在此做出预告，我会将细分动作全部在本概念下更新，每一种姿势对应一个版本，请按需切换下载，下次更新我会将标题修改。

Here is an update notice. I will update all subdivided actions under this lora. Each pose corresponds to a version. Please switch and download as needed. I will modify the title in the next update.

版本之间不存在迭代差异，仅有姿势区别

There are no iteration differences between versions, only pose differences

目前已经更新第二个

The second one has been updated

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）

👑 She-Ra Lycoris👑

🔧Model base: AngrA_Anim.Flex.v01

_________

📝🌟 Trigger: SheRaQuiron character, <lyco:quiron_SheRa_V1Lycoris:1.0>, gold tiara, cartoon, holding sword, red cape, 1980s \(style\), retro artstyle,

_________

📝 Variation: <lyco:quiron_SheRa_V1Lycoris:Y>, Y=0.4 to 1.0

📝 Denoising strength: 0.30 to 0.75

🗒️💡Sample:

(masterpiece, best quality, high resolution), (cartoon), SheRaQuiron character, blond hair, 1girl, solo, long hair, breasts, blue eyes, blonde hair, dress, cleavage, jewelry, medium breasts, full body, weapon, boots, choker, sword, cape, white dress, high heels, cosplay, makeup, knee boots, tiara, lipstick, high heel boots, gold tiara, cartoon, holding sword, red cape, superhero, yellow footwear, <lyco:quiron_SheRa_V1Lycoris:0.8>

🚀 This LORA likes: (best quality:1.1), (masterpiece:1.2), (realistic:1.2), (detailed:1.1),

👇 Negative Prompt: (worst quality:1.2), (low quality:1.2), (normal quality:1.2), lowres,

💡Sample steps: 18 to 35

💡CFG Scale: 5 to 8.5

Hire. fix: ok

👇Restore faces: Yes /No

____________

☕ If you feel like supporting my work, please consider visiting my Beer / BuyMeaCoffe ( https://www.buymeacoffee.com/quiron ) ☕

🌟☕If you like my work please support ( https://www.patreon.com/VisionsofAi )☕🌟

A Lora in the style of Paper Mario.

Please leave a review and/or comment.

Welcome to OF Series Vol. 2! Summon your goddess here!

--

If you love my work, you can buy me a coffee to help me stay awake to create more lora and stuffs : ko-fi.com/tauron or it takes only less than 5 minutes to leave a a like and review, it helps the thread afloat and alive.

Check vol.1 --> Tau's Onlyfans Goddess Vol. 1 [Fin] - 10. Coconut Kitty [Final] | Stable Diffusion LyCORIS | Civitai

Best to use with my mix: Tauron Hybrid Mix - TauHybrid_Anime_Final | Stable Diffusion Checkpoint | Civitai

--

DISCLAIMER:

I'm doing this for fun and not for commercial motive, My main purpose is to compose a fictional character using AI with the beauty of all persons above, please support them if you love their works. i do not support any indecent images generated of all persons in this model, I do not support selling generated images of persons in this model. please refrain to what they have been posting online.

All persons in this models are 21+ and not a minor, please DO NOT post explicit nudity, suggestive content, or pornographic content online using this model. Refer to CivitAi TOS for more details.

===

Request or Suggestion Rule:

1. No request of minor!

2. The requested should have public data (no private)

3. Should have more than 30 good quality images

4. Since all requests or suggestion are free, I will still need to like your request, otherwise its a work not a hobby for me.

5. Be a decent human being and leave a review if your requests is up It takes you only 5 mins while it takes me hours, electricity, and efforts to do your requests.

6. If you don't get what you want, do not review bomb, there could be other creators models or lora that can get better results than mine, use theirs instead, and leave a good review on them too, support any other creators for their hardworks!

NOTE : I will keep updating more actresses in versions update

===

Usage Guide

--

A. Lora Weight

• 0.1 ~ 0.4 -- is to combine multiple faces or features, or if you experience overbaking

• 0.5 ~ 0.7 -- is a balanced weight to get still accurate feature but with more flexiblity

• 0.8 ~ 1.0 -- is to create accurate representation of the features.

B. CFG Scale

• Lower CFG Scale means AI gets more creative and less overbaking problems.

• Higher CFG Scale means results get very accurate with training sets and more prone to overbaking problems.

• Dynamic CFG Threshold, using this method allows you to bump up quality and achieve photorealistic easily, but with lycoris i found out recently that this method actually lower success rate, so only use when you are composing with a Lora / model that works fine with this method.

C. Sampling Steps, High Res Fix & Upscaling

• I like to use sampling steps at 50, with high res step at 20, or 1/2 of sampling steps.

• I find that 2M Karras works better and faster than SDE Karras. with ERSGAN 4x+ method + ERSGAN 4x for Upscaling. This method actually gives quite good result without being too sharp or too plasticky

• Upscaling - GPFGAN @0.25, Codeformer @0.3 & Codeformer Weight @0.15 seems to yield superior results to me.

--

Combining with Attribute LoRa / LyCoris

You may need to do your own testing, but using character at weight -0.2 below attribute lora weight yields superior results, if for some reason one features persists not showing or overbake, you may want to lower the weight of the overbaked feature Lora, and then use emphasis () to boost the specific attribute you want.

DDetailer / ADetailer Script

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.

How to install this script? I kinda forget how because its a bit complicated beacuse you need to install stuff from venv. but a quick google search will land you somewhere in tutorial page.

Enjoy.

A Lora in the style of The Legend of Zelda: Wind Waker.

It didn't turn out all that well but i wanted to post it anyway.

Please leave a review and/or comment.

ギャラリーのように

[pocketbike: (motocompo:1.1) <lyco:motocompo_v10:0.5> :0.7]

prompt editing機能を使うと正しい造形で生成されやすいです

それでも確率は高くないので気長に使ってください

Like Gallery,

[pocketbike: (motocompo:1.1) <lyco:motocompo_v10:0.5> :0.7]

If you use the prompt editing function, it is more likely to be generated with the correct modeling.

Still, the probability is not high, so please use it patiently.

※A experimental LoRa model trained to adjust picture color saturation.

This is a LoHa model that trained by 100+ manipulated picture.

This model can improve the color saturation of the background, depth of field performance, and the naturalness of the joins between outlines in the image.

The use of weights can be referred to the example.

Train based on AnyLora model.Use mostly official arts and the leader live2D.

Recommend weights from 0.6 to 0.8,and enable hires.fix.

Updates:Used some new arts to retrain the model and added a new form into it.

Now there's two forms of this character you may generate with these prompts:

• Silong:silong,white dress,white gloves,white thighhighs,(horns),(wings),(tail)

• Mizuchi:mizuchi,black dress,black gloves,black thighhighs,gold-trimmed,(single horn),(single wing),(tail)

By the way,you may need to add"simple(white,transparent,black) background" to negative prompts to avoid the effect of L2D training materials.

Hope you enjoy this:)

Train based on AnyLora model. Training resources include official arts from Shadowverse,Shingeki no Bahamut and Granblue Fantasy,leader L2d from shadowverse and some fanarts.

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

This character has two types of basic characteristics:

• Alternative1(the usual version):blonde hair,blue eyes

• Alternative2(the dark version):white hair,red eyes

Besides,irrelevant prompts like "hair ornaments(flower)","(very)long hair","armor","flag" are also important.

To generate this character in different costumes, you may need to refer to the following prompts:

• Costume1(default):costume1,thighhighs,long skirt,bare shoulders,gauntlets,boots,chest(breast)plate

• Costume2(純朴なる乙女,Village girl):costume2,village girl,holding basket of flowers,long pink skirt,frills,white topwear,boots,black pantyhose,yellow bowtie,hairband

• Costume3(純白の聖乙女,full dress):costume3,sei otome,white dress,shoulder armor,bare shoulders,detached sleeves,thighhighs,boots,hair flower

• Costume4(Swimsuit):costume4,swimsuit,purple bikini,(side)ponytail,very long hair,see-through,hair flower

• Costume5(聖乙女の戦装束,Saint of War):costume5,battlesuit,armor,pantyhose,long skirt

• Costume6(先導の聖乙女,Virtuous Guardian):costume6,white armor,sei shoujo,shoulder armor,bare shoulders,dual wielding,polearm,sword,gold trimmed,black pantyhose,inner-blue red skirt,boots,red ribbon

• Costume7(清浄潔白振袖,Pearl of Heaven Kimono):costume7,japanese clothes/furisode,patterns

• Costume8(聖乙女の休息,Jeanne d'Slack):costume8,casual clothes,hairband,pink pajamas,red jacket,red pants

• Costume9(Dark Jeanne default):costume9,shoulder armor,boots,(sideboob),(wings)

• Costume10(Dark jeanne Swimsuit):costume10,swimsuit,bikini,flower,straw hat,veil,thigh strap,sandals

This is the first time I made a character Lora with different clothes.It’s a bit rough,and some costumes like costume2,5,6,7 and 8 might be difficult to perfectly match the origin arts due to the lack of training materials.I'll work hard to fix it and release an improved version soon.Hope you don't mind:)

リアからの写真も学習しているので、ある程度は綺麗になると思います

learning to take pictures from the rear, so I'm sure I can clean up some of them.

A simple, cute style, usually cel shaded. Works well all the way up through strength 1.5 (2.0 is still usable, if a bit weird and highly stylized).

0.4-0.7ぐらいの強度で使わないと、画像が滲んでしまうかもしれません

Use a strength of about 0.4-0.7 or the image may blur.

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

I Just started playing the dlc and I thought the character looks cute so I let her skip the line.

I used her japanese name (Naeru) as keyword because I dont know how the AI interacts with ' better safe than sorry

I only found pictures from her in like 3 outfits so it's not very flexibel at strength 1.0 but maybe if you lower it you can cheat some different clothes but dont forget to prompt other things then because it get's less accurate.

Like I said above the Keyword is her japanese name naeru works at strength 1.0 adjust if you have to.

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

Have fun generating

Trained off character and promotional art from Fire Emblem Awakening.

This is the LoHa model of my favorite character, Carmilla Queen.

Works well with weights of 0.6~0.8.

It is trained based on an animated model.

Trained on game graphic images only.

Example prompts: red clothes, red eyes, blond hair, bob cut, blue skin, high leg, fangs.

If you like this Lora, feel free to buy a cup of coffee.

If you have joined our membership, we will accept your request.

You can also follow us on Twitter.

Twitter: @seiheki_kenkyu

As a reminder, please do not use this Lora for commercial or inappropriate use.

トリガーワードではないですがthree-wheelerもプロンプトに加えないと、4輪になってしまう確率が非常に高いです

あなたがこのLohaを利用した画像もギャラリーにアップロードしてみてください

Sentences from here down are machine translated

It's not a trigger word, but if you don't add three-wheeler to the prompt, there is a very high probability that you will end up with four wheels.

You can also upload images of your use of this Loha to the gallery!

其实吧，这个是一个style loha来着的，只不过发现这个loha貌似还原人物还原的挺好就变成character loha了.....（其实还是我想试试看loha的参数选什么比较好误打误撞练出来的一个loha）没有触发词，但是要一些额词来辅助否则出不来老婆这个人物（等我考完试就再搞搞loha训练画风和人物什么的，感觉效果确实是比lora好什么的挺离谱的）

1280步，62张图，batchsize2，repeat4，参数如下，tagger1.4可信度0.3，全标

LoHa of Biko Pegasus (umamusume). Please install extension, a1111-sd-webui-lycoris, on WebUI. LyCORIS, not LoCon

After installing extension, put LoHa file in your stable-diffusion-webui/models/LyCORIS folder and write LyCORIS notation in prompt to applying LoHa. <lyco:your_loha_name:weight>

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

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 around 0.7

• Trigger words

  • Base

    • biko pegasus \(umamusume\)

  • Original Art :

    • star ear ornament, school uniform, long sleeves, orange bowtie, brooch, backpack, bag, wings, double-breasted, buttons, white jacket, purple skirt, pleated skirt, orange thighhighs, boots, white footwear

  • Race :

    • star ear ornament, fingerless gloves, white gloves, puffy short sleeves, purple jacket, hooded jacket, cropped jacket, belt, short shorts, white shorts, sneakers, 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, 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

• 71 images consist of

  • 4x low quality 29 images

  • 8x medium quality 21 images

  • 16x high quality 21 images

  • => 1 epoch = 620 images

• replaced character feature tags with biko pegasus \(umamusume\)

  • 1girl, 1boy, blue eyes, multicolored hair, animal ears, horse tail, short hair, brown eyes, :d, star \(symbol\), white hair, grey eyes, horse ears, grey hair, black hair, pink hair, bangs, brown hair, purple eyes, two-tone hair, solo, simple background, aqua eyes, long hair, horse girl

  • I think these tags are the essentials of Biko Pegasus 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.

english↓

This is lora by azuchi momo, a member of the virtual youtuber group nijisanji.

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

Trigger words:

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

If you want to bring out the ribbon in the hair, putting "hair ribbon", "green ribbon", etc. in the prompt will work.

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安土桃の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,adt

髪のリボンを出したい場合は、「hair ribbon」,「green ribbon」等をプロンプトに入れると効果があります。

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 series of LOHA and LORAs of the character Marin Kitagawa from the anime and manga Sono Bisque Doll. It is trained on several outfits and all of her cosplay appearances in the anime.

Marin's LoHA contains several trained outfits, including her school uniform, her bikini, her off shoulder dress, her blue and green flannel shirt, her hoodie, and her kimono. To prompt Marin in her normal uniform, enter "<lora:MarinKitagawa:strength>Marin Kitagawa, school uniform, plaid skirt, black choker". Other outfit prompts include, "flower halterneck bikini, blue and yellow striped shirt, lace choker, string choker, off-shoulder shirt, high-waist skirt, gray jacket, track pants, gray hoodie, kimono". Each of these models can have the "anime screencap" style from the anime when prompted.

Marin's other cosplay outfit LORAs all have their own specific trigger words. Use each respective LORA and their trigger words to prompt them.

For Kuroe Shizuku, enter "Kuroe Shizuku, rose bonnet, black collar, gothic dress, thighhighs".

For Black Lobelia, enter "Black Lobelia, heterochromia, military hat, military jacket, leotard dress, black gloves, black thighhigh boots, black gem".

For Prisoner Veronica, enter "Prisoner Veronica, white belt collar, white belt bra, white shorts, yellow eyes, sharp teeth"

For Liz Kyun, enter "Liz Kyun, frilled crop top, frilled panties, black socks". "wings, tail" are optional.

All of these models were trained on AnythingElsev4.5 at Clip Skip 2. They're very fun to customize, so have fun with them!

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

Here is Sabrina with her outfit from 4th gen I can't train multiconcept right now so i can only do one at a time I dont know if i will though

Model works fine on 1.0 adjust if you have to and Keyword is Sabrina

Like always if you like it do a backflip and throw some stars at my face :)

Have fun generating

USE EasyNegative TI https://civitai.com/models/7808/easynegative

I trained a LoCon on 200 images of Afrobull and got this. Sorry if the quality is bad, this is one of my first training.

Raphael, Archangel of the Virtue of Temperance from the Seven Heavenly Virtues (Nanatsu no Bitoku).

LoHa trained on NAI (anime). Requires the LyCORIS plugin.

Trigger words:

• raphael - Useful tags: "twintails, wings"

• raphaeloutfit - For main outfit. Add "school uniform, skirt, underboob, midriff, eyewear on head" for best results

Experimental (undertrained) trigger words:

• raphaelspeed - For Speedrunner outfit from mobile game. Add "jacket, black skirt, midriff, bare shoulders, between breasts, thigh boots, eyewear on head" for best results

• raphaelsummer - For Summer Toast outfit from mobile game. Add "german clothes, dress, hairband, apron, fishnet thighhighs" for best results

This is a requested character. Reminder that the request form is closed.

Your characters may have insufficient training data! Click here.

Weight: 1.0

Trigger + Appearance: erza scarlet, hair over one eye

Heaven's Wheel Armor: heavenswheel, armor, pauldrons, shoulder armor, skirt, gauntlets, choker, midriff, cleavage

Casual Outfit: casual, sleeveless shirt, ribbon, pleated skirt

Add red hair and brown eyes if necessary. Despite the Season 5 outfit (the one with the sarashi) having the most images, it doesn't work, so I'll be working on a separate version at some point.

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.

I saw richyrich515 make a FEH Style LoRA and was inspired to make my own.

I only used about 300 images. This LoCON is great at replicating the style of named character in FEH. It's a bit outdated though. It doesn't even have FE16 characters, but that's not an issue and can be rectified easily in future versions.

Keep the weight around 0.8.

This LoCON mixes well with my other FE-Style LoCONs and generated portrait ratio images well.

This LoCON was trained without damage or attack images to keep the output a bit cleaner.

I trained at 600x768. I'll definitely train it larger for v2 in order to preserve more details and have more faithful outputs.

I recommend a prompt like this:

FEH, Fire Emblem, Laevatein (Fire Emblem), Laevatein (Fire Emblem: Heroes), simple background, 1girl, solo, weapon, dark-skinned female, dark skin, black and red armor, long hair, full body, red eyes, twintails, holding, feather trim, holding weapon, pink hair, hair ornament, sword, bangs, bare shoulders, breasts, gradient, multicolored hair, gradient hair, holding sword, looking at viewer, closed mouth, armor, standing, medium breasts, hand on hip, gauntlets, orange hair, thighhighs, sleeveless, cleavage, shiny, shiny hair, feathers

You can replace the italicized words for other named characters in FEH.

LyCORIS of Sarah Silverman

LyCORIS of Panam Palmer

LyCORIS of Neve Campbell

LyCORIS of Natalia "Natsu" Kaczmarczyk

LyCORIS of Milly Alcock

LyCORIS of Mila Kunis

This was trained on a dataset from the movie only. Denise Richards breakout movie role!

DM at https://twitter.com/fitCorderAI

Feedback, Requests and Questions - FC Discord invite

My new checkpoint is RadianceApex. It is fine tuned for aesthetic, dramatic images.

Fitness checkpoint is FitCorderMix. Realistic checkpoint is fCBlendMix. Anime checkpoint is fCAnimeMix.

Color issues? Download a vae, guide here. Pictures never look sharp? Download a ERSGAN, guide here. Issues getting good portraits? Click here.

LyCORIS of Mary Elizabeth Winstead

LyCORIS of John Cena

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.

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.

This is Lora, a character from NEEDLESS, kurumi.

She is my favorite character.

It is trained only on animated TV images.

She is learned based on an animated model.

I recommend using a weight of 0.4~0.8.

If you want to change the outfit, 0.6 or less is better.

Hair prompts: yellow hair ribbons, twin braids, twin low braids, brown hair

Costume prompts: blue uniform, red skirt, black thigh highs

However, not all situations will produce the best results.

If you do not want to output the ribbon on the chest, add it to the negative prompt.

If you like this Lora, feel free to buy a cup of coffee.

If you have joined our membership, we will accept your request.

You can also follow us on Twitter.

Twitter: @seiheki_kenkyu

As a reminder, please do not use this Lora for commercial or inappropriate use.

Translated with www.DeepL.com/Translator (free version)