Akira Todou from the anime "Worlds End Harem"

Kaga from Kantai Collection, the stoic and serious boat wife!

大変に気分がいい

If you create any good images using this LoRA, please consider sharing them by leaving a review. Thank you!

2.0 update
This model has been changed to LyCORIS.

For people who do not use LyCORIS, I still provide a 2.0 version of LoRA, which has a different performance.

• Update version 2.0, compared to version 1.0, there are changes in the representation of glossy skin, but it cannot guarantee to be overall better than 1.0.

• Shiny_skin to trigger, use Tan / Dark_skin to deepen the skin tone.

• Some prompts about lighting and skin can be used:

  Oiled_skin / Glistening_skin / High_contrast / Perfect_lighting / etc.

  However, since they are not been tagged in training images, they cannot be guaranteed to be always effective.

• 2.0 removed most of the training images of muscular, so it won't be a trigger word anymore.
  If you need some girl's muscles, you can refer to my other LoRA: Muscle girl

• I used ClearVAE to generate 2.0 sample images.

LoHa of Sakura Laurel (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 uploaded images are generated by AOM3A1

Recommended options

• LoRA weight 0.7 ~ 0.8

• Trigger words

  • Base

    • sakura laurel \(umamusume\)

  • 'Sakura Eye'

    • symbol in eye, symbol-shaped pupils

    • Without these tags, you can reproduce 'Sakura Eye'. But with tags, you can get more clear shape.

  • Racing competition costume :

    • ear bow, symbol in eye, symbol-shaped pupils, sailor collar, pink ascot, white shirt, pink vest, puffy short sleeves, wrist cuffs, white shorts, single thighhigh, black thighhighs, knee boots, asymmetrical footwear, white footwear, mismatched footwear, high heels

  • SSR Stamina(Christmas) :

    • official alternate costume, christmas, hair ornament, ear covers, symbol-shaped pupils, symbol in eye, halterneck, halter dress, fur trim, fur-trimmed dress, red dress, santa dress, bare shoulders, detached sleeves, elbow gloves, fur-trimmed gloves, red gloves, back bow, green bow, black thighhighs

  • 4th event SPECIAL DREAMERS :

    • official alternate costume, ear bow, symbol in eye, symbol-shaped pupils, white jacket, white shirt, pink bowtie, brooch, long sleeves, white shorts, white thighhighs, white footwear, knee boots, high heels, high heel boots

  • Casual :

    • casual, ear bow, symbol in eye, symbol-shaped pupils, collarbone, pink cardigan, necklace, jewelry, white shirt, long sleeves, grey skirt, plaid skirt, black pantyhose, pink footwear, sneakers, shoes, shoulder bag

  • Tracen stage uniform :

    • official alternate costume, ear bow, symbol in eye, symbol-shaped pupils, choker, long sleeves, wristband, cropped jacket, white shirt, white jacket, red vest, midriff, waist cape, overskirt, red shorts, short shorts, garter straps, purple thighhighs, white footwear

  • 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

• 134 images consist of

  • 4x low quality 41 images

  • 8x medium quality 35 images

  • 16x high quality 41 images

  • 16x closed up 17 images for reproducing 'Sakura Eye'

  • => 1 epoch = 1372 images

• replaced character feature tags with sakura laurel \(umamusume\)

  • 1girl, animal ears, multicolored hair, red hair, solo, red eyes, black hair, purple eyes, pink eyes, horse girl, parted bangs, brown hair, two-tone hair, orange hair, simple background, white hair, horse ears, bangs, short shorts, horse tail, short hair, pink hair, medium hair

  • I think these tags are the essentials of Sakura Laurel 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.

And, special thanks to my best friend. DH.

download my sample and import to webui for prompt!!!

download my sample and import to webui for prompt!!!

download my sample and import to webui for prompt!!!

下载图片导入webui获得提示词！！！

下载图片导入webui获得提示词！！！

下载图片导入webui获得提示词！！！

This loha will turns EVERYTHING into a Neon light!!!

这个loha可以把任何东西变成霓虹灯！！！

And you can combine it with others to add shiny effect to object edge.

你也可以通过组合为其他物品增加高亮边缘特效。

前言:

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！

如何使用 How to use:

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：

neonlight\(ttp\)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

neonlight\(ttp\) 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.

neonlight\(ttp\), 1girl, huge text, neon lights,( contours:1), (lines:1.5),(holographic projection:1.2), (transparent:1.5),isometric, ground platform, profile, upper body, glowing <lora:neonlight_V1_loha_upload:0.65>

使用0.3左右的权重作为辅助光效

use 0.3 weight to add light effect!

LoHa of Mejiro Ryan (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 uploaded images are generated by AOM3A1

Recommended options

• LoRA weight 0.7 ~ 0.8

• Trigger words

  • Base

    • mejiro ryan \(umamusume\)

  • Racing competition costume :

    • ear piercing, white gloves, studded bracelet, long sleeves, sleeveless shirt, collared shirt, clothes writing, vertical-striped shirt, tied shirt, striped jacket, white jacket, open jacket, open clothes, cropped jacket, green necktie, crop top, navel, midriff, vertical stripes, brown belt, short shorts, black shorts, thigh strap, high heel boots, white footwear

  • Valentine :

    • hair flower, official alternate costume, long sleeves, collared shirt, white shirt, brown vest, striped bowtie, brown belt, frills, chain, gold trim, brown pants, brown footwear

  • SSR Guts :

    • ear piercing, official alternate costume, bare shoulders, short sleeves, blue crop top, blue shirt, camisole, open clothes, open jacket, blue jacket, see-through, belt, blue shorts, short shorts

  • Casual :

    • casual, ear piercing, necklace, wristband, long sleeves, white shirt, blue dress, open jacket, open clothes, black jacket, capri pants, black pants, blue 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, 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

• 76 images consist of

  • 4x low quality 28 images

  • 8x medium quality 25 images

  • 16x high quality 23 images

  • => 1 epoch = 680 images

• replaced character feature tags with mejiro ryan \(umamusume\)

  • 1girl, streaked hair, bangs, white hair, brown hair, animal ears, horse tail, short hair, black hair, solo, blue eyes, two-tone hair, brown eyes, horse ears, purple eyes, grey eyes, multicolored hair, very short hair, simple background, horse girl

  • I think these tags are the essentials of Mejiro Ryan 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.

And, special thanks to my best friend. DH.

Semi Almualim style.

It's okay, I guess.

• Trained on YesMix 1.6

• I tried on MeinaMix9 and Comic Babes, it works nicely there aswell.

• I liked 0.85-0.9 weights the most. Waifu or Blessed VAE recommended.

• Showcase images made on YesMix 1.6

• Generates artist logo and "patreon", so either put it in negative or inpaint.

AbyssOrangeMix3(AOM3) + Dataset(774cards Fine-Tuning)

喵喵喵~~~

I made this because I thought that mfy-sensei's artwork and AOM3 might be very compatible.

Bortus was a Moclan Second Officer and Lieutenant Commander aboard the USS Orville.

Trained 10 epochs, i don't know which is best, they all suffer a bit

use in negative: gravel road if you don't want a gravel road, showroom/display to not generate an image in a showroom fashion

if it still generates gravel road use ((gravel road))

you can show support on https://ko-fi.com/truefalse

(This is a machine translation by deepl, sorry if there are any mistakes regarding grammar.)

This is lora of asumi sena, a member of the virtual youtuber group "Buisupo!

The strength of lora is recommended to be about 0.8.

Trigger words:asmsn,1girl

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

It was made as a trial, so it may not be a lora with satisfactory accuracy.

Please enjoy it if you like.

https://vspo.jp/guide/

japanese↓
これは、バーチャルyoutuberグループのぶいすぽっ！に所属しているasumi senaのloraです。

loraの強度は0.8くらいがおすすめです。

トリガーワード:asmsn,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。

これは私の一番好きなガルゲームのキャラクターです。狙われた女神天使エンゼルティア静海涼音です。皆様の貴重なご意見をお願いします。

For a better result, add the parts you want to be covered by steam in the Negative Prompt

Negative Prompt: nipples, areolae, pussy, slip areola

!! PLEASE READ !!

If the original artist requests a takedown, I will immediately remove this model off of CivitAI. Thank you. Please support their work here. Meanwhile, please do not monetize your generations.

Install the LoCon extension here. Or use that extension that's displayed in the blue box.

Resource used: https://civitai.com/models/22530

This was requested through Google Forms

Weight: 1.0

Trigger: there's none

I should probably check if this style's been published already, but I used some of my computing units so might as well release it anyway (I'm actually baking another one as of writing this, hope it turns out well). The resolution trained is at 1024. I recommend hires fix.

Characters featured: Izuku Midoriya, Momo Yaoyorozu, Camie Utsushimi

A lora based on the meme of "he wants to order"

Trained with 119 images

tested on 10 models

Image info

• Model used abyssorange2hard

• bad hands embedding

• bad artist embedding

• bad prompt embedding

• deep negative embedding

Notes

• just use a similar prompt from the examples

• keep prompts simple

Known Issues

• generating males is possible (as it was half the dataset) but outcomes will differ form model to model

Training settings?

The most important part of training is getting a good dataset!

Training settings can be found by installing the additional networks extension in auto1111

Extensions -> available -> load from -> additional networks

Restart webui

place lora into stable-diffusion-webui\extensions\sd-webui-additional-networks\models\lora

To view the training settings

Go to additional network tab -> choose model -> training paramters

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<<

Hardwear

What is Hardwear?

Hardwear is a fashion conept that relies of the aggressiveness of leather to make a deep fashion statement.

While this style of leather and military design usually significates submission, hardwear is here to pivot those codes of submission and walk towards freedom instead.

We will use the chains of our oppressors as weapons to whip them, that is hardwear.

Be hard, be free

And f**k "Sexy Attire"

Trained 10 epochs, 7th is very good!
if you want to show your support https://ko-fi.com/truefalse

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<<

Butterfly Lingerie

Beautiful butterflies...

Im writing this for the second time so i wont pour as much love in this introduction.
Aether Foundation Employee from Pokemon activation Token is Aether_foundation, this is a Lycoris model so put it either in the lycoris folder or use it via additional networks or it wont work properly. You can use weights from 1 to 1.3 I think its mildly undertrained but you can fix that bei adjusting the weight.
To get the default outfit you have to tag for it either look at the metadata or use danbooru as reference.

Have fun generating some stuff with it and if you like it feel free to rate the model or post some of your creations in the comments. If you have trouble while using this model you can also ask me I will answer most questions when i have the time.

Note #1: Currently does not play well with Hasaku. I'll probably make a less robust, but compatible, version later that will be technically worst but will allow people to use it with Hasaku..

What does it do you ask? This more SFW Change-A-Character is focused on transforming your waifu from that normal, adorable to girl to that hot goth gal of your dreams. There is no specific outfit it is trained on but more the idea of a goth (with it purposefully going towards black outfits and heavier make-up). Feel free to attach whatever you want in the prompt for a base outfit you'd like and how it becomes more gothic.

How to use it:

(I use Sampling Method DPM++ SDE Karras and Upscaler R-ESRGAN 4x+ Anime6B).

0.7 to 1 depending on model/lora/etc.

Main Triggers

GothicC - Just to fortify the idea of a goth. Doesn't need to be used if you don't want it as impactful.

And then whatever else you want! You can, but don't have to, specify a type of outfit.

Just To Drop Some Prompt Words That Are Fun

gloves, pants, dress, elbow gloves, veil, jewelry, thighhighs, hat, high heels, gothic, necklace, fishnets, skirt, spikes, spiked collar, cross, torn clothes, earrings, collar, shoulder cutout, cross necklace, fingerless gloves, pantyhose, belt, choker, black nails, tattoo, fishnet pantyhose, black lips, makeup, arm tattoo, piercing, miniskirt, detached sleeves, crop top, corset, shorts, garter straps, eyeshadow, nail polish, multicolored hair, see-through - You don't have to use any of these, mostly just here for some common words that were appearing in training.

Extra, Extra!: Should be well trained and usable in most models. Images shown for example.

Picture Descriptions:

1-2: AnythingV3 with just this Lora with two different but simple outfit prompts.

4: AnythingV3 combo'd with my released Viper (Nikke) Lora.

5: AnythingV3 combo'd with my released Momo Yaoyorozu (My Hero) Lora.

6: AnythingV3 combo'd with my released Makoto (Persona 5) Lora.

7: AnythingV3 combo'd with my in progress Good Maid Locon.

8: AnythingV3 combo'd with my in progress Naughty Maid Locon.

8: AnythingV3 combo'd with my in progress Broken and Defeated Locon.

9: AbyssOrange using just this Lora.

10: RevAnimated using just this Lora.

11: MeinaMix using just this Lora.

How was it trained?

It was trained on animefull_final with 41 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?

I think it's fine? LMK.

What's next that isn't this?

More character Loras. (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, 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 likely kissing), Sultry Succubus Transformation, Tied up with vibrators (basically the waifu tied up with vibrators and being overwhelmed with pleasure), Beta Censorship (Automatically censors any images you create to make them BetaSafe), 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), 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, 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 a Delinquent (The delinquent girls in japanese schools specifically), GoodCop/BadCop (Locon with outfits for being a good and for being a bad cop), Maid (both normal and naughty variants), Biker Chick (ride a motorcycle and look like you should), Race Queen (Chiling sexily on a car), forest fairy, Anime Officer, barbarian.

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.

This is a LyCORIS/Locon model aimed at preserving your base prompt and then add the concept of groping, molestation, chikan on top, without affecting style and with small impact on composition. I always try to aim at having my models not overfitting so that they're more flexible to your prompt and allow you to use different base models together with LoRAs and TI embeddings without burning the image, which is why it took me >30 runs to get this one right...

It can be used from multiple angles, with whatever character description, and it can be used in combination with your favorite character LoRA, as well as style LoRAs.

You can use weight 1.0 or above, with your usual CFG.

This model does not require any trigger word, as it was trained without one, but you can use the following tags to increase/modify the effect, besides increasing the weight beyond 1.0: multiple boys, groping, grabbing, grabbing from behind, breast grab, ass grab, molestation, chikan, etc. You can use many more related tags since the model will amplify their effect.

There is a bias that the location is a train interior since it was prevalent in the chikan dataset, but you can prompt other backgrounds as well.

I make these models for fun/challenge and release them for free for everyone. The one thing I ask 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 / requests here or on Civitai discord server.

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

真正的中国红剪纸艺术风格，中国民间手工艺术世界级非物质文化遗产，也可以出人物，具体效果可以参考图片，由于素材有限，效果并不是最佳的，多抽卡即可

The chinese red paper cut art style, chinese folk handicraft art world-class intangible cultural heritage, can also be out of character, specific effects can refer to the picture, due to limited material, the effect is not the best, produce more pictures for selection

新人练手，不喜勿喷，谢谢

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

在下极少训练人物，经验不足，如果您愿意的话欢迎指教
I seldom train characters and lack experience, welcome to advise if you are willing

素材较少，全身效果较差，建议生成半身像和特写

Suggestions for generating busts and close-ups

（说实话，在"1girl"和"1boy"之间进行了犹豫，但是后来发现虽然设置了“1boy”但是“1girl"也可以触发特征）

(To be honest, I hesitated between "1girl" and "1boy".But later found that although "1boy" is set, "1girl" can also trigger the feature)

AcertainThing + dataset(DreamBooth)

I have the impression that the lines are much sharper than Acertainty, but I feel that it is easier to produce a masterpiece-like picture by default.

Also, it is easier to produce a straightforward picture than Acertainty.
Well, it still depends on the prompt since it is based on Acertain.