LyCORIS

LoHa of Tanino Gimlet (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. 👍

Recommended options

• LoRA weight around 0.7

• Trigger words

  • Base

    • tanino gimlet \(umamusume\)

  • Racing competition costume :

    • eyepatch, black choker, half gloves, asymmetrical gloves, mismatched gloves, black glove, white glove, shoulder cutout, bare shoulders, detached sleeves, long sleeves, sleeveless shirt, blue necktie, open clothes, black jacket, collared shirt, yellow shirt, striped vest, belt, chain, white shorts, black skirt, thigh strap, black pantyhose, fishnet pantyhose, knee boots, high heel boots, black footwear

  • Casual (I guess) :

    • eyepatch, black choker, off shoulder, tank top, purple shirt, black jacket, open jacket, short shorts, denim shorts, cutoffs, fishnet pantyhose

  • 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

• 148 images consist of

  • 4x low quality 65 images

  • 8x medium quality 44 images

  • 16x high quality 39 images

  • => 1 epoch = 1236 images

• replaced character feature tags with tanino gimlet \(umamusume\)

  • 1girl, alternate costume, pink hair, medium hair, horse ears, grey eyes, animal ears, blue hair, purple hair, horse girl, streaked hair, short hair, bangs, black hair, yellow eyes, red eyes, multicolored hair, two-tone hair, puffy sleeves, fishnets, green eyes, simple background, official alternate costume, white hair, solo, brown hair, horse tail, black eyes, blue eyes, brown eyes

  • I think these tags are the essentials of Tanino Gimlet 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.

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

This is a loha, please place it in the models\LyCORIS folder, Download LyCORIS extension.

这是一个loha，请将它放在models\LyCORIS文件夹，并且下载LyCORIS扩展。

This loha is trained using Anything V4.5.

这个loha 使用Anything V4.5进行训练。

The presentation diagram was generated using anything v4.5

展示图使用anything v4.5进行生成

A total of two versions were released, v1 v2. 一共发布了两个版本，v1 v2,

v1 ran 4400 steps, v2 ran 5200 steps, the difference is that v1 is stable in all aspects, v2 skin texture aspects more realistic. Each has its own benefits, please feel free to choose.

v1 跑了4400步，v2 跑了5200步，差异是v1各方面稳定，v2皮肤质感方面更加写实。各有好处，请随意选择。

The recommended weight is 0.45 to 0.60

权重请使用0.45~0.60

The following prompt was used ，使用了以下的prompt。

ass feature, ass focus, straddling, girl on top, pov, from behind, pussy, reverse cowgirl position, sex from behind, facing away, ass focus,shiny skin

Gantz Reika Cosplay Lycoris (TEST Version)

I'm experimenting with LoCon parameters for attire and concept, depending on your model / prompt might hit or miss a lot. Recommended to lower weight at 0.55-0.65 for realistic model, for anime you can safely go at higher weight, test shows bad result at higher weight for realistic model (terrible hands, sketchy images, extra limbs), see trigger guide below for more detail.

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

fantasticmix_real - v3.0 | Stable Diffusion Checkpoint | Civitai

Key trigger are : gzrk
There are 3 trigger version of the bodysuit (do not combine version, will results in inaccurate clothing):

1. full bodysuit trigger = bodysuit / black bodysuit / latex bodysuit (choose 1 only) -- recommended weight = 0.55-0.75 (0.75 only if bodysuit not showing correctly)

2. leotard bodysuit trigger = leotard / black leotard / latex leotard, (choose 1 only), can be combined with: underboob, thigh strap, black thighhighs. -- recommended weight = 0.55-0.65

3. sexy bodysuit trigger = revealing clothes, underboob, thigh strap, black thighhighs. --- recommended weight = 0.5 - 0.6

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.

LyCORIS of Katie Cassidy

LyCORIS of Scarlett Johansson

She is well represented in base models and many derivatives so there is less sense in making a model of her, but perhaps there are some models that her likeness has degraded and this might help.

Still, this turned out a bit harder than I imagined, had to do more tries and it still isn't the greatest. I may revisit her but since she has good representation in base models, it may take a while

LyCORIS of Julia Stiles

LyCORIS of Judy Greer

Emma Brightness (Ore dake Haireru Kakushi Dungeon)

All uploaded images are generated by YesMix

options

LoRA weight 0.7~0.8

Sampling steps 30 or Higher

Recommend Hires

Trigger words

• Default

  emma , belt, emma brightness, ore dake haireru ,blonde_hair,fingerless_gloves, gloves, hair_between_eyes, hair_ornament,pleated_skirt, red_skirt, shiny_hair, side_ponytail, skirt, sleeveless,

Garie Tuman is a character of Senki Zesshou Symphogear GX.

Recommended weight : 0.7~1

All uploaded images are generated by anything-v4.5

If the costume does not come out well, the following prompts may help.

blue dress, black dress, puffy sleeves, long sleeves, bloomers, striped bow,mary janes

Enjoy!

【日本語版】

ガリィ・トゥーマーンは戦姫絶唱シンフォギアGXに登場するキャラクターです。

おすすめweight：0.7～1

アップロードした全ての画像はanything-v4.5で作成しました。

もし衣装が上手く出ない場合は以下のプロンプトが手助けになるでしょう。

• blue dress, black dress, puffy sleeves, long sleeves, bloomers, striped bow,mary janes

楽しんで！

This LORA is Chiba Kirino from BAMBOO BLADE.

She is a second-year high school student, and the captain of the kendo club.

Energetic and enthusiastic, she dreams of leading the team to the nationals.

She plays the position of Second-in-Command (fukusho) in the competition.

inital tags:.

"chiba kirino, ponytail, blonde hair"

main costume:

"hair bow, japanese clothes, barefoot, hakama"

other costume:

"school uniform, socks"

In order to use the lycoris model you will need to install this extension https://github.com/KohakuBlueleaf/a1111-sd-webui-lycoris and use it inside your prompt according to readme or with another extension - additional networks.

It can do both, the original style and the one with chromatic aberration, just use the tags accordingly.

You may want or not to remain original eye style, just prompt white eyes inside the positive or negative. If you still getting generations with this eyes even in the negative prompt just define eye color explicitly inside pos prompt like {red|yellow|blue|green} eyes or so.

Jelly style was not the first by MidJourney. It was actually from Yanjun Cheng. His style is famous on this specific jelly, pastel look, rainbow colour skin. https://yjc.artstation.com

No one, ever, had done any artwork like Yanjun Cheng style. His artworks are absolutely unique.

Weight between 0.6 to 0.8 seems good.

His artwork in low res 400x400 attached, 50 repeats.

Kohya_ss config: 2 batch, 2 epoch, net dim, alpha, conv dim, alpha 16,16, 8,1.

This is a LoCon model that trained by 12 img,which is mainly used to generate cut paper dolls.

weight 1.0 maybe generates better img,trigger is assembly.

Recommend prompts: 1girl, chibi, flat color, .

Lower weight when match other style

Hope you found it usefulミ(・・)ミ

Asta from Honkai Star Rail

Use default-outfit tag to generate her outfit

Meirzhan Nurgozhin is absolutely one of the greatest artists in 2020 time. His artwork recorded the various views in time of the border countries between Russia and Mongolia.

His work are mainly oil painting, dry and thick brushes on canvas.

Not on details, what Meirzhan captured and expressed are the time, feeling and atmosphere.

His typical artworks -roughly interpreted- "the boy on the fence", "boy riding white lamb", "girl in red shoes" recorded the activities, living styles of people, children regardless of the difficult environment in extreme weather.

This model is merely a touch on the surface of his fantastic art works. It is strongly recommended to visit his site in Artstation. Can purchase the print of his work. https://mirzhan.artstation.com

It is not possible to exactly re-produce his dry brush oil painting style, even with PLMS sampler.

His artwork in low res 400x400 attached, 40 repeats.

Kohya_ss config: 2 batch, 2 epoch, net dim, alpha, conv dim, alpha 16,16, 8,1.

This is a model of silent movie actress Lillian Gish. It was made as an experiment in training a model on a limited dataset of mainly low quality black and white photos. It is not as good as I would like with the following issues:

tendency to generate red, blue, both, or purple highlights in hair (fixable for further revisions)

tendency to generate red, blue, or purple hair if hair colour unspecified (fixable for further revisions)

tendency to generate desaturated photos if the negative tag "monochrome" is not used (not fixable for further revisions, is due to the grayscale nature of the dataset)

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

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!

HuoChong is one of great artists on Artstation. His style is mixed between comic, anime and illustration with his unique flat, dreamy, fantasy, magic expression in ancient China flavour.

This model is merely a touch on surface of his fantastic art work. It is strongly recommended to visit his site in Artstation. Can purchase the print of his work. https://huachong.artstation.com

Weight between 0.6-0.8 seems having good imgs.

His artwork in low res 400x400 attached, 40 repeats.

Kohya_ss config: 2 batch, 2 epoch, net dim, alpha, conv dim, alpha 16,16, 8,1.

Constructive previews, comments r welcome.

LoHa of Kawakami Princess (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. 👍

Recommended options

• LoRA weight around 0.7

• Trigger words

  • Base

    • kawakami princess \(umamusume\)

  • Racing competition costume :

    • ear ornament, pink dress, bare shoulders, cleavage, sleeveless dress, detached sleeves, pink sleeves, white thighhighs, pink footwear, boots

  • SSR Speed (Wedding) :

    • official alternate costume, hair ornament, hair flower, tiara, bridal veil, frilled choker, blue choker, pearl necklace, jewelry, collarbone, wedding dress, strapless dress, aqua dress, bare shoulders, cleavage, elbow gloves, wrist cuffs, white gloves, bridal garter, aqua footwear, high heels

  • Casual :

    • casual, ear ornament, red dress, plaid dress, white jacket, open clothes, puffy short sleeves, cropped jacket, black bow, belt, black socks, red 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

• 206 images consist of

  • 4x low quality 105 images

  • 8x medium quality 66 images

  • 16x high quality 35 images

  • => 1 epoch = 1508 images

• replaced character feature tags with kawakami princess \(umamusume\)

  • 1girl, very long hair, braid, horse ears, aqua eyes, simple background, brown hair, asymmetrical bangs, hair intakes, bangs, green eyes, orange hair, official alternate costume, french braid, pink hair, parted bangs, long hair, half updo, red hair, ahoge, grey eyes, crown braid, sidelocks, blue eyes, horse tail, animal ears, horse girl, solo, forehead, ponytail, twintails, alternate costume, alternate hairstyle

  • I think these tags are the essentials of Kawakami Princess 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.

You should try the Velma outfit!

[ lindacardellini, 1girl, solo, breasts, glasses, brown hair, cleavage, short hair, brown eyes, orange shirt, upper body, blurry background, lips, blurry, black-framed eyewear, parted lips, realistic, nose, medium breasts, sweater, large breasts, bangs ]

This particular model was a request, however, anyone is welcome to use it.

LoCon trained on the art of hata4564, i tested on 7thAnimeV3C but it should work well on any model thats doesnt lean too much into realism.

V2: So. I may have previously uploaded one of my older versions of this model when submitting it here, so I've now uploaded my more recent version. This should allow people to get much, much closer to the images that I had posted as opposed to previously >.>. My bad!

Note #1: As this is a Lycoris/Locon file, you will need https://github.com/KohakuBlueleaf/a1111-sd-webui-lycoris extension to use the <Lyco> tag. If you want to use the prompts like I do, specifically being able to use <Lora> instead of <Lyco> (only effects ease of use), you will need this as well https://github.com/KohakuBlueleaf/a1111-sd-webui-locon. Either of these work, you will just need to choose between using <Lyco> and <Lora> prompts.

What does it do you ask? Daring to traverse the DND underdark, your waifu confidently believes that she is capable to defeat any evil being that she encounters. Unfortunately for her, and fortunately for you if you decided to download this Locon, a Mindflayer finds her and decides to make her a toy to be used. Overall, this one turned out fun for me, though it's not the most consistant of my Locon's due to tentacles and monsters not being 100% accurate. This can go even more NSFW then I posted but the pictures would get rejected from Civit. So you do you.

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 combination. This one will take multiple pictures to get perfect, as tentacles and monsters are not always consistently made in SD.

Main Triggers

MindFlayerA - Trigger word to focus the concept.

A Set of Potential Prompt Words

monster, 1boy, 1girl, hetero, purple skin, tentacles, penis, restrained, sex, cum, colored skin, arm grab, monster, torn clothes, tentacle sex, glowing, uncensored, glowing eyes, breasts out, colored sclera, stomach bulge, large insertion, tongue, inflation, size difference, tears, ahegao, fucked silly, open mouth, pregnant, spread legs, breast grab, kiss, oral - I would use my prompts on my images as examples of how these can be used.

Then add whatever else you want!

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

Picture Descriptions:

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

2: AnythingV3 combo'd with my released Makoto (P5) Lora.

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

4-7: AnythingV3 with just this Lora.

8: AbyssOrange using just this Lora.

9: RevAnimated using just this Lora.

How was it trained?

It was trained on animefull_final with 27 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, 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.

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

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

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

你可以尝试不加"hood"来脱下帽子，或者写在负面里

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

颜色有时会错乱，可以加上white来引导

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

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

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