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

The Dark Atmospheric LoRA was trained to produce a style characterized by shadow and mist with a slightly diffuse effect.

I tweaked the training settings for this version, which I think offers improvement over the V01 release for Z-Image. Images are, I think, more detailed, but retain the characteristics of the LoRA.

V01a - Z-Image

V01a - Flux.2 Klein 9b

V01 - Z-Image Turbo

V01 - Qwen

Check the showcase images for example prompts and weights used.

V01 - Flux.1 D

V01 - OmniGen

V01 - SDXL

I recommend using V01a over this earlier version.Ordinarily I would use the res_multistep sampler with Z-Image, but for this LoRA I prefer euler as it softens features and makes them less distinct.

❌ V01 - Z-Image

Dark Atmospheric Style - CE

2024-07-10 062058_00001_.png

Type	LoRA
Stats	1,217 181 329
Reviews	Very Positive (138)
Published	Dec 1, 2025
Base Model	ZImageTurbo
Usage Tips	Strength: 0.6
Hash	AutoV2 F4B59B0F32