sexual situations

physical violence

disturbing

male nudity

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

graphic violence or gore

graphic female nudity

pg-13

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

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

nsfw

suggestive

child on child

self injury

extremist

hate speech

diapers

urine

incest

scat

sexy

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

pov fellatio

Model of the mega level cyborg digimon QueenBeemon from digimon liberator. Trained mostly on images of fan art as she's relatively new, so there may be some inconsistencies with the official design. There also arent many images of her throne in the data set,so good luck generating it. Otherwise this model seems to work well in a variety of styles in a variety of models. Check each version's notes to determine what it is capable of and what issues it may have.

Illustrious version of the model trained on the same dataset as prior versions on civitai's training service for around 8 epochs. Seems to work on a wide variety of styles, on multiple models, and accurately maintains the character regardless of model or style. I recommend a stength of around 0.9-1.0, you can go higher or lower depending on how much of the character you want. The trigger word is just "queenbeemon", but you can add other keywords like "antenna" and "purple hair" to strengthen the look.

Illustrious v1.0

Improved flux version of the model trained on Civitai's service using a single caption. Seems to reproduce the character quite accurately, however some description may be required. The base trigger is "queenbeemon", but I recommend using keywords like horns, antenna, single purple braid, bodysuit, green eyes, etc that help describe the character. It seems to work busy with 3d, anime, and cartoon style images, but you will need to lower the weight for photorealistic images. Seems to work best with a strength of 1.0 to 0.8.

FLUX v1.0

base pony version of the model trained mainly on fan art. pretty consistent and doesnt need many keywords (just "1girl,solo,queenbeemon" seems to work in most instances), but I have listed additional trigger words that help with the style. Seems to work at a strength of 0.7 to 1.0, best at around 0.95 from my tests. Works in a variety of styles, and I have tested it on a few pony models and it seems to work on most of them.

Pony V1.0

SDXL version of the model trained using Civitai's training service trained on the same dataset as the other versions. The amount of prompting youll need to do is dependent on the style you want, anime style generations will require fewer keywords while realistic ones will require much more. It was trained on booru style tags, but it seems to work with sentence style prompts, the trigger words are just an example of what keywords will increase the character accuracy. It seems to work well at a strength of 1.0, and I wouldnt recommend going much higher or lower unless you intend to significantly alter the character or are trying a specific style.

SDXL v1.0

Base SD 1.5 version, trained for about 1K steps at 726X726 on the same dataset as the pony version. May require some additional prompting for character consistency, and definitely benefits from upscaling. Should work in a variety of styles, though I have only tested it in anime and semirealistic, but I will add more examples as I test more styles

SD1.5 v1.0

Flux version of this model trained on booru style captions, seems to be very weakly trained, so it requires a lot of keywords to work properly. Since I cannot run flux very well on my own machine (It takes like a half hour to get a 1024X1024 with 8gb of vram), I will have to spend some buzz to test it on civitai. I have no idea how to get the metadata from SwarmUI for the images, so thats why they dont have any.

FLUX Beta v1.0

QueenBeemon (Digimon)

Type	LoRA
Stats	48 7 19
Reviews	Positive (8)
Published	Oct 14, 2024
Base Model	Flux.1 D
Training	Epochs: 10
Usage Tips	Strength: 1
Trigger Words	queenbeemon horns,antenna,single purple braid energy cape energy wings
Hash	AutoV2 4465552512