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

peeing

emaciated bodies

blowjob

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

sexy

nsfw

child on child

incest

pg-13

convenient censoring

female nudity

suggestive

corpses

wide hips

oral invitation

exposed female nipple

sexual activity

sexual intent

self injury

extremist

hate speech

diapers

urine

scat

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

Experimental models that can run unstable. You have been warned.For those who like to experiment with artist tags.-&gt;Read the description for each model.&lt;-<s>Continuation of HL's styles series</s>

Although the style is trained as a support LoRA to be used with artist tags, but can be used as a standalone style.Additional information.<ul><li>Should work on both WAI and NoobAI. I myself tried it on <a target="_blank" rel="ugc" href="https://civitai.com/models/827184?modelVersionId=1490781">WAIv12 </a>and <a target="_blank" rel="ugc" href="https://civitai.com/models/1217645/sih?modelVersionId=1371790">ΣΙΗ</a>, no particular problems in my workflow.</li><li>Trigger word is nhl-004.</li><li>LoRA itself is unstable, so additional artist tags would be helpful. Also the quality appears after upscaling. I recommend using adetailer and inpainting to improve eyes, hands and details.</li><li>weight from 0.6 to 0.9. If used with artist tags, it can be lowered. The weight depends on the particular artist tag / LoRA. Experiment.</li><li>Was trained on the modified dataset of artist <a target="_blank" rel="ugc" href="https://danbooru.donmai.us/posts?tags=kukka+&amp;z=5">Kukka </a>images.</li><li>kukka artist tag enhances the style effect.</li><li>I recommend to use indoors/outdoors, scenery tags. there are many images with plant in dataset, so this tag can be used. potted plant is fine too.</li><li>LoRA can make interesting textures and sky.</li></ul>I'm still testing this LoRA, I'll add additional details later. If I don't forget.

Style 004 - WAI | NAIXL

Although the style is trained as a support LoRA to be used with artist tags, but can be used as a standalone style.Additional information.<ul><li>Should work on both WAI and NoobAI. I myself tried it on <a target="_blank" rel="ugc" href="https://civitai.com/models/827184?modelVersionId=1490781">WAIv12 </a>and <a target="_blank" rel="ugc" href="https://civitai.com/models/1217645/sih?modelVersionId=1371790">ΣΙΗ</a>, no particular problems in my workflow.</li><li>Trigger word is nhl-003. greyscale and monochrome if a black and white image is required. The recommendations in <a target="_blank" rel="ugc" href="https://civitai.com/models/1116233?modelVersionId=1284348">klskx </a>should also work.</li><li>Was trained on the modified dataset of <a target="_blank" rel="ugc" href="https://civitai.com/models/1116233?modelVersionId=1284348">klskx</a>. The main difference from previous <a target="_blank" rel="ugc" href="https://civitai.com/models/1116233?modelVersionId=1284348">LoRA </a>is that all images in the dataset are greyscale. Also, LoRA is not that strong, if you want a full style effect, it's better to use the <a target="_blank" rel="ugc" href="https://civitai.com/models/1116233?modelVersionId=1284348">klskx </a>version, this one is made to work with black and white images + artist tags.</li><li>Kan Liu /(666k/) artist tag enhances the style effect.</li><li>weight from 0.7 to 0.9. If used with artist tags, it can be lowered. The weight depends on the particular artist tag / LoRA. Experiment.</li></ul>I'm still testing this LoRA, I'll add additional details later. If I don't forget.

Style 003 - WAI | NAIXL

I'll probably rebuild the dataset and retrain afterwards, removing this version. But I will keep it for now, as it fits my workflow perfectly.Well... This LoRA is shitty AF in terms of stability and strength cuz of experimental dataset. But! I really like the way it smooths/blends out the brushstrokes/colors/skin in other styles. So I decided to upload this version.So yeah, here's my main recommendation: Don't use it, just skip it and be happy :^)As a standalone style it is quite weak. But if you're a masochist like me who enjoys combining different artist tags, finding interesting combinations, then suffer. Let's cry together.Here's some information that might be helpful:<ul><li>Like STYLE 001 used as a SUPPORT LoRA, meaning you need to add artist tags or other LoRAs for better quality and stability.</li><li>Was trained to work with semi-realistic, realistic illustrations. </li><li>There is an activation tag: nhl-002, but you can leave it out. The difference is minimal.</li><li>More useful tags: realistic, painterly, nose, lips .</li><li>Trained on <a target="_blank" rel="ugc" href="https://civitai.com/models/833294?modelVersionId=1371790">NoobAI-XL vpred 1.0</a> . So it may not work well on other illustrious models. I recommend using <a target="_blank" rel="ugc" href="https://civitai.com/models/1217645?modelVersionId=1371790">ΣΙΗ</a>. My favorite merge at the moment.</li><li>Weight from 0.5 and up to 1. Here you need to adjust based on your own preferences. I've settled on 0.8. But look at your workflow, it's different for everyone.</li><li>If you are using ReForge and <a target="_blank" rel="ugc" href="https://civitai.com/models/1217645?modelVersionId=1371790">ΣΙΗ</a>, Try to use RES Multistep/Euler A Schedule type: Beta. I don't know how it is in other UIs, so I can't say anything.</li></ul>

Style 002 - NAIXL

I'm figuring out the model. In process rn.So far I can tell you this:<ul><li>Was trained and tested on the <a target="_blank" rel="ugc" href="https://civitai.com/models/827184/wai-nsfw-illustrious-sdxl">WAI-NSFW-illustrious-SDXL v12</a>. I haven't tried other models yet.</li><li>You can use weights in the range of 0.7-1, I stopped at 0.8-0.9</li><li>VERY RECOMMENDED to use artist tags. Improves quality.</li></ul>LoRA shows itself quite well with the following tags:<ul><li>limited palette - the basis of this LoRA, I recommend using it.</li><li>-any color- theme - just add a theme.</li><li>multicolored background - if you're tired of one color simple backgrounds</li><li>realistic - improves style, but it's a matter of taste.</li><li>film grain - it depends. Sometimes it improves image quality, sometimes it downgrade it. Also fine to put this tag to the negative prompt. Try it.</li></ul>And ye, experiment.

Style 001 - WAI

not HL's styles - [WAI/NoobAI] - [experimental garbage]

3dgifmaker20319.jpeg

Type	LoRA
Stats	1,361 27,627 8.3k
Reviews	Very Positive (308)
Published	Mar 14, 2025
Base Model	Illustrious
Usage Tips	Clip Skip: 2 Strength: 0.9
Trigger Words	nhl-001, limited palette, realistic
Hash	AutoV2 0594A1E908