V2 is LoHa LyCORIS, so you should place it in your models/LyCORIS folder

Now your AI girls can get some good massage! :D

Works best at around 0.5 the main keyword is massage, to try to force hands you can add "male hands". Also there are several poses:

1. (on stomach, massage) - Girl is laying on stomach. I recommend to add (on back) as a negative prompt, cause it can sometimes malfunction.

2. (on back, massage) - Girl is laying on back. Like in previous I would recommend adding tag (on stomach) as negative.

3. (girl on top, massage) - Now the girl is doing the massage, surprisingly pretty consistent.

4. (foot massage, massage) - Girl is getting a foot massage as tags implie. Very hard to get good results, but it is there. This is not feet-oriented lora, so you can get ready for common feet fingers problems. Accommodate it with such tags as: toe, feet, sole, toe, etc, so it can focus on generating feet...

You can also experiment with several interesting tags, such as: ass grab, grabbing another's ass, thigh grab, nipple tweak, breast grab, groping

Also there are lotion and towel tags, if you want the real massage experience.

Can generate boys doing massage to each other, it can happen from time to time even if you don't intent tho. Tag hetero can exclude this situation if it pops up too much. I didn't test this scenario much enough, so it's up to you.

Dataset was scraped from gelbooru, tagged with the main word massage and with one pose tag (on stomach, on back, laying on body, foot massage). Dataset contained ~300 images. There was only about 20 images about foot massage.

LyCORIS of Lauren Southern

LyCORIS of Lindsay Lohan

LyCORIS of Melissa Benoist

LyCORIS of Milla Jovovich

LyCORIS of Nina Dobrev

LyCORIS of Olivia Wilde

LyCORIS of Penélope Cruz

LyCORIS of Radha Mitchell

LyCORIS of Rashida Jones

LyCORIS of Rihanna

LyCORIS of Salma Hayek

Adut Akech Bior is a South Sudanese-Australian model.

This is the LyCORIS version trained on the dataset I also used for the TI version (https://civitai.com/models/36954/adut-akech-model)

Please let me know which you prefer!

This LoCon was trained with https://github.com/bmaltais/kohya_ss on NAI.

If you would like to use the same training settings I used, the config is saved in the LoCon. (Open it using notepad and it'll show most if not all the settings)

The keyword is futanarimix but you can get better gens by using flaccid or futanari. The more NAI your model contains, the better the results. For best results, use clip skip 2 and kotosmix: https://civitai.com/models/5245/kotosmix

This LoCon was trained with https://github.com/bmaltais/kohya_ss on NAI.

If you would like to use the same training settings I used, the config is saved in the LoCon. (Open it using notepad and it'll show most if not all the settings)

The keyword is futanarimix but you can get better gens by using gigantic penis or futanari. The more NAI your model contains, the better the results. For best results, use clip skip 2 and kotosmix: https://civitai.com/models/5245/kotosmix

A request from friend.

Role of Girls' Frontline, and it's costume--"First Light's Whispers"

Weight 0.8~1.0 ,and you can ADJUST prompt to reductive character

TRIGGER:

1.BASE: DSRwhisper;

2.Costume: white towel on head,white bathrobe,

ᶘ ᵒᴥᵒᶅ
ᶘ ᵒᴥᵒᶅ
ᶘ ᵒᴥᵒᶅ

One of the taller T-Dolls produced by I.O.P., using the rifle as a comparison and assuming it is drawn to size, DSR-50's height well exceeds 170cm. This tall and mature looking T-Doll has long brunette hair well pass her knees. Her black and red colouring theme is likely inspired by her Germanic origins.

Licking Urethra!! Licking Peehole!!👍

(v1->v2)

Trigger word changed.

简述 - sketch

欢迎使用武墨模型，这是一个武侠与墨风交融的Lora

==========

Welcome to the Wumo model, which is a Lora that blends martial arts and ink style

注意1 - Attention 1

注意1！a1111中的本地额外网络不支持扩展的LoRA。但是，安装机车分机：https://github.com/KohakuBlueleaf/a1111-sd-webui-locon将添加扩展的LoRA支持（这可能在未来获得本机支持）。

==========

Supporting extended LoRA
The native extra networks in a1111 does not support extended LoRA. However, installing the locon extension: https://github.com/KohakuBlueleaf/a1111-sd-webui-locon will add extended LoRA support (this may get native support in the future).

注意2 - Attention 2

大部分预览图使用了( https://github.com/ototadana/sd-face-editor.git )插件对脸部进行了自动修复( 插件的介绍与使用：https://www.bilibili.com/video/BV1RN411w7LQ/ )

1代武墨推荐权重：0.7-1.3，适用于2.5D与2D模型
特别推荐国风3.3( https://civitai.com/models/10415/3-guofeng3 )

==========

Most preview images use（ https://github.com/ototadana/sd-face-editor.git ）The plugin has automatically repaired the face (introduction and use of the plugin: https://www.bilibili.com/video/BV1RN411w7LQ/ )

1st generation Wumo recommended weight: 0.7-1.3, suitable for 2.5D and 2D models

Special Recommendation: National Wind 3.3（ https://civitai.com/models/10415/3-guofeng3 )

(English): I created a Lora model for various colorful shiny pantyhose. The training images were downloaded from e-commerce websites, so the resolution is not very good. The recommended weights are between 0.4 and 0.7; too high weights will affect the image quality.

(Chinese): 我制作了一个适用于各种颜色亮丝的Lora模型。训练所用的图片是从电商网站上下载的，因此分辨率不佳。推荐权重在0.4~0.7之间，过高的权重会影响出图质量。

(Japanese): さまざまな色の光沢のあるパンスト用のLoraモデルを作成しました。トレーニングに使用された画像は、電子商取引のウェブサイトからダウンロードされたため、解像度があまり良くありません。推奨される重みは0.4〜0.7の間で、高すぎる重みは画像品質に影響します。

(Korean): 다양한 색상의 반짝이는 팬티 스타킹을 위한 Lora 모델을 만들었습니다. 훈련에 사용된 이미지는 전자 상거래 웹사이트에서 다운로드 받았기 때문에 해상도가 좋지 않습니다. 권장 가중치는 0.4에서 0.7 사이이며, 너무 높은 가중치는 이미지 품질에 영향을 줍니다.

Round Glasses Lora

This is my very first lora, was trained with 15 images and 1600 steps. I tried with multiple configs and images, trying to get a small size and a roundness glasses, but at final this one was the best.

Read the notes of each version to see the usage notes.

Note:

V1 is a LoRa

V2 is a LoHa

V2提升性能，减少影响其余部位。

V2Enhances performance and reduces impact on the remaining parts.

///

As shown in the picture, most anime-style models should work. Weight of 0.6-0.8 is recommended.

Adding heart tape can change the shape, and sometimes it can also match the appearance according to the character's clothing.

如图所示，大部分二次元模型应该都可以。权重0.6-0.8。

加上heart tape可以变形，有时候也会根据角色的衣服调整外观。

Astaroth, Sin of Melancholy from the Seven Mortal Sins anime (Sin: Nanatsu no Taizai).

LoCon trained on NAI. The dataset does contain some mild NSFW images, so it might tend towards these if no outfit is specified. Works well with weights from 0.6~1. Higher weights might tend to veer closer to the anime's style.

I tried to isolate the following concepts so that they may be used either together or independently:

• "astaroth" - For the character. Keywords "red eyes, tail, twintails" may help. Use as a negative prompt if attempting to use the other concepts on different characters.

• "astarothdress" - For the main outfit. Keyword "striped thighhighs" may help for the stockings. This is somewhat overfit into the model, so use as negative prompt if attempting to change or remove the outfit.

• "astarothguitar" - For the guitar. Keywords "playing instrument, electric guitar" may help. Kind of a hit or miss for this one, but increasing the strength also seems to help.

Sample image is generated by AnyMiniPasky

• 欢迎加入AI绘画模型博物馆QQ群

• ①群：791222249

• ②群：599962550

This is a model trained on lovecraftian artworks. It's not strictly lovecraftian, it does pretty well with any creepy theme. I think it's pretty neat, but it isn't too versatile, unfortunately.

Enjoy the spooks!

- - - - - - - - - - - - - - - -

Hello. I suffer from CPTSD and am very scared of sharing things that I've made. I'm pushing myself to slowly step out of my comfort zone and upload things that I've created, and among them are Stable Diffusion models. I hope you guys and gals enjoy this and the other models. If you have a request, I'll be glad to take a look. No guarantees though!

It is one of my first models that I trained thanks to this guide:

[Guide] Make your own Loras, easy and free | Stable Diffusion Other | Civitai

There are LoRas and Checkpoints that reference the VHS style, and after this inspiration, I came up with the idea of being able to create a LoCon of a VHS stylized taking references to interviews, television programs, movies and commercials from the late 80s and mid 90s to create an effect not so destroyed or glitched by the quality of the VHS of that time. It was intended for portraits more than for other purposes, for landscapes and others, I am not 100% sure that it works well.

It was trained by approximately 140 portrait-type photos extracted from video fragments and other image sources.

In the training I used this checkpoint with SD 1.5 as a base, so I also recommend that you use this checkpoint in conjunction with the LoCon to obtain the most faithful result to the one I had.

(Surely there will be better combinations, better options, but that I have not tested or documented.)

How to install LoCon:

• How to use models · civitai/civitai Wiki (github.com)

How to use it:

Prompts: 90VHS, vhs still from tv, + whatever-you-want

I also recommend using epiNoiseoffset_v1.

Negative Prompts: rz-neg-foranalogportrait, cartoon, 3d, ((disfigured)), ((bad art)), ((deformed)), ((poorly drawn)), ((extra limbs)), ((close up)), ((b&w)), weird colors, blurry

You can experiment with negative prompts, but for me ‘rz-neg-foranalogportrait’ give very good results.

I recommend these parameters:

• LoCon Strength: 1.0

• Size: 512 x 512 - Truly I have not tried with other resolutions, I think the most stable is this measure.

• Sampling Steps: between 20 and 40 is the most stable.

• Sampling Method: DPM++ SDE Karras works very well for portraits.

Using this LoCon in img2img interesting results are achieved maintaining 512x512, and with these settings:

Same settings as txt2img but with these differences:

• CFG Scale: 26 ~

• Denoising strength: 0,5 - sometimes 0,8
  

I invite you to experiment with checkpoints, mix them with other Loras and share them!

Don’t forget to put the prompts you used, thank you!

It is trained on the same images as the previous LoRa, probably wont update the LoRa

Does basically the same thing only with more detail it works better at 512x1024 compared to the LoRa

I trained as a locon at dim16, alpha 8, conv dim 8, alpha 1, for 1600 steps at 5e-4 unet, 1e-4 te.

All preview images were generated then upscaled using tiled controlnet + after detailer to inpaint the eyes. Since this is my normal workflow, I opted to gen preview images in this way. The images are not cherry picked, and upscaled like this, they are very high quality.

This LyCORIS has been trained after carefully selecting 40 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 Pirsus Epic Realism, 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!

Attention Please

Before I tell you anything about this model, I must tell you to check out Babes - Babes 2.0 | Stable Diffusion Checkpoint | Civitai

It's a great checkpoint and the ver2 was released! Go download it and support its creator, he's nice and worked hard for months to train it!

Navel Cutout

I know that the possibility to have a navel cutout already exists but I think that this model offers more possibilities.

So, I played in Persona again, and make this. Enjoy!

Devil May Cry Lady Cosplay Lycoris (TEST Version)

I'm experimenting with LoCon parameters for attire and concept, depending on your model / prompt might hit or miss a lot.

Works best with FantasticMix model. ( v2.0 is better imo )

fantasticmix_real - v3.0 | Stable Diffusion Checkpoint | Civitai

Trigger workds : lady_dmc, short hair, large breast, cleavage, black hair, white shirt, open shirt, rolled up sleeve, (((heterochromia))), holster, suspender, thigh holster, boots, gloves, plaid skirt

Recommended Weight : 0.8-1.0

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.

灵感来源如下，由于那个版本在二次元模型上基本没法使用，所以我做了这款基于NAI的

The inspiration comes from the following link, since that version cannot be used on anime models, so I made this NAI-based

Shiromuku 白無垢 - v1.03 final | Stable Diffusion LoRA | Civitai --- Shiromuku 白无垢 - v1.03 final | Stable Diffusion LoRA | Civitai

你可以尝试不加"hood"来脱下帽子，或者写在负面里

You can try without the "hood" to take the hat off, or write it in the negative part

颜色有时会错乱，可以加上white来引导

The color is sometimes confused, you can add white to guide

我对这个衣服了解不多，在我看来它就是白色的和服加上帽子，所以我不知道这个lora的表现是否合适

I don't know much about this dress, in my opinion it's just a white kimono with a hat, so I don't know if this lora's performance is appropriate

Why is it called Almighty, because I hope the Lora can be used with pose and clothing.

The current version: more than 300 pictures, a dozen Concept. recommended with realistic. Can be combined with pose lora, using Basil_mix_fixed can reduce limb collapse. Clothing lora need to increase some weight.

I recommend using Basil_mix_fixed, followed by Perfect world. other models are also available, but I still prefer Basil_mix_fixed, because the most restored. Weighting 0.6-0.9.

为什么叫万能，因为我希望该Lora可以搭配各种动作和衣服使用。

目前版本：300多张图，十几个Concept。推荐搭配realistic使用。可以结合动作lora，使用Basil_mix_fixed可以减少肢体崩坏。衣服lora需要加大一些权重。

推荐使用Basil_mix_fixed,其次是Perfect world。其他模型也可以，但是我还是更喜欢Basil_mix_fixed，因为最还原。权重0.6-0.9。

内置的衣服： Included clothing:

1.Advent_Children_costume,midriff, crop top,skirt, swept bangs, bare shoulders, sleeveless, black skirt, gloves, bangs, collarbone, belt,

2.chinese_dress_purple,thighhighs, double bun, hair bun, chinese clothes, dress, china dress, jewelry,

3.chinese_dress_dragon,double bun, dress, jewelry, hair bun, cleavage cutout, chinese clothes, earrings, gloves, bracelet, cleavage,

4.clothes_lift,nipples, breasts, shirt lift, large breasts,

5.sliver dress,

6.golden dress,

7.Honoka_costume,swimsuit, breasts, bikini, torn clothes, shorts, torn thighhighs,navel, front-tie top, belt, short shorts, front-tie bikini top, bikini top only, jacket, cleavage, open clothes, open jacket,

8.Maid,breasts,maid headdress, cleavage,alternate costume, apron, enmaided, ,jewelry, earrings, leotard, wrist cuffs

9.Standard_clothes,crop top,gloves, suspenders, elbow pads, midriff,  fingerless gloves, red footwear, black thighhighs, black skirt, elbow gloves, suspender skirt, boots,  tank top, navel,sports bra, abs, bare shoulders, zettai ryouiki, pleated skirt, toned, miniskirt

10.nsfw,bondage, bound, arms behind back, nude, nipple rings, rope, pubic hair

USE Basil_mix_fixed,Weight 0.6-0.8