We're a Day-0 launch partner for MiniMax H3, a next-gen open-weights multimodal video model - and it's already in the generator. No waitlist. Open weights land in a few days.

MiniMax H3 is live: open-weights video, generate now

Lora for the Digimon Chaperomon from Digimon Liberator. Literally Little Red Riding Hood with a Gatling gun. I recommend reading the version release notes to see what each version is capable of.

Trained on illustrious using the same dataset as the SDXL and pony versions on CivitAI's training service. Seems to work in a variety of models and styles, but best on NoobAI derived checkpoints. The trigger word is just "chaperomon", but the other trigger words I have included make the character more consistent.

Illustrious V1

By removing some redundant images from my data set and fixing some of the captions, I have finally trained pony XL to reliably replicate the character, including her unique shoes and basket (though the gatling gun part of it still needs some work). This model is very flexible in terms of both style and poses it can do. Just prompting "1girl,solo,chaperomon" is enough to get the character's likeness, but some non-base Pony models may require some additional prompting. In addition, to actually get her shoes, use "animal slippers" in your prompt. I have included some of the additional trigger words that help, but keep in mind they may not all be necessary depending on what model you are using. It seems to work best at a strength around 0.95 for most models, but it can go as low as 0.8 or as high as 1.0 depending on how much more flexible you need it.

PonyXL v1.0

Base SDXL version, trained on slightly more images with booru style captions than other models. Seems to be inconsistent with her shoes, but it can kinda generate them if you use the tag "animal slippers". Doesnt need much prompting with anime style images (just "1girl,solo,chaperomon" seems to work with a strenth of around 0.85-1.0), but for 3d and realistic stuff you may need to add more tags and tweak the strength,

SDXL Beta v1.0

Initial version, trained on very few images, mostly of the upper body. I trained it on my PC at 512X512 for 1800 steps, so its a little bit under-trained. As such, it cannot generate her shoes and requires some additional prompting for full body images. I find that it does work with a wide variety of styles and poses otherwise.

Pony Beta v1.0

Initial SD1.5 version. Seems to have difficulty with generating her face, as it insists on giving her eyes. Also has difficulty with her shoes, due to lack of training data. While just "chaperomon" is enough to trigger the model, I recommend adding more keywords to describe her.

SD1.5 Beta v1.0

Chaperomon (Digimon)

physical violence

weapon violence

wide hips

revealing clothes

downblouse

convenient censoring

pg-13

corpses

suggestive

oral invitation

pg13

sexy

huge breasts

thick thighs

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

female underwear

nude

nsfw

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