sexual situations

physical violence

disturbing

male nudity

extremist

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

self injury

graphic violence or gore

graphic female nudity

corpses

wide hips

convenient censoring

peeing

oral invitation

emaciated bodies

exposed female nipple

blowjob

female nudity

suggestive

sexual activity

sexual intent

undressed

male underwear

female swimwear

genitals

female underwear

thick thighs

breasts out

strapless leotard

vore

bestiality

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

bukkake

cumshot

cumdrip

cum in pussy

cum on face

cum on hair

cum on body

cum on tongue

cum on hands

cum in mouth

cum on pussy

eat_cum

fellatio

implied fellatio

after fellatio

triple fellatio

autofellatio

pov fellatio

fucked silly

presenting ass

presenting pussy

spreading legs

spread legs

swimwear

TRPCError

Strange named experimental styles trained on distinct cherrypicked AI outputs. Check version descriptions for more specific info.

Version trained from <a rel="ugc" href="https://civitai.com/models/833294?modelVersionId=1140829">Noob-vpred-0.7.5</a> from hf. Should be compatible with recent vpred and S versions either. <a rel="ugc" href="https://files.catbox.moe/if8v0u.txt">List of all styles</a> in this version, oekakischizo was renamed to firedotinc

AIO-noob-vpred0.7.5_v3.2

<a target="_blank" rel="ugc" href="https://civitai.com/models/950531?modelVersionId=1130140">Rouwei 0.6.1</a> version. Half of the styles already presented in the model from v2 version of dataset. You can prompt with or without "by", while using this lora, both should work fine. <a target="_blank" rel="ugc" href="https://files.catbox.moe/vkd9e2.txt">List of all styles</a> in this version is same as <a target="_blank" rel="ugc" href="https://civitai.com/models/723360?modelVersionId=1138482">AIO-noob-eps1.1_v3.1</a>.

AIO-rouwei-0.6.1_v3.1

Version trained from <a rel="ugc" href="https://civitai.com/models/833294?modelVersionId=1116447">Noob-epsilon-1.1</a>. Simple to use, since it's just epsilon checkpoint. <a rel="ugc" href="https://files.catbox.moe/vkd9e2.txt">List of all styles</a> in this version

AIO-noob-eps1.1_v3.1

Version trained from <a target="_blank" rel="ugc" href="https://civitai.com/models/833294?modelVersionId=1070239">Noob-vpred-0.6</a>. Should be compatible with 0.65 and 0.5 either. The main difference is filtered and expanded dataset. <a rel="ugc" href="https://files.catbox.moe/21wbdv.txt">List of all styles</a> in this version

AIO-noob-vpred0.6_v3

<a rel="ugc" href="https://civitai.com/models/833294?modelVersionId=1070239">Noob vpred 0.6</a> version. <a rel="ugc" href="https://files.catbox.moe/02z6s2.txt">List of all styles</a> in this version. CFG rescale could be useful with some prompts, if you see color blowing out, enable it

AIO-noob-vpred0.6_v2

<a target="_blank" rel="ugc" href="https://civitai.com/models/950531?modelVersionId=1064242">Rouwei </a>version. Checkpoint itself has fried unet, it may output mess with some random conditions or some unlucky seeds, so expect that. <a target="_blank" rel="ugc" href="https://files.catbox.moe/02z6s2.txt">List of styles</a> in this version

AIO-rouwei0.6-vpred_v2

This version was trained from <a rel="ugc" href="https://civitai.com/models/833294?modelVersionId=962003">early vpred noob conversion</a>, NOT from 0.5 vpred or higher and I haven't tested if it will work properly with that, but probably should. Set settings like on the <a rel="ugc" href="https://files.catbox.moe/l0slu3.png">screenshot</a>

youmuanon-noobvpred0.1_v2

Version trained from <a target="_blank" rel="ugc" href="https://civitai.com/models/833294?modelVersionId=1022833">noob-epsilon-v1.0 checkpoint</a>, checkpoint itself is stiff and hard to control, until you start using some cfg rescaling. I highly recommend <a target="_blank" rel="ugc" href="https://files.catbox.moe/mn3ow9.png">doing that with comfyui</a> or <a rel="ugc" href="https://files.catbox.moe/pjru7k.png">reforge</a> with a value &gt;0.75. A lot of images doesn't display metadata, it's comfyui images with whole workflow and prompts. <a target="_blank" rel="ugc" href="https://files.catbox.moe/tsddmz.txt">List of all styles in the model</a>

all-in-one-noob-eps1.0_v1

Version trained from <a target="_blank" rel="ugc" href="https://civitai.com/models/833294?modelVersionId=1046043">noob 0.5 vpred checkpoint</a>. Should be used with it, settings in reforge <a target="_blank" rel="ugc" href="https://files.catbox.moe/l0slu3.png">should be set like this</a>. List of all styles contained in this version <a target="_blank" rel="ugc" href="https://files.catbox.moe/4b4ej0.txt">here</a>. Could be useful to use a little bit of cfg rescale, like 0.35

AllinOne-noob-vpred0.5_v1

Same as all-in-one-noob-eps1.0_v1 but for pony. No need for any rescales, just as usual. <a rel="ugc" href="https://files.catbox.moe/tsddmz.txt">List with all styles</a>

all-in-one-pony_v1

<a rel="ugc" href="https://www.pixiv.net/en/users/109593509/artworks">Cherrypick</a>. Trained from and for noob vpred checkpoint and derivatives, settings for using vpred <a rel="ugc" href="https://files.catbox.moe/l0slu3.png">should be set like this</a>. More like a fishmonger optimizer test that ended up as a success.

mm_type_one_noob_vpred_v1

Version inspired by <a target="_blank" rel="ugc" href="https://civitai.com/models/734181/flutesalad-style-artist-mix">this artstyle lora</a>. Half of the dataset was kindly provided by the author of that lora, the other half was additionally added from nai gens. This version was trained from <a target="_blank" rel="ugc" href="https://civitai.com/models/833294?modelVersionId=962003">noob-vpred-checkpoint</a> checkpoint and should be used with vpred noob model and derivatives. Use latest version of <a target="_blank" rel="ugc" href="https://github.com/Panchovix/stable-diffusion-webui-reForge/tree/dev_upstream">reforge dev_upstream branch</a> with <a target="_blank" rel="ugc" href="https://files.catbox.moe/l0slu3.png">this settings</a>.

flutecocktail_noob_vpred

Version inspired by <a target="_blank" rel="ugc" href="https://civitai.com/models/734181/flutesalad-style-artist-mix">this artstyle lora</a>. Half of the dataset was kindly provided by the author of that lora, the other half was additionally added from nai gens. This version was trained from <a target="_blank" rel="ugc" href="https://civitai.com/models/833294?modelVersionId=968495">noob-0.5-epsilon</a> checkpoint, so should be compatible with most illustrious epsilon models.

flutecocktail_noob_eps_v2

This version same as dj_sloppa_illust_v2, but trained from <a target="_blank" rel="ugc" href="https://civitai.com/models/833294?modelVersionId=962003">noob vpred checkpoint</a>, so you should use it exclusively with that model. Reforge webui settings should be set as depicted on <a target="_blank" rel="ugc" href="https://files.catbox.moe/l0slu3.png">this screenshot</a>.

dj_sloppa_noob_vpred_v2

Version trained on mostly random, but consistent, shiny ai arts

dj_sloppa_illust_v2

Same as hstoigaf_pony_v3 but trained for Illustrious model, config included

hstoigaf_illust_v1

"Holy shit that one is good af" trained from autism checkpoint, so it will probably work good only with autism base mixes. Reason of that is simply because it's working and transferring style better that way. Trained on cherrypicked pics from <a rel="ugc" href="https://www.pixiv.net/en/users/18898196">here</a>

hstoigaf_pony_v3

"You might be seen this style somewhere huh" trained on works from <a target="_blank" rel="ugc" href="https://www.pixiv.net/en/users/103452158">here</a>. Could go up to even 1.5 strength for more effect when used alone. There is also a nice combo in separated examples down in the gallery that gens nice, imo, outputs

ymbstssh_pony_v2

"I don't know what that style is but I like it" trained on works from <a rel="ugc" href="https://www.pixiv.net/en/users/49622199">here</a>

idkwtsibili_pony_v1

AI styles dump (Illustrious/pony/noob)

holo_main.png

Type	LoRA
Stats	707 6,027
Reviews	Very Positive (75)
Published	Dec 12, 2024
Base Model	SDXL 1.0
Training	Steps: 20,940
Usage Tips	Clip Skip: 1 Strength: 1
Trigger Words	style_name
Training Images	Download
Hash	AutoV2 0147E2941B