Civitans! Most issues have been resolved! LTX generations and training will have issues, ComfyCloud is also having some issues with outputs. Our team is on it, working hard to get things running smoothly again, but you may experience some inconsistent behavior in the meantime. Thanks for your patience!

Generation and Training Limitation

Krea 2 LoRA training is 50% off, and we're running a Krea 2 Training Contest with 1.8 million Buzz in prizes across four LoRA categories.

⚡ Krea 2 Training Contest + 50% Off Training

<h1 id="heading-113">VivCharMix</h1>Recommended DPM++ 2M Karras Hires Nearest 0.5 negative Prompts: (low quality,EasyNegative:1.2)No need for VAEAdvantages:(1) Generates good-looking faces, suitable for turning ACG characters into real-life people, preserving their looks, charm, and clothing details(2) Highly adaptive and tolerant to ACG Loras (recommended weight: 0.3~0.8, adjust in 0.05 intervals)(3) Photorealistic ( Vivid, full colors and dynamic expressions in previous version

ViVCharMix_V5 New Era

v2.9

v4.0 recommed neg words: (low quality, worst quality, lowres, grayscale, normal quality, username, outline, poorly drawn, copyright name, character doll, scribble , silent comic, doujinshi,:1.4) Outstanding ACG female figures, backgrounds, and actions are vivid and vibrant. High tolerant. The downside is that there is a problem with the feminization of male characters.

v4.0

更好的細節呈現 Better detail presentation

v3.0

Another interesting version, deeply integrated with an excellent model - kencanmix, is merged using the mbw-R-consine method (don't ask me why; it's just testing and selection). It has outstanding light and shadow effects and foreground sharpening performance, but the body shape is not stable at different angles (within an acceptable range). I think it's better and more interesting than before. 另一個有趣的版本，和一個出色的model-kencanmix深度融合，使用mbw-R-consine方式融合(別問我為什麼，就是測試和挑選)。 擁有更出色的光影和前景銳化表現，但是不同角度體型不穩定(在可接受範圍)。覺得比之前好，有趣。

v2.1R

很好的光影感、背景，調整色調，身材 更真實，所以可以有更高的容忍值增加其他LORAs 不像V1如此鮮豔，所以V1更適合展示 所以我給予V1命名-Aesthetics、V2-Appealing Great sense of light and shadow, background, color adjustment, and body shape. It's more realistic, so it can have a higher tolerance for adding other LORAs. Unlike V1, which is so vibrant, V1 is more suitable for display. Therefore, I named V1 - Aesthetics and V2 - Appealing.

v2.0

v1.0 puned

如果沒有辦法改進場景問題，這個就是完成版If there is no way to improve the scene issue, this is the final version.

v1.0

VivCharMix

physical violence

weapon violence

wide hips

revealing clothes

downblouse

convenient censoring

pg-13

corpses

suggestive

oral invitation

pg13

sexy

huge breasts

thick thighs

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

female underwear

nude

nsfw

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