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

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

Granblue for ZimageTurbo

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	469 47 68
Reviews	Very Positive (57)
Published	Dec 2, 2025
Base Model	ZImageTurbo
Training	Steps: 3,000 Epochs: 12
Usage Tips	Strength: 1
Hash	AutoV2 578EB8BBA4