Thanks to @konyconi for the guide, and thanks to @navi_os for the dataset.

LyCORIS of former adult actress Bree Olson. Trained at 768x768 with 111 images, mostly close-ups but some from waist up & full body included, should be pretty flexible.

Use bree olson as the trigger, also smiling and grinning can be used for a happy expression, or put those in the negative for a more neutral expression.

Sample images were generated with realisticVisionV20, with 0.65 strength then inpainted at 1.0 strength (used the batch face swap extension to automate this).

First model I've uploaded here, so I'd love to hear your feedback/suggestions!

好的手需要运气这件事我想大家应该不用我再强调了吧

Good hands need luck. I don’t think you need me to emphasize it.

下面是脱口秀时间，因为比较长还是一个梗，我就不翻译了

The following is the time for the talk show, as it is still a meme, I will not translate it anymore

总结一下就是，目前我试了几个已有的Pov missionary都是简单动作概念，我本来打算将Pov missionary的多细分概念合一，然而失败多次，决定拆分制作

The general content is that at present, I have tried several existing Pov missionary loras, all of which are simple action concepts.
I originally planned to combine the multiple subdivision concepts of Pov missionary into one, but failed many times, so I decided to split it.

我也想一个lora概念全包

是不是很大胆

一个lora概念全包

在Pov missionary这一个

就这个lora

就完全是这个lora   分概念全包（指包括什么leg grab、holding another's wrist、torso grab等等）

我最早收集数据集的时候

跟所有群友说的都是一个全包

难以想象

喔所有群友啊 

他们所有人都很兴奋（其实只有我）

一个全包一直说的是一个全包

我一直在做一个lora概念全包的准备

所以当时跟显卡说的时候

我只要你20天

或者只要你25天

10epoch到15epoch

显卡说为什么

我说很简单

我每天炼两遍

一锅lora两个小时

我每天炼两遍

上班炼一遍

下班炼一遍

我每天炼两遍

我炼十天

400多个lora我选一个

一个lora概念全包啊

这个Pov missionary就完了

我选一遍

那十天就够了

然后前面的十天打标

严格的打标

我说只要你10天咱就炼一超全的lora

就挑战性太大了

一点都不能错呀

但是后来我还是放弃了

你知道为什么

我研究了大量的包含复数概念的lora

也有一些大概念lora

还有尤其是最近这2个月

有一些实验性的多概念多角度lora

我自己做的别人做的我都看过

我专门   看研究

也就一直我就一直下不了决心

其实在sex from behind的时候

我就想做一个多概念多角度合一的

到底后来也没有做

你知道最大问题是什么

当然这是一个专业问题

简单的说最大的问题就是，同步拟合

就是同步拟合

因为多个概念啊，拟合没有办法

对于一个多细节的

对于一个多变化的

一个复数概念的一个lora来说

那么适合的一个拟合程度达不到，同步拟合达不到

拟合度达不到

因为你不能正面是这样子

不可能

你从正面到侧面、从握手到抓胸

这一出图就寄了

第一是拟合达不到

无论怎么样

我想来想去

因为我算个内行吧（笑）

我不炼我就知道拟合达不到（其实炼了）

同步拟合实现不了

第二个   作者的精神状态会损失一半以上

作者的精神会损失一半以上

作者的大脑会损失一半以上的san

是看不看不到的

lora就不好做了

lora就不好做了

最后我差不多半个多月的思想斗争

那是个重大决定

一个个训练集都是按照一个lora概念全包准备的

还ps、打标呢

后来说我放弃

 我自己决定放弃

一个人做的决定

一个人的思考

半个多月以后

我放弃以后

就觉得好像就没劲了

不能一个lora概念全包

就觉得好像就不想做了（哈哈哈）

开玩笑啊

就所有人都沮丧而失落（就我自己）

我也很难过

我后来还是放弃了吧

所以制作概念lora是一个学习

它对于一个追求高质量的一个创作者来说

它是破坏性的

一个lora概念全包又能怎么样

你丢掉了质量

丢掉了牺牲了出图成功率

孰重孰轻啊（点头）

Get early access to build and test build, be able to try all epochs and test them by yourself on Patreon or contact me for support on Discord

Recommended settings:

• Make sure you are aware on the usage instructions of LORA

• Sampler: DPM++ SDE Karras (Recommended for best quality, you may try other samplers)

• CFG Scale : 5 to 10

• Lycoris weight for txt2img: reccomended 0.35

Those are a Lycoris, to use it you need to install the proper extension on Stable Diffusion.

My advice is to start from the prompt of the posted images on civitai, or in any case use most of the keywords with 1.2-1.3 weight.

In general if you want a classic ironman suit you just need to use the keyword "wearing irongirl_suit" maybe with a weight if necessary.

If you want a mix like irongirl|ballet or irongirl|spider you should use both keywords, in this cases i have an important advice, play with weights! mostly when adding a particular color to the suit. I make you an example, most of the training ballet dress images are white, most of the training irongirl suit are red, so if you write "(wearing ballet dress with tutu, wearing white irongirl_suit:1.3)" SD will probably generate a normal white ballet dress, so in this case it's better to lower the weight for the ballet dress to have the mix you want, like "(wearing ballet dress with tutu:1.1), (wearing white irongirl_suit:1.3)". Opposite case if you want a red irongirl ballet dress suit.

Enjoy!

If you'd like to support my efforts and have access to early and bleeding edge builds, please think about joining my Patreon: https://www.patreon.com/betterCuteAsians

pregnancy test concept

you can active with:holding, pregnancy test, pregnancy announcement, pregnancy test strip

here my pixiv:https://www.pixiv.net/en/users/34515535

my tw:https://twitter.com/phucbessu216

Get early access to build and test build, be able to try all epochs and test them by yourself on Patreon or contact me for support on Discord

My advice is to start with posted images prompt.

Also, for each model, look on version description and on keywords on the right panel.

Enjoy!

If you'd like to support my efforts and have access to early and bleeding edge builds, please think about joining my Patreon: https://www.patreon.com/betterCuteAsians

A Locon of ba-zerarudo from Frame Arm Girls.

Trained Trigger words:

ba-zerarudo | leotard | pantyhose | rabbit tail | high heels

Pictures below are generated on Any4.5 with Controlnet.

Can't believe she is 40! Very affectionate and beautiful woman. Best result with 0.7-0.8 weight with hiresfix.Hope you like it :)

Credits (Because civitai doesn't recognize them even though I installed the extension):

EnvyBetterHands LoCon : https://civitai.com/models/47085?modelVersionId=55199

Sharpness Tweaker LoRA : https://civitai.com/models/69267/sharpness-tweaker-lora-lora

I wanted to generate some non-erect penises so ended up training on flacid penises.

For now it's mostly dicks with foreskin and it's hard to change dick size. Will update this in the future.

This is trained on zoomed in/cropped images so it does not interfere with other content or style in a gen.

The token is 'flacid' and you can combine 'foreskin' or 'retracted foreskin' though mileage may vary.

You can also add 'testicles' but it might look iffy with front facing views and make a double penis.
Also works great with inpainting!

english↓

This is lora by lain paterson, a member of the virtual youtuber group nijisanji.

The strength of lora is recommended to be around 0.8~1.

Trigger words:1 girl,pta

It also works well if you put the words that occur frequently by putting lora itself through analysis.

This may not be a lora with satisfactory accuracy since it was made as a trial.

Please enjoy it if you like.

https://www.anycolor.co.jp/guidelines/

japanese↓

これは、バーチャルyoutuberグループのにじさんじに所属しているレイン・パターソンのloraです。

loraの強度は0.8~1くらいがおすすめです。

トリガーワード:1 girl,pta

また、lora自体を解析にかけて頻出するワードを入れてみると効果があります。

お試しで作ったので、満足のいく精度のloraではないかもしれません。

よければお楽しみください。

This is a lycors\locon you have to use the additional networks extension or the lycoris extension for this to work.

As I was going through my list of Pokemon Girls that I have still to make I deliberately left out all the popular ones because they have most likely already a model or two and I thought Erika would be no different but out of curiosity I just typed Erika in the search bar and got zero matches. So here we are.

Keyword is Erika works well on 1.0 can get her default outfit very easily (it's just a kimono so it's not very difficult to begin with) you might have prompt her eye color if you use tags like beautiful eyes or perfect eyes because for some reason the AI thinks perfect eyes are blue most of the time and i didn't want to prune her eye color because it was so different in the dataset some had grey eyes others were black and some had brown eyes...

But the model came out pretty well I think I messed up my training settings in the last model I published and I will review it tomorrow this model is totally fine though.

If you like it leave a comment, like and rate it that would be appreciated.

Have fun generating

This is a lycors\locon you have to use the additional networks extension or the lycoris extension for this to work.

Not much to say about this one..

It had a small dataset and I don't really like the model it looks kind of blurry for no reason maybe because of the background prompts i used but i don't want to hold it back for the people that actually wished for this character to be released .

Keyword is Rui works on strength 1.0 adjust if you have to.

If you like the model leave a comment, like and rate that would be appreciated.

Have fun generating

LyCORIS (LoCon) trained to generate elevator interiors. Some models aren't able to generate elevator backgrounds consistently so this should help.

Please rate and leave a like if you enjoyed it! And be sure to follow to check out the upcoming models.

Trigger: elevator

Some useful positive or negative tags: control panel, door handle, handlebar.

Additional info

I make these models for fun and for the challenge and release them for free for everyone to enjoy, for non-commercial use (see license). The one thing I ask of you is to provide rating and feedback! That helps me understand where I can improve and helps me stay motivated to produce more content!

I accept suggestions or requests here or on Civitai discord server.

You can also check my more polished images and upcoming models on my pixiv profile.

( ͡° ͜ʖ ͡°)

V2Beta:

• it's a LoCon now, trained at 768x768

• Much better at making 3D clothes and "coop gamemodes" now

• suggested strength:0.8

• best used with a character lora

• rim lighting, stylized 3d render, 3d, overwatch, blender, arhoangel (or yeero) are heavily recommended prompts

• Check the example images for pretty good prompts ( <lyco:LoCon2reps6000-000002:0.8> is indeed this LoCon, i renamed it a bit late)

• Dataset is now about 1000 images

V1:

it's 2 AM here so i'll keep it short for now:

• trigger word is overwatch 3d porn style

• suggested strength: 1

• blender, 3d are relevant extra prompts

• trained on about 620 overwatch porn renders from a handful of top artists, lazily grabbed using grabber with: "[artist name] overwatch -animated"

• some character LoRAs work best at around 0.8 strength, other at 0.5 (especially 2D anime girls)

• rule of thumb: the more clothes your character wears, the less 3D it will look

• defaults to an absolute fertility goddess body

• also tends to turn blonde characters into Mercy

• trained on nai, works pretty good on Anything V4.5, where my example images come from

• check the example images for decent prompts

As usual with my stuff, lots of room for improvement but i like what it does already and should really just go to bed

Trained on vanilla sd1.5

Please check out my Ko-Fi page if you are interested in supporting me.

LoRA commissions open! -> Fiverr

This is a LoHa LoRA! You need the extension! Why? They do a lot better with multi-concepts.

Trigger words for V1.20:

positive: <lora:tongheLeotardv120:0.75>(thong leotard)

Lower Lora weight to generate men.

Follow the steps in the Model Version notes to reproduce my images.

Sample images generated with Nothing, DeimosAnime and .

All negative embeds should be easy to find. and Prompts should be included in the sample images! Click the little icon in the bottom right to see it.

It was trained on 71 512x512 images provided by thesauceer, 20 epochs using Animefull-final-pruned for the Training Model.

Danbooru tags generated by Waifu Diffusion 1.4 Tagger.

This LyCORIS has been trained after carefully selecting 150 images. All photos have been enhanced to make the most of them. I hope you like it!

Any feedback would be highly appreciated!

From my experience it runs best with Edge Of Realism, pirsusEpicRealism, epicDiffusion ,RealisticVision, CyberRealistic, Deliberate checkpoints, among others, although I think it will be just fine in other SD 1.5 models as well.

CFG scale should be between 4-7.

LyCORIS weights should be between 1-1.4

Notice: This free work is intended for art and illustration purposes of emergent technology and not intended nor' trained for making illicit images, as the author I've taken care to not use any private data in the training process or designed it for such purposes. By downloading this model you are agreeing with the aforementioned intent and that you will not use my work to create / share images of a potentially immoral and / or illegal nature.

If you'd like to support me and do more:
https://ko-fi.com/edgonkofi - commissions open!
If you're looking for a >>LoRA Making Tutorial<<

Lycoris Couture

This model explores what we can do with Lycoris and fashion design.

Lilith Diablo 4 Cosplay Lycoris (Unstable)

Early iteration of diablo 4 lilith, depending on your model / prompt might hit or miss a lot. Note: limited pose variation from her dataset, you may need to use control net

Tested with my model: Tauron Hybrid Mix - TauHybrid_Real_v2.1 | Stable Diffusion Checkpoint | Civitai

Trigger words : lilith_d4, horns, breasts, pale skin, dress / long dress, armor, cleavage, fingernails, glowing, demon horns, demon girl, rose petals, red theme, alien, monsters, wings / demon wings / dragon wings / bat wings

Note: (choose 1 only for prompt1 / prompt2)

Recommended Weight : 0.6-0.8

For best result use Dynamic CFG Threshold:

• Mimic = 10 | Clamp Percentile 99.5

• Min. Mimic Scale = 0, Cosine Up

• CFG Scale Sch. = 15, Half Cosine Down

If subject face is small / far away use: DDetailer Script with bbox anime face with default settings except denoiser at 0.2-0.3. You can combine this LoRa with a lot of other Style / Attire / Pose / Acts LoRa, Also works well with character LyCoris.

Please leave a review if you have any critiques or if you find this LoRa good.

Reminder that the request form is closed.

Your characters may have insufficient training data! Click here.

Weight: 1.0

Parish: sarventedef, colored skin, habit, dress, long sleeves, puffy sleeves, thighhighs, garter straps, white gloves, cross

Gospel: sarventegos, demon girl, colored skin, leotard, clothing cutout, heart cutout, thighhighs, elbow gloves, demon wings, spider web

May generate pink hair sometimes. Hearts may also generate due to the heart cutout tag. You can give her a microphone by prompting holding microphone.

The results of your generations are dependent on the additional LoRAs, weights, and models you use, so it may not work or come out as consistent as my sample images. Other reasons may include me using xformers, token merging, and a modified DPM++ 2M Karras sampler.

mamimi.........

use at like 0.8 or sumthin, add serafuku + plaid skirt to get her standard outfit

:3

Miu Furinji v3.0 Premium - LyCoris

Entrenada con 50 imágenes del anime y ovas en 1080p ,recortadas ,editas a mano una por una,10 horas de trabajo, redimensionadas 768x768 , espero que les guste esta ultima versión.

entrenado 768x768

Testeo Rapido 512x768 con icomix_V04

Prompt

<lyco:Miu-Furinji-V3:0.7>, 1girl, blonde hair, blue eyes, style anime

Altamente recomendado para con ControlNet Openpose

¿Te gusta mi trabajo? ¡Ayuda a mi gato!

¡Una bolsita galletas seria genial! 😻😻😻😻😻😻