LyCORIS

这个模型在使用前记得下locon插件，要不会没有效果！！！

Remember to use the locon extension before using this model, or it will not be effective!!!

https://gitcode.net/ranting8323/a1111-sd-webui-locon.git

推荐权重0.6-1，高权重下适合出头像

The recommended weight is 0.6-1, and it is suitable for avatars under high weights

所有示例图均由T-anime-v2生成

All example plots were generated by T-anime-v2

真正的翡翠雕像/制品艺术风格，色彩丰富的东方瑰宝，也可以出人物，具体效果可以参考图片

The jadeite carving art style, colorful oriental treasures, can also be out of character, specific effects can refer to the picture

材质模型的正确使用方式是图生图，效果贼拉棒

The correct way to use the material model is image to image, It works really very well

1.0:

这个版本的颜色淡一点

This version color it's not that dark

1.1:

这个版本的颜色会更深

This version color it's going to be a little darker

新人练手，不喜勿喷，谢谢

Rookie practice. Don't abuse if you don't like it. Thank you

This is a model of Alyx Vance from Half Life 2. It is fairly versatile, and should be able to depict her in a variety of styles, poses, and clothing.

Issues:

• Kinda breaks over 768x768 if not using high-res fix.

• Her grey Black Mesa sweater shows up very often even if not specified. I can fix this by finding and training the model on a few nude versions of Alyx, I guess. For now you can somewhat mitigate it by putting "gray / grey shirt" in the negative prompt.

• Tends to generate her with a sweater, jacket or hoodie even if specified otherwise.

• AND sections of prompts can be fairly strong sometimes, you can decrease their weights with (brackets:)

• Occasional lazy eye. No idea how to fix.

• Her hair can be shaped as though she is wearing an invisible headband.

• Her necklace can have two laces or no lace.

• It likes to give her a crop top. Not really a problem tbh, it looks cool. :>

Enjoy! Eli Vance will be coming next. :)

1boy,1girl,standing sex

如果你想让腿伸直，加入spilt，否则可以试试leg grab之类的

If you want to straighten the legs, add split.Otherwise try leg grab or something

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

• LORA weight for txt2img: reccomended 0.5-0.9.

• Keys: circuit, circuit board, computer, wearing wedding_dress_style made of circuit, wearing_computer_dress, wearing_circuit_dress, inside church

This is a Lycoris, to use it you need to install the proper extension on Stable Diffusion. I'll try to make a LoRA in a future version for easier use.

Very complex to use, my advice is to start from the prompt of the posted images on civitai.

I uploaded on civitai last epoch: circuit_weeding_dress, feel free to try them all in my patreon and i'm open to any advice in the comments to improve the model.

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

培训讯息

第一版本v10训练步数1800步(第二版本V20训练3600步)，v10与v20可两个版本同时使用，基于sd1.5模型训练，请根据使用的模型调整权重。 Clip跳过层1。

V30训练步数1800步，基于我的模型PornMaster-AsianV1-pruned来做训练，

V40训练步数3600步，基于我的模型PornMaster-AsianV1-pruned-FP32来做训练，

V30和V40可以一起使用，与我的模型相容性最高，而且可以画出非常逼真的阴部。(此lora如果一次使用两个版本，建议权重在0.5)

训练使用86张高清无码无水印去除背景的NSFW照片,全部皆为裸体照片，手动标记提示词,300张正则化照片。

擅长分开阴部、分开肛门、分开肛门。

培训照片的解析度512x768,768x512.(脸和全身和阴部特写)

如果你想欣賞她的裸照:

正面提示词:a asian woman Anya01 and <lyco:Anya01V30:1> and completely naked

负面提示词: (worst quality:2) and (low quality:2) and (normal quality:2) and (bad anatomy) and (semi-realistic and anime and  illustration and 3d rendering and drawing)

分开阴部如果超过两只手，负面提示请加入(more than two hands:1.2)

请勿再评论发布裸体照片。

这是一个 LyCORIS (LoCon/LoHA) 模型，需要在 Automatic 1111 中额外扩展才能工作。

范例测试使用的模型:

PornMaster-AsianV1-pruned

PornMaster-AsianV1-pruned-FP32

braBeautifulRealistic_brav5(臉較好看，但根本人不太像)

chilloutmix_Ni

realisticVisionV20_20

触发词

触发词:A woman named Anya01,Anya01

额外可用提示词: asian,Detailed skin texture, detailed skin pores, high skin detail,mole,mole_on_breast, nude,completely naked, a woman with a hairy pussy, on all fours, legs apart, simple background, White background, LABIA MINORA,nympha,LABIA MAJORA,everted labia,clitoral hood,urethra,Goosebumps,urethral opening,vaginal opening,

sitting, lying, Moist pussy,small breasts,rough areola,long hair, tattoo

spread pussy,gaping, spread anus,spread ass, puckered anus,indoor, upper body,medium close shot,pussy close-up,face close-up,photo_\(medium\),

photorealistic,Realistic,anal hair, pussy juice,pussy_juice, fingernails,fingers,hands, hairy pussy,excessive pubic hair,mismatched pubic hair, from behind,ass focus,butt lift,m leg,ass in the air, laughing, legs up,from side,

如果你喜欢我的工作并想支持我：https://ko-fi.com/O5O2K9TV1

免责声明：

我不支持公开散布此模型中所有人物生成的任何不雅图像，我不支持出售此模型中人物生成的图像。请不要使用他们在网上发布的不雅内容。

TRAINING INFO

The first version v10 has 1800 training steps (the second version V20 has 3600 training steps), Both v10 and v20 can be used at the same time,based on the sd1.5 model training, please adjust the weight according to the model used. Use Clip skip1.

V30 has 1800 training steps, based on my model PornMaster-AsianV1-pruned for training,

V40 training steps are 3600 steps, based on my model PornMaster-AsianV1-pruned-FP32 for training,

V30 and V40 can be used together, the most compatible with my model, and can draw very realistic pussy. (If this lora uses two versions at a time, the recommended weight is 0.5)

Training using 86 high-definition uncensored NSFW photos without background removal. All are nude photos. Label the prompt words manually. 300 regularized photos.

Good at spread pussy,spread anus,spread ass.

The resolution of the training photos is 512x768, 768x512. (face & full body&pussy close-up)

If you want to enjoy her nude photos:

Positive prompt: a asian woman Anya01 and <lyco:Anya01V30:1> and completely naked

Negative prompts: (worst quality:2) and (low quality:2) and (normal quality:2) and (bad anatomy) and (semi-realistic and anime and illustration and 3d rendering and drawing)

If there are more than two hands separating the genitals, add a negative cue (more than two hands: 1.2)

Don't comment on posting nude photos anymore.

This is a LyCORIS (LoCon/LoHA) model, and requires an additional extension in Automatic 1111 to work.

Models used for example tests:

PornMaster-AsianV1-pruned

PornMaster-AsianV1-pruned-FP32

braBeautifulRealistic_brav5(The face is nicer, but it doesn't look like a person at all)

chilloutmix_Ni

realisticVisionV20_20

TRIGGER WORD

Trigger Words: A woman named Anya01,Anya01

Additional prompt words available: asian,Detailed skin texture, detailed skin pores, high skin detail,mole,mole_on_breast, nude,completely naked, a woman with a hairy pussy, on all fours, legs apart, simple background, White background, LABIA MINORA,nympha,LABIA MAJORA,everted labia,clitoral hood,urethra,Goosebumps,urethral opening,vaginal opening,

sitting, lying, Moist pussy,small breasts,rough areola,long hair, tattoo

spread pussy,gaping, spread anus,spread ass, puckered anus,indoor, upper body,medium close shot,pussy close-up,face close-up,photo_\(medium\),

photorealistic,Realistic,anal hair, pussy juice,pussy_juice, fingernails,fingers,hands, hairy pussy,excessive pubic hair,mismatched pubic hair, from behind,ass focus,butt lift,m leg,ass in the air, laughing, legs up, from side,

If you love my work and want to support me: https://ko-fi.com/O5O2K9TV1

Disclaimer:

I do not support the public distribution of any indecent images generated by all the characters in this model, and I do not support the sale of images generated by the characters in this model. Please do not use the indecent content they post online.

This incorporates:

• boneyardai

• demonmawAI

• gothichorrorAI

• InfernalAI

• ManyEyedHorrorAI

• NightmarishAI

• TentacleHorrorAI

• TrypophobiaAI

• ArachnophobiaAI

• DragonScaleAI

Example pictures were generated using this prompt:

<lyco:HorrorBundleAI:0.9> { 2$$ boneyardai | demonmawAI | gothichorrorAI | 1nf3rnalAI | ManyEyedHorrorAI | NightmarishAI | TentacleHorrorAI | TrypophobiaAI | ArachnophobiaAI | Dr490nSc4leAI } [concept]

^it needs the Dynamic prompt extension. I didn't check the pictures much, didn't cherry pick.

Notes:

1) Don't worry about the individual LoRAs, they will be available. Also each new theme will be first released as a LoRA.
2) Sorry for my occasional whining about low-energy/needing a break/tiredness ... that happens.
This helps little bit *wink

https://www.buymeacoffee.com/konyconiN

https://ko-fi.com/konyconi7992

Trained on vanilla sd1.5

Realistic models recommended.

https://t.me/neuropsyop

Keyword is russorel.

Dataset was small and I will remake this in the future.

I use this to inpaint small details and it does its job.

Trigger word is alpha_1918.

Use my Double headed eagle model to fix the hair ornament with inpaint.

https://t.me/neuropsyop

Default face:

red eyes, long hair, white hair,

Default upper body:

hair ornament, white jacket, epaulettes, uniform,

Default lower body:

white gloves, black skirt, white thighhighs,

First 50 tag frequencies:

1girl: 478

long hair: 478

solo: 477

white hair: 468

uniform: 430

upper body: 400

red eyes: 389

jacket: 385

epaulettes: 383

gloves: 381

white gloves: 379

simple background: 378

military uniform: 372

military: 363

hair ornament: 280

looking at viewer: 263

long sleeves: 233

smile: 223

white jacket: 210

bangs: 184

blush: 175

breasts: 160

open mouth: 140

medal: 111

white background: 96

armband: 88

green background: 85

braid: 83

closed eyes: 82

holding: 79

black background: 69

cross: 61

closed mouth: 60

purple background: 54

medium breasts: 53

belt: 53

hand on hip: 51

hair between eyes: 38

blue background: 38

heart: 27

grey hair: 27

tears: 24

one eye closed: 23

skirt: 23

blue jacket: 21

shirt: 21

hat: 19

teeth: 18

parted lips: 18

英语(English): This model does not come with clothing information, but it has correctly memorized the body data through regularization, so the character proportions are perfect. You can dress her in any clothes. A weight of around 0.6 is recommended.

中文(Chinese): 本模型不带有服装信息，但是通过正则化正确地记忆了身体数据，因此人物比例完美。你可以给她穿上任何衣服。推荐权重0.6左右。

日语(Japanese): このモデルは服の情報を持っていませんが、正則化を通じて体のデータを正しく記憶しているため、キャラクターの比例は完璧です。彼女にはどんな服でも着せることができます。推奨される重みは約0.6です。

韩语(Korean): 이 모델은 의류 정보를 포함하고 있지 않지만, 정규화를 통해 몸 데이터를 올바르게 기억하고 있으므로 캐릭터의 비율은 완벽합니다. 그녀에게 어떤 옷이든 입힐 수 있습니다. 권장 가중치는 약 0.6입니다.

英语(English): This model does not come with clothing information, but it has correctly memorized the body data through regularization, so the character proportions are perfect. You can dress her in any clothes. A weight of around 0.6 is recommended

.中文(Chinese): 本模型不带有服装信息，但是通过正则化正确地记忆了身体数据，因此人物比例完美。你可以给她穿上任何衣服。推荐权重0.6左右。日

语(Japanese): このモデルは服の情報を持っていませんが、正則化を通じて体のデータを正しく記憶しているため、キャラクターの比例は完璧です。彼女にはどんな服でも着せることができます。推奨される重みは約0.6です。

韩语(Korean): 이 모델은 의류 정보를 포함하고 있지 않지만, 정규화를 통해 몸 데이터를 올바르게 기억하고 있으므로 캐릭터의 비율은 완벽합니다. 그녀에게 어떤 옷이든 입힐 수 있습니다. 권장 가중치는 약 0.6입니다.

LoHa of Katsuragi Ace (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 Katsuragi Ace and Mr. C.B. is created with Tiled Diffusion and my LoRAs of them. If you interested in, see my uploads.

NOTICE

• After careful consideration, I decided not to produce LoRA of the characters below.

  • Otonashi Etsuko, Akasaka Misato, Hosoe Junko

• If anyone wants the characters above, I will consider making them.

• Except for the above, I will make the rest of the characters in Umamusume: Pretty Derby, unless there is a special notice.

Recommended options

• LoRA weight 0.7 ~ 0.8

• Trigger words

  • Base

    • katsuragi ace \(umamusume\)

  • Original Art :

    • ear covers, hair ornament, black gloves, red gloves, two-tone gloves, half gloves, high collar, blue shirt, frills, clothing cutout, cleavage cutout, long sleeves, black coat, belt, black shorts, short shorts, kneehighs, black socks, white footwear, sneakers

  • 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, ear ornament, hairclip, winter uniform, puffy long sleeves, sailor collar, purple shirt, white bowtie, horseshoe ornament, purple skirt, pleated skirt, purple thighhighs, 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

• 175 images consist of

  • 4x low quality 78 images

  • 8x medium quality 50 images

  • 16x high quality 47 images

  • => 1 epoch = 1464 images

• replaced character feature tags with katsuragi ace \(umamusume\)

  • 1girl, 1boy, solo, alternate hairstyle, simple background, ponytail, fu hua, cosplay, genderswap, personification, matoi ryuuko, aged down, virtual youtuber, eyepatch, [a-zA-Z\s\-]+hair{0,1}[s], [a-zA-Z\s\-]+eyes, [a-zA-Z\s\-]+ears, horse[a-zA-Z\s\-]+, [a-zA-Z\s\-]+bangs, horns, tassel

  • I think these tags are the essentials of Katsuragi Ace 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.

Forastero - Style

Ísadóra Finnsdottír, better known by her nickname Dóra, is a Nótt Dvergur who works as Sigurð's bodyguard.

Tingyun from Honkai Star Rail

Use foxian-outfit tag to generate her outfit
Adding fox_tail tag helps generating... fox tail :skull:

If you like my works, consider buying me a coffee.

Fire Emblem Three Houses Style V2 is here!

The age relevant tags work a lot better. Younger, Older, Aged up.

This version is much more faithful to the art style of Fire Emblem Three Houses portrait art.

You can replicate the style of character but to replicate the character as they appear in the game, you'll have to mix this FE16 Style LoCon with Fire Emblem LoRAs.

I'm still keeping the weight around 0.7

Have fun!

Please leave a review!

Made using Derrian's SDscripts

--Below is for the v1 LoCON

The New LoCon is much more flexible with a wide variety of checkpoints. Feel free to experiment. The dataset and tagging at the same as the original LoRA. The LoCon remains exceptionally good at generating characters with dark skin.

Oh, I think it's also good for NSFW. I tested it and seems pretty good.

Lastly, you can find some tags from the dataset you can use in your prompts at he bottom.

--Below is for the v2 LoRA

This is a WIP LoRA that replicates the portrait art style of Fire Emblem Three Houses & Fire Emblem Warriors: Three Hopes.

This was trained at 768x768 so it will also best generate images at 768x768 or larger.

I recommend 0.75-0.6 weight for this LoRA. Try different checkpoints, some produce steller results and some produce garbo. Just experiment around, its fun! I use my buddy's Dutch Olympus Model and Dreaming of Olympus which may be released soon if all goes well.

This LoRA can also replicate the different emotions that the character's portraits displayed such as Angry, Blush, Happy, Sad, or Surprised. Just a note. I had better results with Surprised, Open Mouth instead of just Surprised.

This LoRA can replicate the style of the Garrag Mach Monatary outfit as well.

PLEASE leave a review & your comments & opinions because this will not be the final version. I can't even choose between a LoRA or a LoCon.

Also, expect more FE Portrait LoRAs in the future! FE13, FE14, & FE15 are next!

Here are some tags from the dataset you can use:

• simple background

• upper body

• armor

• long hair

• looking at viewer

• closed mouth

• cape

• Young

• garreg mach monastery uniform

• breasts

• uniform

• Older

• green eyes

• Aged Up

• smile

• blonde hair

• open mouth

• Neutral

• Angry

• Happy

• Sad

• Surprised

• Blush

• fur trim

• official alternate costume

Train based on AnyLora model. Training resources include official arts ,leader live2D and some screenshots from the game on NS platform.

Strongly recommend weights from 0.6 to 0.8,and enable hires.fix.

Here's some trigger words you may need to access different costume of the character:

Form 1 (with helmet):alternative1,unevolved,covered eyes,white helmet,white armor,middle blue skirt,(blue sword);

Form 2 (no helmet):alternative2,evolved,hair ornaments,blue eyes,white armor,middle blue skirt,(blue sword);

Form 3 (black,with helmet):alternative3,unevolved,covered eye,black helmet,yellow eye,black armor,middle red skirt,(red sword);

Form 4 (black,no helmet):alternative4,evolved,hair ornaments,yellow eyes,black armor,middle red skirt,(red sword).

Some words like "armor","holding sword(shield)","glowing","star-shaped pupils" might be necessary to enhance the costume,making it more faithful to origin artworks.

Also,you may add"white(black,transparent,simple) background" to negative prompts to avoid those backgrounds caused by L2D trainning materials.

Hope you enjoy this loha:)

抽出新皮玩了几天护符和结晶教，又重新鬼堕了捏，嘻嘻嘿嘿哈哈玩主教哪有不疯的，受不了了，一拳把圣女头盔打爆👊👊👊😭👊👊👊

LoHA trained on Asuka Kazama from Tekken

suggested by @BlackHatake

just noticed that someone else did her today, well thats unlucky

anyways enjoy the new Tekken 8 outfit then :D

Asuka Kazama

models used

anime: MeinaAlter, Anything and Everything

2,5D: CamelliaMIx_2.5D_V2, MeinaUnreal - V3, HELLmix, ReV Animated

realistic: fantasticmix_real

Asuka Default: kazama asuka, 1girl, open jumpsuit , sports bra, shorts, belt, sleeveless, elbow gloves,

Asuka Tekken 8: asuka tekken8, 1girl, sweater vest, shirt, hat, uniform

Asuka Casual Outfits: asuka alternative, 1girl,

negative embeddings: embedding:bad-hands-5, embedding:ng_deepnegative_v1_75t, embedding:bad-artist, embedding:EasyNegative

Recommended settings:

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

• VAE: vae-ft-mse-840000-ema-pruned (for realistic models & 2,5D), kl-f8-anime2, blessed2.vae (for anime models)

• Sampler: DPM++ SDE Karras or DPM++ 2M Karras

• Steps: 20 to 35

• Clipskip: 2

• Upscaler : img2img in comfyui using 4x-UltraMix_Smooth

• CFG Scale : 5 to 9 (mostly 7 and 8)

• LORA weight for txt2img: 0.5-1 (for the examples i mostly used 0.8)

• Denoise strength for img2img: 0.4 to 0.7

If you want the exact same settings, just drag and drop the picture into ComfyUI

for the pictures i used comfyui

Trained on vanilla sd1.5

Weight 0.9 seems ok

Realistic checkpoints recommended

Trained on vanilla sd1.5

Realistic checkpoints and Hires fix recommended

Hoshii Miki from IDOLM@STER, trained as a LyCORIS network.

Requires extension for use:

https://github.com/KohakuBlueleaf/a1111-sd-webui-lycoris

Recommended tags are:

dsmiki, blonde hair, long hair, ahoge, green eyes

Check out my HuggingFace repository:

https://huggingface.co/Doctor-Shotgun/ds-LoRA

Check out my Pixiv:

https://www.pixiv.net/en/users/90447503

Trained on AOM3. This is a LoCON/LyCORIS, so please install the appropriate extension to be able to use it.

Consider tipping me through Ko-Fi!

https://ko-fi.com/muscleenjoyer

This LyCORIS has been trained after carefully selecting 44 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.

I made this one a long time ago and never really shared it and a few days ago i decided to retrain it.

Keywords are Carole_Peppers. You can dress her up as you want but if you use shirts they might look a bit like her default outfit. just tone down the strength if you cant seem to change it.

I will work on one more Honkai Impact character before i return to Pokemon.

If you like it share your own generations and leave a like or a review. Or both if im allowed to be greedy.

Have fun generating

Enjoy the new Riju Model from Tears of the Kingdom.

Dataset was very limited (about 25 pictures) but every day new picture are being released so i will retrain it eventually when enough pictures are present.

Activation Token is Riju and if you want to get her default outfit you can use tags like crop top, skirt, bracelets. Her lipstick is kind of weird though and always present maybe you want to put "lipstick" in negatives or just prompt it, it works most of the time.

I haven't tried generating her in different outfits but i think it's possible. You can always change the strength and then it should work.

If you need guidance while prompting you can look at the metadata

If you like the model you can leave a comment with your pictures and i would appreciate if you could leave a rating or feedback.

Have fun generating.