We will comply with the ANYCOLOR secondary creation guidelines.
https://www.anycolor.co.jp/guidelines/
It seems that no particular intention is indicated. I pledge to create and publish works that respect the spirit of ANYCOLOR content.
特に個別の意向が示されていないと思われます。ANYCOLORコンテンツの精神を尊重した作品を制作、公表していく事を誓います。ange katrina
I am not responsible for the content you create with this model. However, it is CLEARLY not meant to and should not be used to create NSFW.
Also, go watch inuyasha if you haven't yet - THEN watch yashahime.
Towa Yashahime
I'm not responsible for the content you create, that being said this is NOT meant to produce NSFW of any kind, and there should be NO Danbooru or Gelbooru explicity content in any of the three yashahime models. This was created out of love for the fact that we've watched both seasons and adore this.
If you haven't watched it, do so.
I"d recommend all Inuyasha content first LOL.
Moroha Yashahime
We will comply with the ANYCOLOR secondary creation guidelines.
https://www.anycolor.co.jp/guidelines/
It seems that no particular intention is indicated. I pledge to create and publish works that respect the spirit of ANYCOLOR content.
特に個別の意向が示されていないと思われます。ANYCOLORコンテンツの精神を尊重した作品を制作、公表していく事を誓います。inui toko
One of EXTREMELY FEW NSFW models we'll produce. And while this isn't REALLY NSFW by the realistic count of it - it's CERTAIN that it is NOT PG 13. We don't have any porn models laying around but i'm sure you could get it to play ball. THIS IS ALSO TECHNICALLY A BETA EDITION - It still produces watermarks, text and is VERY hard to neg prompt the way out of it. (C'mon her data was REALLY hard to do without anything getting in the way - she's practically softcore before you actually gotta pay 24.95 an hour ..er .. wait what? XD)
TRAINING DATA IS A ZIP FILE WITH EPOCHS 1-9 of the model, it is'nt training data it's 9 other safe tensors files :3
This booba of death was something we were never allowed own in teh 90s (Shiz, we were what ... 11 when her popular trading cards were out? LOL)
Don't do anything you grandma wouldn't do, don't resell this, feel free to put on generative sites as long as it's credited and tagged properly.
Lady Death
Recommended weight: 0.85
have fun
This is an experimental model, the original purpose is to improve the picture quality, increase the sense of transparency, but in fact it will turn the screen tone into the color of amethyst, increasing the gray scale of the screen, the character's skin also tends to become pale, maybe it can have some special use, recommended weight 0.8~1, no trigger words,, have fun!
这是一个实验模型，本来的目的是改善画质，增加画面通透感，但实际上它将画面色调变成了紫水晶的颜色，增加了画面的灰度，人物的皮肤也容易变成惨白色，或许能有某些特殊的用途，推荐权重为0.8~1，没有触发词，玩的开心
We will comply with the ANYCOLOR secondary creation guidelines.
https://www.anycolor.co.jp/guidelines/
It seems that no particular intention is indicated. I pledge to create and publish works that respect the spirit of ANYCOLOR content.
特に個別の意向が示されていないと思われます。ANYCOLORコンテンツの精神を尊重した作品を制作、公表していく事を誓います。lain paterson
We recommend a weight between 0.7 and 0.9 when using it.
ex) <lora:moo:0.8>, ...
ハチナイ本校のユニフォームLoHAです
学習素材が背景透過だったからか背景があまりよくない気がするので気が向いたらVerupする
商用利用できるクオリティではないと思うけど商用利用はやめてね
hachinai uniform
如果你要支持我，请通过tangtuanzhu的微信联系我，给我支持...，这样我才有电费和显卡继续跑图。我的其他模型都在这里：ttplanet Creator Profile | Civitai
请下载我的范例图片并从webui中获得提示词，不知道是不是bug不能直接读取！！！
if you see missing generated data, please download the pic and get it back from webui! this is the new bug of Civitai！
Hires fix is highly recommended!
推荐一定要高清修复！
这个模型非常的好玩，可以把你的人物塞入一个包装盒里面，如果你组合使用其他模型就会出现玩具的效果。塞入包装盒的除了人物，还有和他相关风格的装饰，衣服等，你可以自己输入关键词来添加，虽然不能精准到每一个物品，但是也基本上八九不离十了。
目前没有加入动作支持，请自行使用controlnet控制动作，将在V2版本中迭代大量的动作，让使用起来更加简单随机，但是依然推荐使用controlnet进行控制以获得最好的效果。
注意事项，由于webui没有内置LyCORIS使用前一定要记得安装插件,
https://github.com/KohakuBlueleaf/a1111-sd-webui-locon
然后使用传统的方式调用lora, 比如： <lora:miniatureWorldStyle_v10:0.6>
请注意使用我的tag,你记得修改lora的名字，我的tag是本地的名字，和你下载的不一样！！
Reminder: if you want to use my tag, please check the lora name, see if it is consistent to what you downloaded!!! my local file name does not match the online version!!!
根据不同的模型，建议使用权重为0.6-0.8，但是不要使用1,基本上会爆炸。
使用结构为：
inbox\(ttp\)作为触发词，<lora:loraname:0.7>作为调用词，中间放入你放入的人物行了。使用很简单，人物描述尽量使用自然语言。
use 0.6-0.8 weight based on different SD models, but don't use 1
inbox\(ttp\) to trigger，<lora:loraname:0.7> to use the lycoris, and put down the person you want to put into the box, please use nature language to describe the person.
范例 example:
inbox\(ttp\), (8k, RAW photo, best quality, masterpiece:1.2), (realistic, photo-realistic:1.37),1girl, huge breasts, (holding a guitar:1.5), (solo), blonde hair, instrument, guitar, boots, pants, male focus, reference inset, standing, electric guitar, red pants, shirt, full body, microphone, long sleeves, amplifier, looking at viewer, white footwear, holding, realistic, shoes, blue eyes, black shirt, jewelry, fashion, short hair, english text, print shirt, glasses, holding instrument, full body, simple background,
<lora:inboxgirl_V1_loha-pickup1:0.65>
权重0.6-0.8是变成盒子的最好区间，低于0.6不会进入盒子但是会提高模型的身材，高于0.8会由于lyCORIS特点出现独特的画面劣化。请注意调整。日常使用请用0.65,这是我调节过最平衡的参数
please use 0.6-0.8 weight to get the best result, any weight lower than 0.6 won't trigger the box, and above 0.8 will destory the pic. for regular use 0.65 will be the best!!!
模型本身倾向使用平坦的胸部，请使用巨大来进行平衡。
the model is with high weight to be flat breast, so use huge to balance it
使用controlnet来控制你的人物动作，记得调整骨架的大概大小和位置。please use controlnet
controlnet也可配合大头骨架生成Q版造型，请查看我的范例图获得灵感。use controlnet can build the chibi outfit
可以和很多lora进行融合，使用的时候请注意控制权重。本模型权重较大，请适当增加你配合的lora权重, can be used with other lora together
face editor plugin 强烈推荐使用，脸部会因为lora变成你不喜欢的样子，可以搭配不同的lora使用face editor提高效果。就算不用lora也会更好看，使用face editor的时候请移除本lora再使用，保留其他prompt
inbox\(ttp\)
[......深度睡眠......Zzzzz......修改高级配置与电源管理接口......Zzzzz......]
Recommeneded prompts (from Sample Pics):
Outfit 1:
<lora:pti_locon_v1a:0.7>,1girl, black gloves, coat, cowboy shot, dress, gloves, goggles, goggles around neck, grey coat,medium hair, open clothes, open coat, simple background, solo, white background, white dress, looking at viewer, long sleeves, armband, wide sleeves,bangs, closed mouth
Negative prompt: EasyNegative, verybadimagenegative_v1.3
Steps: 20, Sampler: DPM++ SDE Karras, CFG scale: 5.5, Seed: 580231220, Size: 512x1024, Model hash: c870e984cd, Model: anythingv5.5, Clip skip: 2, ENSD: 31337
Saved: 00269-580231220-_lora_pti_locon_v1a_0.7_,1girl, black gloves, coat, cowboy shot, dress, gloves, goggles, goggles around neck, grey coat,medium h.png
Outfit 2:
<lora:pti_locon_v1a:0.7>,1girl, backlighting, black shorts, black thighhighs, breasts, closed mouth, coat, dress, expressionless, eyelashes, feather hair ornament, feathers, from above, hair between eyes, hair ornament, large breasts, looking at viewer, looking up, medium hair, open clothes, open coat, short dress, short shorts, shorts, simple background, sitting, solo, thighhighs, turtleneck, white background, white coat, white dress, zettai ryouiki, bangs, long hair
Negative prompt: EasyNegative, verybadimagenegative_v1.3
Steps: 20, Sampler: DPM++ SDE Karras, CFG scale: 5.5, Seed: 2596584012, Size: 512x1024, Model hash: c870e984cd, Model: anythingv5.5, Clip skip: 2, ENSD: 31337
Saved: 00271-2596584012-_lora_pti_locon_v1a_0.7_,1girl, backlighting, black shorts, black thighhighs, breasts, closed mouth, coat, dress, expressionless.png
Trigger word: You don't need trigger word for this model!
Recommeneded Weight: 0.6-1 (You can adjust it by your perference.)
CFG scale: 5.5-7
Check point recommendation: Anything V5
I am still tuning the LoCon model, I may publish a new version later.
Some sample figures were generated with my Vivid Impactful Style - LoRA
How to use LoCon/LyCORIS? Please read instruction of a1111-sd-webui-locon.
If you like my work,please give me a like <3.
如果你喜欢我的模型请给我一个赞 <3.
もし、私のモデルが気に入ったら、「いいね！」をクリックしてください<3。
1girl, black gloves, coat, cowboy shot, dress, gloves, goggles, goggles around neck, grey coat,medium hair, open clothes, open coat, simple background, solo, white background, white dress, looking at viewer, long sleeves, armband, wide sleeves,bangs, closed mouth1girl, backlighting, black shorts, black thighhighs, breasts, closed mouth, coat, dress, expressionless, eyelashes, feather hair ornament, feathers, from above, hair between eyes, hair ornament, large breasts, looking at viewer, looking up, medium hair, open clothes, open coat, short dress, short shorts, shorts, simple background, sitting, solo, thighhighs, turtleneck, white background, white coat, white dress, zettai ryouiki, bangs, long hair
Trained on Anything V3 using cherry picked pictures from the Love Hina Anime adaptation (aired in 2000).
Gettings pretty good results with a default weight of 1, and then going to 0.8 (more liberty on outfits) or to 1.2 (better looking face and fidelity of the character). Adding kendo training and shinai keywords in prompt helps to get her with the kendo outfit and a fighting pose.
As training pictures are only from the anime adaptation, you will also have a high chance to get the same "2000 anime style feeling".
motoko aoyama
Will get retrained soon. V1 is more stable than v1.5
ruby hoshino
Lycoris model
Natalia Poklonskaya
natpok
LyCORIS of Morgan Freeman.
Along with the model is the guide on how I make those models: https://rentry.co/lycoris-and-lora-from-dreambooth
Morgan helped me by providing narration and his face for tests :-)
The guide also has its own page here: https://civitai.com/models/45539/dreambooth-lycoris-lora-guide
sks person
一个简单而普通的姿势，表现出好兄弟之间的深刻友谊（？
A simple and common gesture that shows the deep friendship between good brothers (?
可供参考的prompt：
Prompts for reference:
1boy,1girl,muscular,large breasts,breast grab,arm over shoulder,smile,breasts out,nipples
在此基础上你大可随意改动而不必拘泥
On this basis, you can change it at will without sticking to it.
breast grab
What does it do you ask? I dub thee waifu, Dame "Insert Name Here"! Basically, makes your waifu a sick armored knight ready to go fight gloriously against some... Husbandos? Other waifus? Unsure but this one is for those who like their waifu's to look like warriors (who show a little skin) and who are ready to kick some butt.
How to use it:
(I use Sampling Method DPM++ SDE Karras and Upscaler R-ESRGAN 4x+ Anime6B)
Main Triggers
KnightT, armor - Main trigger words.
Optional
Anything that you want to push more in this Locon. Holding a sword? Wearing a skirt? Decked in full armor? You choose!
Extra, Extra!: Should be well trained and usable in most models. Images shown for example.
Picture Descriptions:
1-2: AnythingV3 using just this Lora.
3: AnythingV3 combo'd with my released Rosalina (Disgaea 5) Lora.
4: AnythingV3 combo'd with my realeased Yunaka (Fire Emblem) Lora.
5: AnythingV3 combo'd with my released Tohru (Dragon Maid) Lora).
6: AnythingV3 combo'd with my released Catherine (Catherine: Full Body) Lora.
7: AnythingV3 combo'd with my released Symbiote Taking Over Locon.
8: AnythingV3 combo'd with my released Phone Pic Locon.
9: AbyssOrange using just this Lora.
10: PerfectWorld using just this Lora.
11: ChilloutMix using just this Lora.
How was it trained?
It was trained on animefull_final with 32 images with the usual self-pruning and tagging and a wide range of different images. I like keeping my prompts simple for the first few pictures so that you can see it without a whole bunch of mumbo jumbo. Make your pictures better than mine though!
What's next for this?
Should be good to go with this one but let me know of errors.
What's next that isn't this?
More character Loras. (Viper and Rupee from Nikke, Spectre Tenebria from E7, Zephia from Fire Emblem Engage, Ivy from Soul Calibur 5, Heine from Combatants Will Be Dispatched, Conqueror Lilias from E7, Evelynn from LoL (both base and All Out version), Tharja from Fire Emblem, Laharl-Chan from Disgaea 5, Miku from Idaten Deities, Kuribayashi Shino from GATE, Rin Sohma from Fruits Basket, Kasumi from P5, Ann from P5, Ikumi Mito from Food Wars, Alice Nakiri from Food Wars, Chika Fujiwara from Kaguya-sama, Lulu from FF10, Momo from My Hero, Sheik from Zelda, Lucoa from Dragon Maid, Laharl-chan from Disgaea, Dominique de Sade from Vanitas, and Dos from One Punch Man.) And maybe Wilhelm van Astrea, my favorite Re:Zero husbando or a Prinny from Disgaea.
V2's of some of the previous Loras. Specifically make them more diversely acceptable with other models and LORA's.
I also have some more quite NSFW Locon's. I decided to list them as well, so if people have preferences on which to fix up first let me know. Specifically, Bound Yuri (two girls tied up, breast to breast, and forced to make out), Beta Censorship (Automatically censors any images you create to make them BetaSafe), Demonic Transformation, being stepped on, Robotification, Defeated (decently NSFW defeat scenario for the waifu getting abused), Petrified (I'm unsure if I should bother with this one anymore), Infection (this one is VERY nsfw, as the waifu is completely infected), Dominatrix (waifu becoming a dominatrix), Brainwashing Machine, Tentacles, Pillory, Masked Evil (A mask that possess' the waifu), Latex Corruption, Combat Drone (hard to describe but basically making them a mindless sci-fi combat warrior), JAV Supervillain, Jiangshi (Transforms into a Jiangshi), Mind Flayer Defeat, Blacked, Hypnotized Harem, Hourglass Figure (just to make your waifu curvy), and Holding a Leash.
And, uh, I want to make a few SFW Locon's so I have an GoodCop/BadCop (Locon with outfits for being a good and for being a bad cop), Biker Chick (ride a motorcycle and look like you should), Race Queen (Chiling sexily on a car with a hot outfit), forest fairy, Anime Officer, barbarian, Gothic Girls.
Additionally, I love the style of Defaultz_17, so I'm making a Locon to mirror that.
Or just give me some random suggestion or priority opinions. That works too.
I've also added a couple of my extreme NSFW preview images to my twitter (https://twitter.com/TwoMoreTimes89). Let me know if you think I should work on them more for a submission here.
KnightTarmor
1boy, solo, orange hair, short hair, mask on head, red mask, grey coat, mask, half gloves, stand, look at you, red scarf, single red earrings, tartaglia \(genshin impact\), grey pants, close mouth, blue eyes, ruby on scarf, masterpiece, best quality, <lora:childeloha:0.75>
权重0.6-0.85之间都可以的，最好0.7/0.75，如果想融合别的lora权重可调低到0.3-0.45
训练依赖的大模型：mixProV3_v3
更了换了训练用的大模型
这个版本比较内向，还是有过拟合
1boyorange hair