Your AI agent can use Civitai now: browse, generate, post, and engage through the new MCP server and gen skill.

Agents Welcome

Our primary data center is pulling GPU support to switch to mining, on under 48 hours notice. Generation still works but will be slower while we move. Here is the full picture and what to expect.

A GPU Crunch, and Bumpy Days Ahead

This model focus on ancient orient and myth age.

神话V10=未来科技v5+复制特效(AgarthaChadstyle+泥巴+fantasyworld)-山顶洞人+渲染（1234567） 测试:气球、海底城市、DNA建筑、未来科技、飞机、飞空艇、做菜。0.75(123hellocounterfantasyagartha7550) + 0.25(1234567oukawestfantasyagarthaelementdarkweird202627232425)0.65(123hellocounterfantasyagartha7525 + 0.25(FTv5 - hrv10test250山顶洞人)) + 0.35(1234567oukawestfantasyagarthaelementdarkweird202627232425)

shenhuaV9=noreal50(fantasy+agathaChadstyle-anime-realistic)+123zhunomanazovya4050+chinoiseriemixv2

a+b,fantasy world+(lofi+epic)+(zhuzhishanG+aZovyaRPG+no man diffusion+urben)+robotv2+中国风=ShenHuaV8原名：shenhuav7.1test1945,测试了不计其数配比合并顺序，有很多独具特色样本但作为全能性MODEL并不完美，V8特点实在太多了，和6功能性相比虽然稍弱，然而强在美观和想象力的延展，以及机械表现，ShenHuaV8兼具FTv4,Fantasy world的部分功能，或搭配来用。

ShenHuaV8

暂时最终版，a+b:fantasy world+lofiepic50+zhunourben50+robotv2+中国风=Shenhuav7,部分情况下容量可以翻倍，先用大并小，5G多再用小并5G大到7G，再7G并5G到9G。搭配多次失败，暂时最终版有点遗憾不是完全真实，但9G内容出图不错且更加稳定，AI筛选样本游刃有余，不过还是需要更多测试图。

ShenHuaV7

2.8Dv5+(Zhuzhishan+No man diffusion+Minustype UrbanDesign)+Neon Isometric+Fantasy World=ShenhuaV6,不是我要的但超出想象，具体看测试图。

ShenHuaV6

A+B,(刀鞘2+NightSky+EldenRing3+Envy)+(Chosenchinese+Chinese Wedding2.0)=ShenhuaV5,comic or anime.

ShenhuaV5-ANIME

2.8D神话版本最好，可以看是V2的完美升级版，4模型合并了神话V1、诡异中式、西幻和5000LORA模型2.2，橙汁有更好表现力，文字成图容易出怪，减少高纬度出2D抽象图的比率。The 2.8D myth version is the best and can be seen as the perfect version of V2. The 4 models combine ShenhuaV1, chinese weirdness, WestMagic, and megamodel 2.2(5000lora). fruit juice has better expressive power, and text graphics are prone to monster, reducing the ratio of 2D abstract images at high posible.

ShenhuaV4-2.8D

神话V3是基于V2版基础上，与西幻，5000LORA模型，真实v6四拼装合成的，由于真实V6加入现在也可以使用年代服饰，但牺牲了敦煌的一些特点，水中敦煌出图直裸片瓦不带，LORA融合程度和V2版差不多，每个不同维度丧失的功能可以前模型交换着用。A+B,Four Packs:ShenhuaV2+Westmagicv10+megamodel4800_21+HRV6=ShenhuaV3ShenhuaV3 is a realistic fantasy model.ShenhuaV2 is 2.8D,and GuzhuangV1(ShenhuaV1)is 2.5D. They are not which one the best but each one got own features by itself.

ShenhuaV3-HR

2.8D（内含GuZhuangV1,CHINESE WEDDING,SERVMIXV2）融合了敦煌模组,与LORA很好的兼容性。2.8D (including GuZhuangV1, CHINESE WEDDING, SERVMIXV2) integrates Dunhuang modules and has good compatibility with LORA.

ShenHuaV2

merge some hanfu model, very good effect.2.5Dv4+刀鞘2.0+ChosenChineseStyleNsfw+hanfuDreamboothv1=GuZhuangv1

GuZhuangv1

MYTH AGE/神话时代

00381-2071421457.png

physical violence

weapon violence

wide hips

revealing clothes

thick thighs

downblouse

convenient censoring

huge breasts

pg-13

corpses

suggestive

oral invitation

pg13

sexy

sexual situations

male nudity

disturbing

male swimwear or underwear

female swimwear or underwear

partial nudity

undressed

female nudity

breasts out

exposed female nipple

breast out

lingerie

male underwear

hair over breasts

female swimwear

gigantic breasts

no panties

graphic violence or gore

covered nipples

huge butt

strapless leotard

sitting on face

emaciated bodies

one breast out

nsfw

female underwear

nude

graphic male nudity

adult toys

illustrated explicit nudity

nudity

graphic female nudity

hentai

futanari

porn

sexual intent

genitals

peeing

vore

oral

sexual activity

anal

blowjob

dildo riding

incest

hanging

hate symbols

nazi party

white supremacy

diapers

scat

self injury

hate speech

urine

extremist

child on child

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