adult toys

anal

blowjob

breast out

breasts out

corpses

extremist

gigantic breasts

hair over breasts

hanging

hentai

male swimwear or underwear

male underwear

physical violence

porn

self injury

suggestive

thick thighs

convenient censoring

exposed female nipple

genitals

graphic female nudity

graphic male nudity

graphic violence or gore

no panties

one breast out

revealing clothes

scat

sexual intent

sexual situations

sexy

strapless leotard

vore

wide hips

covered nipples

dildo riding

disturbing

emaciated bodies

futanari

huge breasts

huge butt

urine

child on child

diapers

downblouse

illustrated explicit nudity

incest

male nudity

nsfw

nude

partial nudity

pg-13

sexual activity

white supremacy

female nudity

female swimwear

female swimwear or underwear

female underwear

hate speech

hate symbols

lingerie

nazi party

nudity

oral

oral invitation

peeing

sitting on face

undressed

weapon violence

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

presenting ass

Only initial vertical drawing is used as the training set, and breakthrough vertical drawing is not used.So there aren't many additional effects.

trained on <a target="_blank" rel="ugc" href="https://civitai.com/models/1369089?modelVersionId=1546777">Illustrious XL 2.0</a>

granblue for illustrious

granblue for Neta-Lumina

granblue for qwen-image，use 800*960，with danbroou tag. key word：granblue fantasy

granblue for qwen-image

由于noobxl对于各种知名角色有画风污染，因此不建议添加任何角色词作为tag，用wd1.4反推的时候角色置信度建议调成1。Due to the art pollution of various well-known characters in noobxl, it is not recommended to add any character words as tags. When using wd1.4 for reverse inference, it is recommended to adjust the character confidence level to 1.

granblue for noobxl

After testing, secondary sampling can achieve better image effects. It is recommended to perform 2 or more samplings in Comfyui to avoid incomplete noise reduction in the FLUX model

Granblue for FLUX

采用ponynai3作为底模，未训练文本层，推荐权重0.8

Granblue Pony-XL

该版本采用突破立绘进行训练，训练分辨率768x768，生成图片具有较大动态与较多特效，如单纯需要站姿，请使用1.0版本。This version uses breakthrough vertical drawing for training, with a training resolution of 768x768. The generated images have significant dynamics and many special effects. If you only need standing posture, please use version 1.0.

v2.0

ver1.0

Granblue fantasy style

04805-403600811-amazing quality,beautiful color,highers,1girl,sexy,skinny,small breasts,pov,_lora_niiiitoooon-XL-000012_0.8_,.png

Type	LoRA
Stats	456 452 558
Reviews	Very Positive (66)
Published	Oct 17, 2025
Base Model	Illustrious
Training	Steps: 10,000 Epochs: 20
Usage Tips	Clip Skip: 2 Strength: 1
Trigger Words	granblue fantasy
Hash	AutoV2 2FAA469FDB