physical violence

revealing clothes

weapon violence

pg-13

corpses

wide hips

convenient censoring

oral invitation

thick thighs

huge breasts

downblouse

suggestive

sexy

pg13

sexual situations

disturbing

male nudity

female swimwear or underwear

male swimwear or underwear

partial nudity

graphic violence or gore

emaciated bodies

exposed female nipple

female nudity

undressed

male underwear

female swimwear

female underwear

breasts out

strapless leotard

breast out

one breast out

gigantic breasts

huge butt

covered nipples

hair over breasts

no panties

sitting on face

nude

lingerie

nsfw

adult toys

nudity

graphic male nudity

illustrated explicit nudity

graphic female nudity

sexual intent

genitals

porn

futanari

hentai

peeing

blowjob

sexual activity

vore

anal

dildo riding

oral

incest

hanging

hate symbols

nazi party

white supremacy

self injury

extremist

hate speech

diapers

urine

scat

child on child

bukkake

fellatio

bikini

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

<h3 id="lotmcoi-lora-for-animagine-3.1ponyillustriousanima-model">LOTM/COI LORA for Animagine 3.1/Pony/Illustrious/Anima Model</h3>Characters (18 total from official/fan art): Klein Moretti (+3 personas: Merlin Hermes, Gehrman Sparrow, Mr Fool), Audrey Hall, Fors Wall, Leonard Mitchell, Alger Wilson, Amon, Azik Eggers (past/present), Derrick Berg, EBR, Emlyn White, Lumian Lee, Evernight goddess, Medici, Adam, Cattleya, Xio Derecha, Roselle Gustav, Bernadette Gustav

Tried to train it on the same dataset as all the others, without captioning with natural language. Turned out better than expected, but definitely not the best it could be. Characters separately work better than together, probably trained too much.

Anima-test

Trained on IllustriousXL 1.0. I think it's a bit overfitted in some ways and may have issues with generating more than 1 character (2 is still possible depending on prompt). Experimental version based on the old dataset as I had issues with training Illustrious models before. It is compatible with finetunes, but depends on the model. I'll update dataset and captions, with new characters, later.

Illustrious v0.5

Another 10 epochs at a lower training rate made it more stable

v1.1.5

Pony v1.0

Retrained with more data that I cherrypicked from the previous model. Less epochs, but seemingly better and flexible. But I do recommend to increase strenght a bit (like to 1.1), if the details are often off. There is still some overfitting issues, but now at least it allows variations. And in for next versions, I would need to remove watermarks I guess, or to not use them in prompts.

v1.1

First model. While it can generate all the characters, it has certain problems. Some characters, for which I didn't find many images, have a certain tendency to generate the official illustration of them under certain prompts, while working fine otherwise.

v1.0

Version for the 1.5 model. It can require a bit more prompting for the likeness of the characters.

1.5 v1.0

LOTM [Anima, SDXL, Illustrious, Pony, SD1.5] LORA

Type	LoRA
Stats	56 0
Reviews	Positive (14)
Published	Feb 9, 2026
Base Model	Anima
Training	Steps: 52,520 Epochs: 52
Usage Tips	Strength: 1
Trigger Words	amonlotm audreyhall forswall gehrmansparrow kleinmoretti leonardmitchell merlinhermes algerwilson azikdeath azikeggers +12 more
Hash	AutoV2 1E44971D47