So... They have done numerous porn out there, what's left to enjoy?

Well, some reasons maybe that they are retired, or getting old.. or you like younger version of them, or, maybe you just want to put them into a cosplay, a specific play that they never done in porn maybe? or you want to mix them with your other waifus and create some beautiful angel. Now thanks to SD, the possibilities is limited only your imagination and prompt, or maybe bad hands... or some mutated limbs, let us pray to the god of Ai that we are protected against such evil.

===

Open to suggestion or request

NOTE : I will keep updating more actresses in versions update

===
As usual, all models used in this lycoris are all 21+, I'm doing this for fun only, and please do not use for commercial purpose.

===

Usage Guide

Lora Weight = 0.1-0.4 (is best for combining, be mindful that your model may contain bias towards specific face such as korean or asian), 0.5-0.7 (is good to retain original face, while not too constraining your prompt), 0.8-1 ( is to generate accurate features of the original person ).

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.

Due to key masking, I had to delete part of the element data of the preview image.

Completely rebuilt, 300 training sets. I will release the EarlyAccess version on the TG channel https://t.me/stabledchat

Chelsea Agatha's Lycoris.

She is Indonesian actress. Use at your own discretion and i do not support sharing indecent generation of her. I'm moving onto Lycoris, as my test shows very little to no difference to her model generated in Lora (144MB), and is only takes ~10% memory space of LoRa in general. and i need disk space as i'm starting to fill up my C: with SD images, training and experimentations.

IS NOT A MINOR (21+)

DO NOT USE THIS FOR COMMERCIAL PURPOSE

Works best with henmix model.

henmix_real - v2.3_pruned | Stable Diffusion Checkpoint | Civitai

Trigger word is = chelsea_agatha (if needed)

Lora Weight = 0.1-0.9 ( 0.4 / 0.6 / 0.8 is best )

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.

Trained on many milady and remilio oc collections. Main tags: remilio, milady, and additionally pixel art for pixelady colletions.

Most traits should work, you can check those at opensea or something.

Trained on anything v5. Works best with 2D base models.

故 杉山新一氏の画風LoHA

人物や生物は学習させていないのでそれらの生成は推奨しません。

weight: 0.6-0.9

If you'd like to support me and do more:
https://ko-fi.com/edgonkofi - commissions open! I can make a model for you!

Royal Gowns

We do like to dress to impress, don't we? What's more, we are lacking in beautifully detailed clothing.

Fear not friends. I've got your back.

More beautiful clothing is incoming, beautiful royal gowns to please your eyes and dress your women with style!

Special shout out to @Zovya, I am very impressed with the results of the clothing on her model as I am showcasing it here.

I highly recommend you download either her model A-Zovya RPG Artist Tools - V2

or my Amixx - v1.0-pruned-fp16

when prompting with these models.

Have fun!

Download this LoCon and get some gowns!

english↓

This is lora by siina yuika, a member of the virtual youtuber group nijisanji.

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

Trigger words:snayi,1girl

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siina yuika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:snayi,1girl

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。

Quiet MGS5 Lycoris (TEST Version)

I'm experimenting with LoCon parameters for attire and concept, depending on your model / prompt might hit or miss a lot. There are some NSFW caption mixed in, sometimes her jacket does not show properly. you may need to get few tries until good results. Use lower weight if you want to combine with person lora

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

fantasticmix_real - v3.0 | Stable Diffusion Checkpoint | Civitai

Trigger words : qmgs, quiet (metal gear solid), torn pantyhose, torn clothes, front-tie bikini, holster, thigh holster, boots, black gloves

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.

V2

Significantly improve the effect, I am personally very satisfied, the applicability is much stronger

Reduce the problem of overfitting, use in combination with other characters lora, weighting 0.6-0.9

Optimize the 2.5D/3D model, recommend using Rev animated

大幅度提升效果，我个人十分满意，适用性更强了

降低过拟合的问题，结合其他的角色lora使用，权重0.6-0.9

优化真人版模型，推荐使用Rev animated

////

This is a Lora made at the request of a friend. I hope they will be satisfied with it.

Usage: Most anime-style models can be used, while 3D models may need some adjustments. Recommended weight is between 0.6 and 0.9.

Garter straps can be replaced with pantyhose.

If combining with other character Lorais, weight may need to be adjusted to 0.4-0.7.

If necessary, you can add "(head out of frame:2)" to the negative prompt.

这是应朋友要（X）求（P）做的一个lora，希望他能满意。

使用方法：大多数二次元模型都可以，三次元模型勉强能用，可能还需要调整，权重0.6-0.9。

garter straps,可换成pantyhose。

如果要结合其他的角色lora使用，权重可能需要调整到0.4-0.7。

如果需要，可以在negative prompt加上(head out of frame:2)。

Katsuragi Ace (umamusume) Lora (LYCORIS - locon) ver.1

※Please do not post NSFW content in places where it can be seen by many people, such as on social media.

I promise! 😁👍

※NSFWはSNSなど、多くの人目につく場所に公開しないようお願いします。

約束だよ😁👍

I'd be happy if you could follow and support me to increase my motivation.

モチベーション向上のためにフォローや支援してくれると嬉しいぞ。

👇😎👇

https://twitter.com/oLAcle1220

https://fanbox.cc/@olacle

Trigger words

• base

  • Trigger word

    • katsuragi_ace

  • custom prompt

    • horse girl, horse ears, horse tail, black hair, blue eyes, hair ornament, ponytail, short hair, multicolored hair, streaked hair, two-tone hair

• race clothes

  • Trigger word

    • katsuragi_race_clothes

  • custom prompt

    • black jacket,black coat,black gloves,black shorts,black socks,black pants,short shorts,coat,white footwear,kneehighs,shirt,blue shirt,open coat,open jacket,open clothes,belt,socks,red gloves,sneakers,gloves,jacket,long sleeves

Recommended settings（おすすめ設定）

・race clothes（勝負服）

weight 0.75~

If no trigger words are specified, the basic racing wear will be used.

If you want to emphasize your upper body, it may be better not to use words related to socks and shoes.

The text on the back of the jacket and the dragon embroidery on the back of the jacket may not appear properly... (depending on the model, it may appear?)

トリガーワードなくても指定しない場合は基本勝負服が出ます。

上半身を強調したい場合は靴下、靴系のワードは使用しないようにするといいかも

ジャケットの背中の文字、ジャケット裏の龍の刺繡はうまく出ません...（モデルによっては出るかも？）

・other clothes（その他の服）

weight 0.5~0.75

Please adjust the weight down if you want to make the model wear other clothes.

その他の服を着させたい場合はweight を下げて調整してください。

Works well at 1, might need to reduce weight a bit if you want to remove the headbands. While Plana doesn't have an actual swimsuit outfit, I wanted to give her a swimsuit that was opposite to Arona's in color. The model was also trained with the assumption that genning both of them is wanted, and it is possible to do, even without regional prompting, though with some bleeding. All preview images were genned at 512x768 then controlnet tile upscaled + adetailer to 1280x1920 as that is my normal workflow. The images are only slightly cherry picked, being the best one of out 4-6 gens for each element, except for the images of them together, which was the best gens out of 14 or so. Personally, I believe that to be a very good ratio of good to bad gens given the complexity of generating two characters with distinct traits such as hair color, hair length, and eye color. I did sort of tag the different halo types that arona can make (heart halo, anger halo, green halo) but there isn't really enough in the dataset to make it worth mentioning past this. It does seem to be able to do heart halo decently enough.

This readme is also embedded in the model itself which you can look at by using the tab for additional networks.

all tags are as follows:

Plana common tags:

Plana, red halo, grey eyes, white hair, long hair, single braid, hair over one eye, flat chest

Plana main:

black hairband, white hair bow, black sailor collar, black serafuku, black choker, black pantyhose, black skirt, black jacket

Plana swim:

black hairband, white hair bow, white bikini

you might also need to add frilled to the bikini, white frilled bikini

Plana negative tags:

black bikini, black jacket (if you are putting them into something else, sometimes shows up with the bikini)

Arona common tags:

Arona, blue halo, blue eyes, blue hair, short hair, single braid, hair over one eye, flat chest

Arona main:

white hair bow, white hairband, blue shirt (or blue serafuku), white sailor collar, white skirt, white choker

Arona swim:

white hair bow, white hairband, black bikini

Arona negative tags:

red halo, black jacket (sometimes shows up with the bikini)

Third Lazy LoRA. his one is focused on just rendering fancy animals.

It is made on the base of extra lazy tagging way, which involves only barebones editing of auto-tagged images. This dataset consists of 500+ images.100% SFW, obviously(im not a furry).

Generally, this is not supposed to be used for anythin complex, because it was not tagged in a way to be, but you still can try and show me your results :3

Generally, it's very strong, and will change all your outputs to being animal portraits, generally i've loosely tagged 5 groups:
feline, canine, avian, aquatic and reptilian
Also some animals are specified, but autotagging was so bad, and i was so laaazy, that i didn't bother fixing further, after all, this is a lazy lora(tm).
And no, this is not a furry model and it will not help you with this. I can't stop you from trying of course, but come on... I just wanted a fancy animal portrait model...

It's editable enough in terms of clothing and stuff, and you can apply other various traits even at full power, it should react.

weight: 0.5-

option: jacket, head-mounted display, thigh strap, sandals, energy sword, dual wielding

Herzha, from "Fandeltales - The Cursed Prince" by Derpixon.

LoCon trained on NAI using mostly screen caps from the video. The source is very NSFW and images might tend to these if no outfit is specified. But it does allow SFW (you know, since most CivitAI users are pure of heart and don't want any of that filthy stuff ;P).

Works well with weights from 0.6~1. Use high weight for animated style and low weight for realism.

Trigger words:

• "herzha" - For the character. Add "pink eyes, slit pupils, black lips, grin, sharp teeth, purple skin, horns" for best results. Using one or more of the following can help for the hair: "purple hair, medium hair, multicolored hair". Some models seem to want to make a dude version instead, so adding "1girl" might help too. (Though I guess its still valid, since she is a shapshifter...)

• "herzhaoutfit" - For the outfit. Add "checkered jacket, fur trim, bare shoulders, navel".

I've started a community on Deviant Art to share images made with my models/LoRAs! Join here if you are interested!

IF YOU ARE NEW TO STABLE DIFFUSION OR YOU HAVE PROBLEMS WITH MY MODELS, GO HERE: Guide

IF YOUR PICTURES HAVE PROBLEMS, CHECK MY FAQ SECTION: FAQs

What's this LoRA

This is a Lycoris trained on AI generated pictures of girls with thick outlines and curvy bodies (made usingmy custom Models). My models are not trained to achieve the exact style of their source, but to change the general vibe of the image. They are also fine-tuned on anime models, so they may not work perfectly with realistic ones.

The images in the examples are created using only this LoRA and different models (mainly my custom):

• https://civitai.com/models/24149

• https://civitai.com/models/26332

• https://civitai.com/models/28322

• https://civitai.com/models/32022

• https://civitai.com/models/33707

You don't need to specify a word to trigger this LoRA.

This LORA is trained on NSFW images!

Guides

Learn how to create pictures like mine with my step-by-step tutorials:

• Beginner's Guide

• Prompting

• My Workflow

• Inpainting

• ControlNet

If you want to create images with a high LoRA weight, I highly suggest you to check the tutorial.

Support

Do you want a custom LoRA or picture? Check out my commission page:

LoRA and Picture Commissions

Do you want to get access to my LoRAs before everyone, and contribute to my next models? Check out my supporter tiers on Deviant Art:

If you want to support my work for free, you can also check out my music/art here:

• Bandcamp

• Instagram

• DeviantArt

This Locon was made in collaboration with MerryTail [Twitter] [Pixiv], a talented artist who almost exclusively makes juicy ass.

Use at weight 1 for shiny, juicy closeups of anime girl ass at various resolutions (tags still required). Lower the weight if you want to remove all clothes, get more traditional angles, or get better hands & feet.

This Locon was made with my training guide. If you like my work visit me on kofi. Thank you!

Trained in 8 images of Rimuru bunny figure 10 epochs using "anything-v4.0-pruned-fp32.safetensors" as base model

weight: 0.6-

exs-slave alpha (Marina/真理奈)

exs-slave beta (Riesz/リース)

exs-slave gamma (Azarin/アザリン)

exs-slave delta (yuri/百合)

exs-slave outfit (コスチューム)

4キャラと衣装に対応したLoHAです。

バイザーを学習させているので着脱可能です。

バイザーが中途半端に出ることもあるので付けない時はネガティブプロンプトに設定することをおすすめします。

クッキー☆のキャラクターLoRAに合わせて使用するためのLoRAです
LyCORIS model for use with Cookie☆ Character LoRA models

モデル特有の絵柄を崩さずにキャラクターを再現してPromptの反応性が上がります

Increases Prompt's responsiveness by reproducing the character without destroying the model's style.

使用するためにLoConを導入してください/system requirements LoCon

https://github.com/KohakuBlueleaf/a1111-sd-webui-locon
https://github.com/KohakuBlueleaf/LyCORIS

ACertaintyベースで学習しています。

This is trained on ACertainty.

学習にDanbooruの画像とタグを利用しています。

Using Danbooru's images and tags for learning.

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!

LoHa of Inari One (umamusume). Please install extension on WebUI.

After installing extension, put LoHa file in your sd/models/lora folder and write LoRA notation in prompt to applying LoHa. <lora:your_loha_name:weight>

All of my works is free. If you'd like to support me, feel free to buy me a coffee. 👍

Image of Heisei Top Three and Tamamo Cross is created with Tiled Diffusion and my LoRAs of them. If you interested in, see my uploads.

Recommended options

• LoRA weight around 0.7

• Caution : She often try to do 'Kitsune sign'. If you want to avoid this

  • give instruction like 'hands on hip' in Positive Prompts or

  • write 'fox shadow puppet' in Negative Prompts

• Trigger words

  • Base

    • inari one \(umamusume\)

  • Original Art :

    • fox mask, mask on head, hair bow, yellow bow, school uniform, collared shirt, white shirt, purple necktie, short sleeves, necklace, bead bracelet, clothes around waist, purple skirt, pleated skirt, socks, red footwear

  • Racing competition costume :

    • fox mask, mask on head, hair bow, yellow bow, choker, jewelry, japanese clothes, purple kimono, short kimono, tasuki, wrist scrunchie, short sleeves, wide sleeves, chest sarashi, ribbon trim, obi, sash, o-ring, shimenawa, kouhaku nawa, rope, kimono skirt, blue skirt, shorts under skirt, bike shorts, white shorts, black socks, zouri, ribbon-trimmed legwear, sandals, brown footwear, mismatched footwear, mismatched legwear

  • Casual :

    • casual, mask on head, fox mask, hair bow, yellow bow, drawstring, purple hoodie, long sleeves, belt, purple bow, black shorts, sneakers, white footwear

  • Festival :

    • official alternate costume, two side up, ear covers, hair ornament, choker, japanese clothes, bare shoulders, detached sleeves, wide sleeves, ribbon-trimmed sleeves, long sleeves, white kimono, sleeveless kimono, taut clothes, sash, obi, skirt, black pantyhose, toeless legwear, sandals

  • Tracen summer uniform :

    • tracen school uniform, summer uniform, serafuku, puffy short sleeves, purple bowtie, horseshoe ornament, sailor collar, sailor shirt, purple shirt, white skirt, pleated skirt, frilled skirt, miniskirt, zettai ryouiki, white thighhighs, brown footwear, loafers

  • Tracen winter uniform :

    • tracen school uniform, winter uniform, puffy long sleeves, sailor collar, sailor shirt, purple shirt, white bowtie, horseshoe ornament, purple skirt, frills, brown footwear, loafers

Use a model derived from or mixed with animefull model.

• Settings

  • Stable Diffusion WebUI by Automatic1111

  • DPM++ Series(SDE Karras, 2M Karras, etc.)

  • about 20 steps, CFG scale 3.5~6.5

  • I recommend kl-f8-anime2.vae

  • CLIP skip = 1

  • Use Hires.fix to get higher quality image

    • Upscaler

      • Latent, Latent (nearest-exact), Latent (bicubic antialiased) or other Latent series.

    • Denoising strength 0.50~0.65

LoRA training info

• trained on sd-scripts by kohya_ss.

  • LyCORIS by KohakuBlueleaf

  • Thank you all a lot!

• based on Animefull-pruned model

• 141 images consist of

  • 4x low quality 55 images

  • 8x medium quality 46 images

  • 16x high quality 40 images

  • => 1 epoch = 1228 images

• replaced character feature tags with inari one \(umamusume\)

  • 1girl, hair between eyes, fang, animal ears, grey eyes, brown hair, bangs, horse tail, horse ears, medium hair, aqua eyes, solo, blue eyes, horse girl, simple background, brown eyes, black hair, green eyes, twintails, skin fang, long hair, thick eyebrows

  • I think these tags are the essentials of Inari One or

  • unnecessary for training because of duplication.

• resolution : 768x768 with aspect ratio bucketing.

• other training settings is included in training data or metadata of LoRA file.

All uploaded images are generated by AOM3A1

And, special thanks to my best friend. DH.

Claire Redfield RE2 Lycoris (TEST Version)

I'm experimenting with LoCon parameters for attire and concept, depending on your model / prompt might hit or miss a lot. There are some NSFW caption mixed in, sometimes her jacket does not show properly. you may need to get few tries until good results. Use lower weight if you want to combine with person lora

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

fantasticmix_real - v3.0 | Stable Diffusion Checkpoint | Civitai

Trigger words : recr, claire redfield, red jacket or vest, tank top, denim shorts or jeans, holster

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.

This is a model of Iranian singer and former actress Googoosh. She is a cultural icon. It has been mainly trained on photos from the 1970s. It's decently versatile, perhaps a bit overtrained. It does not really require the use of its trigger word, although it can help tweak your results.

Please do not generate anything disrespectful to her with my model, thank you.

Issues:

tendency to merge crossed legs into one

tendency to give Indian facial features, accessories, or clothing (Stable Diffusion models mix up Iranians and Indians quite a bit)

occasionally produces a lazy eye

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!