custom node in comfyui for the showcase that is able to capture all of the generation info except for the lora stack. I'm mostly using eldritchadam's loras, I'll have them linked in the suggested resources. I'm a fan and I like using his loras with my models. If your prompts are really lengthy and you're using a bunch of other loras, i find it useful to negative prompt things like "rodent", "whiskers", and "fins". This is because stable diffusion's idea of an axolotl is a pink salamander but sometimes their head frillies get turned into something that looks like mouse ears and then it just runs with making something that looks like a mouse. This won't come up as much because I regularized this model against generations of what stable diffusion thinks an axolotl is, but it can come out if there are a bunch of other things fighting for control. I'll try to make a pdxl version soon, I don't use it, but I've seen some fun loras I've been missing out on and it seems like my models don't have much of an affect on those checkpoints.

v3.0

Finally figured out how to make the file size reasonable, 200 mbs! Also more flexible and accurate as I spent more time with captioning and selection of varied images. This is mostly an update to make the file size more manageable. Now that I figured that out, I plan on making at least one more version that can be more responsive and flexible than this one.

v2.1

Sorry about the file size... I was trying so many new things I forgot to look up how to make these smaller. If it's a simple setting in Kohya SS I would super appreciate you let me know. I'll make sure to make the file size smaller in the next version. This version should be a lot more responsive. The first one was definitely overtrained. The triggerword is "axomodel2". If it's being stubborn, I've found that you can not use the trigger word if it's at full weight. I'm thinking because I generated 200 regularization images of what SDXL thinks an axolotl so this model prevents the generation creating a generic pink salamander. This one should be a lot more adaptable to different art styles and bring up unrelated ideas that I overtrained into the last one. Clip skip 2, I particularly like euler smea dy, but I've tried it with the other poplar samplers. CFG 4-10 depending on what you're trying to do. I've found keeping the clip strength at 1 and strength from ranges 0.6-1.0 is good when it's being stubborn at higher CFG.Hope you all enjoy it. I plan on eventually making another version as I find what the weaknesses of this one are and learn how to compensate for them as well as make the file size smaller.

Type	LoRA
Stats	126 528 8
Reviews	Positive (16)
Published	May 11, 2024
Base Model	SDXL 1.0
Training	Steps: 5,000 Epochs: 5
Usage Tips	Clip Skip: 2 Strength: 1
Trigger Words	axomdel2 axolotl
Hash	AutoV2 B4568AC998

Axomodel XL