Short-ish, anime proportions with a fairly unique face style.

weight: 0.8-

トリガーワード不要。

convertibleとか入れると生首みたいになるのが改善されます。

👑 Blowjob Top of Head POV LyCORIS👑

🔧Model base: sd1.5

_____________

📝🌟 Trigger: BlowjobTopofHeadPOVQuiron pose, <lyco:quiron_BlowjobTopofHeadPOV_V1_lycoris:1.0>

_____________

📝 Variation: <lyco:BlowjobTopofHeadPOV_V1_lycoris:Y>, Y=0.7 to 1.0

📝 Denoising strength: 0.30 to 0.8

______________

🗒️💡Sample:

1girl, BlowjobTopofHeadPOVQuiron pose, blond hair, <lyco:quiron_BlowjobTopofHeadPOV_V1_lycoris:0.8>

______________

🚀 This LORA likes: (best quality:1.35), (masterpiece:1.45), (detailed:1.15), (realistic:1.2),

👇 Negative Prompt: (text, watermark, website, signature, logomark:1.5), bad-hands-5, bad_prompt, (worst quality), (low quality), (normal quality), lowres, double head, clone,

💡Sample steps: 20 to 55

💡CFG Scale: 5.0 to 13.5

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 )☕🌟

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

Hello my fellow gacha enthusiasts this time i decided to train Melleau from Granblue Fantasy I already collected a dataset ages ago (like 2-4 months) but it was very small and pretty bad. With my newly acquired skills in picture editing I managed to get a lot more pictures that had overall a better quality (but that process also took very long).

Keyword is Melleau and works well on strength 1.0.

I didn't test it as extensively as some of my other models but that's because it has some weird attributes which are not bad just confusing.

I normally bake my models until they are deep fried after that I jump back a few epochs to select the model with the best quality, after having similar training settings for so long I already know which epochs are the best for that but this model somehow managed to not get fried at all it only has a slight shift in style every 5 epochs or so because of that Im not entirely sure which epoch is the best.

Anyway I will test it some more when have the time and might upload another epoch as an alternate version if I deem it necessary in terms of quality and consistency.

Like always a comment , like or a rating would be appreciated if you feel generous you can do all three.

Sharing your thoughts and generations for this model would be highly appreciated because from that I can see a lot more variety in models and combinations of prompts and maybe style lora and that would help me figuring out the epoch problem.

Have fun generating.

真正的大理石雕像/制品艺术风格，流行上千年的高级雕塑材质，也可以出人物，具体效果可以参考图片

The real sand sculpture art style, popular for thousands of years of high-grade sculpture material, 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

注意本材质一定要高修放大才可以有纹理的细节

Note that this material must be highly refined to enlarge the details of the texture

1.0:

这个版本的纹理少一点，更亮

This version is a little less textured and a little brighter

1.1:

这个版本的纹理更多，更深

This version is a little more textured and 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 was trained using Nai based on official and promotional art from Ocarina of Time and Majora's Mask.

Trigger word is oot_style.

Should work fine at strength of 1 but may need to adjust depending on the modal you use.

NSFW capable.

誰も乗ったことがない車に乗ってみませんか？

LoHa of Shinko Windy (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

• The remaining characters of Umamusume : Pretty Derby in on below.

  • Byerley Turk, Godolphin Barb, Darley Arabian

  • After releasing LoRA of these characters on above, I don't have any plan to make LoRA of other individual characters.

Recommended options

• LoRA weight around 0.7

• Trigger words

  • Base

    • shinko windy \(umamusume\)

  • Original Art :

    • ear ornament, school uniform, collared shirt, white shirt, black jacket, hoodie, hooded jacket, hood down, open jacket, blue necktie, drawstring, partially unzipped, zipper, backpack, long sleeves, black skirt, pleated skirt, miniskirt, black socks, black footwear, sneakers

    • (optional) hand puppet

  • Race :

    • ear ornament, black choker, spiked choker, fur-trimmed jacket, sleeveless jacket, cropped jacket, open jacket, black shirt, sleeveless shirt, torn clothes, arm strap, fur-trimmed gloves, fingerless gloves, black gloves, midriff, navel, belt, fur-trimmed shorts, black shorts, short shorts, garter straps, thigh strap, black thighhighs, torn thighhighs, fur-trimmed boots, black footwear

  • SSR Guts :

    • official alternate costume, crown, demon horns, brooch, jewelry, black bowtie, chain, fur-trimmed cape, two-sided cape, black cape, red cape, purple shirt, long sleeves, frilled sleeves, black shorts, short shorts, frills, black thighhighs

  • 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

• replaced character feature tags with shinko windy \(umamusume\)

  • 1girl, brown eyes, ahoge, brown hair, horse girl, medium hair, horse tail, long hair, ponytail, simple background, red eyes, white hair, sidelocks, two-tone hair, animal ears, grey eyes, horse ears, hair between eyes, orange hair, purple eyes, short hair, multicolored hair, alternate costume, bangs, streaked hair, solo, pink eyes, messy hair, teeth, sharp teeth

  • I think these tags are the essentials of Shinko Windy 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.

Screwllum from Honkai Star Rail

Use 1other tag as the subject word

LoHa of Jungle Pocket (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

• The remaining characters of Umamusume : Pretty Derby in on below.

  • Shinko Windy, Byerley Turk, Godolphin Barb, Darley Arabian

  • After releasing LoRA of these characters on above, I don't have any plan to make LoRA of other individual characters.

Recommended options

• LoRA weight around 0.7

• Trigger words

  • Base

    • jungle pocket \(umamusume\)

  • Original Art :

    • ear ornament, hairclip, yellow jacket, crop top, cropped jacket, open clothes, open jacket, strapless, tube top, bandeau, long sleeves, midriff, navel, suspenders, animal print, belt, suspender skirt, black skirt, pleated skirt, green socks, black footwear, boots

  • Casual

    • casual, ear ornament, hairclip, necklace, jewelry, orange hoodie, hooded jacket, hood down, open clothes, open jacket, animal print, sleeveless shirt, white shirt, clothes writing, long sleeves, black shorts, black 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

• replaced character feature tags with jungle pocket \(umamusume\)

  • 1girl, brown eyes, white hair, short hair, simple background, orange hair, medium hair, multicolored hair, blonde hair, animal ears, streaked hair, horse ears, hair between eyes, green eyes, official alternate costume, antenna hair, horse girl, yellow eyes, long hair, ahoge, horse tail, bangs, brown hair, solo, braid

  • I think these tags are the essentials of Jungle Pocket 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.

真正的青花瓷艺术风格，华夏国粹，也可以出人物，具体效果可以参考图片

The real blue and white porcelain art style, chinese quintessence, 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:

在3D风格表现更好一些

Perform better in 3D styles

1.1:

在2D和2.5D风格表现更好一些，更容易出大肚子

Perform better in 2D and 2.5D styles, It's easier to draw a big belly

新版本进行了更好的迭代

The new version iterates better

2.0:

这个版本的颜色淡一点

This version color it's not that dark

2.1:

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

やがて君になるのメインキャラクター三名。

小糸侑、七海燈子、佐伯沙弥香を追加学習したデータです。

LoRAの強度は0.8～1.0で使用する事を想定しています。

佐伯沙弥香の髪の編み込みが不安定なので、気力がある時に作り直すかもしれません。

小糸侑

koito yuu, brown eyes, orange hair, ahoge, short twintails, low twintails, 

七海燈子

nanami touko, long hair, black hair, gray eyes, 

佐伯沙弥香

saeki sayaka, long hair, blonde hair, light brown hair, brown hair, braid, half updo, bangs, 

This was actually intended to be my Warrior locon (it was trained on the same data), but it was a bit too colorful and outlandish and lacking in actual armor. It was too good to toss out, though, so I adapted it into this. My favorite SD model to use with this is DarkRevPikas, although it looks good with a lot of stuff.

This model belongs in horny jail. You have been warned.

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

Today I dare to treat the ambiguous field of Idolm@sters. I dont even know where to start with this show I haven't watched an Idol Anime in my life except Zombieland Saga and thats more of a parody. I only know this character from pictures.

Keyword is Natalia works great on 1.0 adjust if you have to.

The artists were not really sure wether to give her green or black hair so I just left this out. Most of her body features are pruned so things like her skin color and eyecolor but i would recommend you add the prompts as well just for consistency. There is one weird bug sometimes cat ears will appear even if not prompted but the dataset doesn't even have a picture with cat ears. Maybe the name Natalia is also used by a character with this features so tough luck I guess.

One more thing that I knowingly did was to add a lot of pictures in different outfits so you should be able get more "fashionable" with this model but at the cost of not being able to generate her default outfit or any skin she might have in the game consistently. I can't train multiconcept right now so that's the only way for me to get a good variety of outfits.

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

Have fun generating.

Please read this description for some advice on using this!

As this model is a LyCORIS, it requires the appropriate extensions to be used.

LyCORIS model intended to replicate the official 2D art style of the Splatoon series of games. It's a bit quirky so it could probably use another pass or two, but I've liked the results I've gotten so far so I thought I could share it now.

Trained on official artwork. Version 1 mostly used artwork from Splatoon 2, so in theory that should be what it looks closest to. It kind of seems to go off in its own directions though...

Seems to work pretty great on a weight of 1.0, and was pretty alright on the small handful of different checkpoints I tested, but you may have to experiment yourself a bit.

Interestingly, this model seems to have some sort of secret double life -- if used without prompting it with specifically Splatoon-related terms (splatoon, inkling, octoling, etc), it will make images of more non-specific anime characters in a similar but not identical colorful painted style. I haven't completely tested this side of it yet, but it's kind of neat.

Some quirks to keep in mind if using this:

• This is intended for getting some semblance of the art style first and foremost, and isn't made with the intent of replicating any specific named characters from the games. There are other LORAs for that already, though there may be some issues in getting them to mix well together. My testing has been a bit varied on this.

• This model struggles somewhat to distinguish between glasses and the mask on Inklings, so if trying to generate Inkling characters I would typically recommend putting "glasses" in the negative prompt to prevent it from looking weird.

  • Annoyingly, this problem is way worse on male Inklings, and putting glasses in the negative prompt doesn't seem to work, at least not as well.

• If prompted with a Splatoon-related term, the model gets an odd obsession with putting suction cups on people's heads, which can be a bit annoying if you're trying to make a picture of anything that isn't an Octoling. Despite being tagged for, putting "suction cups" in the negative doesn't totally fix this by itself -- I found a slight amount of success with some combination of "suction cups, octoling, marina, object on head", but it's definitely a weak point.

• The model also tends to give characters random straps around their shoulders -- this can be quelled somewhat by putting "ink tank" in the negative prompt. You could also try something like "backpack" if that doesn't work out.

• Sometimes the model will give characters extremely short legs for some reason, which looks very doofy.

I do not endorse or condone this model, or any other models I may make, being used to deceive or defraud, or to create any kind of illegal content. Please be responsible and not awful.

GalaxyBad

日本語

こちらはGalaxyBadのloha版です。

lycorisの拡張 を導入する必要があります。

-0.75ぐらいの重みで掛けると良さそうです。

また、こちらのembeddingやmasterpiece, best qualityなどのクオリティタグと併用することを推奨します。

English

This is the loha version of GalaxyBad.

You need to install the lycoris extension.

It would be good to multiply it by a weight of about -0.75.

It is also recommended to use with quality tags such as embedding, masterpiece, best quality, etc.

(Using Deepl Translation)

Gives your characters a warrior look (even if you don't call them a warrior in the prompt).

Note that, like its creator, this model believes in the rule of cool and has no opinion about the real-world practicality of armor on fictional characters. If you want practical, realistic armor, put words like this in the prompt (potentially weighted higher than 1):

• armor

• faulds

• pauldrons

• chestplate

• shield

• etc

...and maybe add "nsfw" to your negative prompt if that's not enough.

Nothing more nothing less..

just your everyday LLaMA generator ¯\_(ツ)_/¯ 🤟 🥃


PS: The second file: Training Data (201.28 MB)
is a zipped version of a smaller LyCO
Dynamic resize with sv_fro: 0.9 from the 768 DIM version

Note #1: Doesn't work amazingly in the non-anime model's I've tested (Perfect World and RevAnimated). Namely because it screws up the veils and makes them super ugly. Can be fixed with in-painting or photoshop, or just mass amount of image creation. Also due to there not being a ton of images around for a data-set, if you want to make major edits drop the weight to like 0.5-0.6.

What does it do you ask? Your waifu was invited to a club by her boss but... Oh no! He hypnotized her and made her into his own little harem girl. Now she just likes dancing, looking sexy, and having some sexy time with any man who walk into the club. And so, she has hit one of her bad end scenarios! Basically does what it says, harem outfit + more submissive looks. I did add some prompt tags that help reinforce that to the prompt recommendation.

How to use it:

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

0.5 to 1 depending on model/lora/etc combination.

Main Trigger

HypHarem- For the main effect.

symbol-shaped pupils, heart-shaped pupils, expressionless, :o, mind control - A starter for the blank look.

straddling, vaginal, sex, spread legs, 1boy, hetero, penis, girl on top - An example of what you can do for her to be giving a man a good time.

Other Useful Tags

Anything Else You Want!

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

Picture Descriptions:

1: AnythingV3 with just this Locon.

2-3: Hasaku with just this Locon.

4: Anythingv3 with just this Locon.

5-6: RevAnimated with just this Locon.

7: Hasaku combo'd with my in progress Tied Till Orgasm Locon.

8: Hasaku combo'd with my in progress Censored Locon.

9: AnythingV3 combo'd with my released Lucoa Lora.

10: AnythingV3 combo'd with my released Ivy Lora.

11: AnythingV3 combo'd with my in progress Yunaka Lora.

How was it trained?

It was trained on animefull_final with 21 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?

Maybe a V2 for more flexibility as I found more images.

What's next that isn't this?

More character Loras. (Kanzaki Kaori and Musujime Awaki from the Railgun Series, Jill Valentine and Ada Wong from Resident Evil, Echidna from Re:Zero, Rupee and Volume 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 (base 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, Ikumi Mito from Food Wars, Alice Nakiri from Food Wars, Lulu from FF10, 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, Train Groping/Sex, Sex Doll, Slutify/Hookerify, Shy Gal-ify (I had no idea this was a thing but I found so many images of it when looking at other stuff), Ruination (from League of Legends), Bowsette Transformation (Makes your waifu kinda look like Bowsette without changing other aspects), Fallen Angel, Evil Sailor Scout, Team Rocket (Make the waifu a Team Rocket Grunt), Pony Bondage (specifically with the capability of being "riden"), X-ray Vision (glasses that give you x-ray vision of a girl), Vore (Waifu mid-way being eaten specifically), Revealing Clothes (just makes normal clothing even more revealing), More Brainwashing (in ideation for this still), Slime Corruption (transforms your waifu into a slime girl), Cowify (Make your waifu into a cow-girl), Bound Yuri (two girls tied up, breast to breast and likely kissing), 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, Broken and 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), Tentacles, Pillory, Latex Corruption, Combat Drone (hard to describe but basically making them a mindless sci-fi combat warrior), JAV Supervillain, Blacked, 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 Schoolgirl and Naught Schoolgirl, Witch, Pirate, Samurai, Tomboy, Delinquent (The delinquent girls in japanese schools specifically), Maid (both normal and naughty variants), forest fairy, barbarian.

I'm also planning to split up my Evil-ify your Waifu into two separte files, Corruption and Pure Evil.

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.

Now your favorite witch girl can masturbate using her broom, or your favorite cook girl using what she can find inside her refrigerator, or some office girl using her pencil's arsenal...

Recommended weight: 0.8-0.9

Best resolutions: 640x896,896x640

This is LoCoN about girls using various objects for masturbation purposes (not dildos). It is mostly tries to do vaginal interactions, but you can add tags like anal, anal object insertion, currently it can give anal after a few retries (also depends on type of object, some are good with it, some not).

Food objects are tend to be inserted, while pens and pencils rubbed against girls pussy. You can change it of course with the power of tags.

All images were tagged with: masturbating with <item>

Instead of item you can place your object, the following are list of working objects:

masturbating with sword
masturbating with broom
masturbating with staff
masturbating with bottle
masturbating with plastic bottle
masturbating with glass bottle
masturbating with zucchini
masturbating with carrot
masturbating with banana
masturbating with popsicle
masturbating with cucumber
masturbating with leek
masturbating with eggplant
masturbating with daikon
masturbating with corn
masturbating with candy cane
masturbating with mushroom
masturbating with lollipop
masturbating with mechanical pencil
masturbating with pen
masturbating with tube
masturbating with stick
masturbating with wand
masturbating with recorder
masturbating with flute
masturbating with microphone
masturbating with katana saya
masturbating with stick tube
masturbating with wood stick
masturbating with long stick
masturbating with shovel

Next are the objects that come out distorted or that are not stable:

masturbating with filled wine bottle
masturbating with filled glass bottle
masturbating with green glass bottle
masturbating with soda can
masturbating with dango
masturbating with marker
masturbating with stylus
masturbating with pencil
masturbating with remote control
masturbating with candle stick
masturbating with brush
masturbating with long wood stick
masturbating with syringe
masturbating with katana
masturbating with wooden sword
masturbating with toothbrush

Finally, the objects that don't work, but they were in the dataset (although in small quantities):

masturbating with wine bottle
masturbating with filled plastic juice bottle
masturbating with ink pen
masturbating with crystal
masturbating with thermometer
masturbating with explosive
masturbating with unwrapped banana
masturbating with large broom

You can make the girl to either insert it, or to make her rub with it.

Insertion: object insertion, vaginal object insertion

Rubbing: crotch rub, clitoral stimulation

Also don't forger about various pose tags (on back, squatting, tiptoes, standing, sitting, etc.) and general masturbation tags (female masturbation, female orgasm, pussy juice, trembling, etc.).

Riding broom/staff

For proper broom riding masturbation you can use prompt like this (I find it pretty consistent): masturbating with broom, crotch rub, between thighs, (riding broom:1.2)

For staff riding: masturbating with staff, (crotch rub:1.1), riding staff

Swords

Yeah, there are also swords. They are kinda interesting, you can use either default prompting, or you can add planted sword, I would recommend using it with full body like this: full body, (planted sword:1.2), masturbating with sword, vaginal object insertion

Through clothes

If you want to make rubbing there is no need for a girl to be naked or bottomless. You can use tags such as "masturbation through clothes, clothed masturbation", also consider placing clothing tags, such as white/black panties, etc.

If you want to make inserting, I would wish you luck with such tags as "clothes aside, panties aside"

There was around 500 images in the dataset, pretty good for such small amount...

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

I made a twitter account which you can find in the little box where my username and all that datastuff is located. I will upload previews pictures for model im currently working on there or stuff that that I can't post here and information about the new model im working on.

You should read some of the description. This model might be difficult to use.

Let's skip the introduction and just get to the details because this model is difficult to use in my opinion.

First of I would recommend using a style model because most of the data were from the artist who drew the pictures for the light novel so it kind of defaults to that style which has a bit washed out colors but looks alright overall. I used cfg scale 7 for all my gens but maybe adjusting that might help with the colors.

Keyword is Elbia Hanaiman. I pruned her ear and tail and her skin/eye and hair color but i would recommend prompting those as well to get them consistently, or at least her animal features and maybe her skin color if you don't prompt her skin color she will be a bit paler but not "whitewashed" but that might also depend on your checkpoint.

If you want her default outfit use tags like: bandeau, pants (you might have to add the color) armlet, necklace and bare shoulders

I will include some images that i made during testing which are from an older model but the old model was inferior in most aspects.

This model is not perfect and I might retrain it one or two more times with other settings.

Things that might happen include: double animal ears, wrong color of her top (might be because of the pants), weird tail but that might also depend on your checkpoint, missing ears, wrong hair color if you want to gen nudes you might have to add more weight to the tag you are using to disable her clothing.

Thats the one i found so far.

So with everything out of the way let's talk about the character.

Most of you might not know her she is a supporting character from an Anime called "Outbreak Company" but even though she has a minor role she gets her own arc which fleshes out her character pretty well.

She is energetic and very likable a top tier waifu in my opinion.

The Anime also has some banger OST if you are a fan of that genre you should totally listen to that.

Sorry for that wall of text and thank you to the people who actually read and enjoy my ramblings. Now for some copy pasta.

If you like the model consider liking, rating and commenting that would be appreciated.

Have fun generating.

Trained with a lot of screenshots of the move [ The Mask of Zorro 1998 ].

Check the metadata of the images posted as example.

Use the next resolutions to get better results:

• 512x712 [ For Portraits ]

• 712x1024 [ For Full Body ]

Support me on buymeacoffee if you like my work.

I know Merve from an old show called Acemi Cadı.She has changed a lot since than but still has a charm that interest me.

Recommended values : 0.8 weight with hiresfix.Hope you like it :)

Unlimited Blade Works (UBW) | Weapon LoHA

This is a Lycoris and you need this Extension for this to work. IF YOU ARE HAVING PROBLEMS, CHECK YOUR CONSOLE. HERE IS A BUGFIX FOR LYCORIS: Link and Image.

Weight can go from 0.5 up to 1.0. I recommend 0.9. ControlNet will streamline full body shots much easier, or more complex poses. Works with almost every Style, every Character and Photorealistic Models. I also recommend using some ControlNet Depth/HED for easier use. I personally dont use them, but every help is appreciated. Some of @antonio_riolo2610 Models: v1 / v2. Also a big thanks to @Temporarium for helping me out with the Dataset.

Refer to the version details for Changelog. Keep in mind, that despite this LoHA, that Weapons are very difficult to generate. This only helps, but dont solve the issue.

This is now an official release of this Model and includes 23 CONCEPTS. Trained on 6,5k Images with 16,5k Training Steps. Some of these are still unstable, even going over every Image manually. I also included some stances and Weapons that can be combined (Dual Wield of Axe, etc). Try some crazy stuff, even I couldn't fully test this Model after many hours. Here are the Triggerwords and helping prompts:

TRIGGERS:

• Axe²

• BowAiming³

• BowHolding³

• DualWielding²

• Fan²

• KatanaOneHand

• KatanaTwoHands³

• Knife²

• Kunai²³

• Lightsaber²

• Unlimited Blade Works²

• MasterSword³

• PlantedSword

• Scythe

• Sheathed

• Shield²

• Spear²

• Staff

• SwordAndSheath³

• Tomahawk²

• Trident²

• Unsheathing³

• Warhammer²

• Whip

² = can be combined

³ = very unstable

Helping Prompt:

holding, weapon, holding weapon, holding (Triggertag)

Stances Prompt:

Weapon over shoulder, Weapon on back, fighting stance, stance

BETA RELEASES:

This is only a BETA. I will add more Swords, Weapons and Guns to this. SD doesn't like to generate Weapons (just like Ranni with 4 Arms). Trying to improve it on every Update. I recommend using these Settings: Sampling Method DPM++ SDE Karras with 30/40 Steps. If you know how to improve this, i'm happy to hear you out.

WARNING: This LoHA does have some problems and hits most of the time 1 out of 10 times. Hands are a big problem. Hand does not connect with the sword and sword does not appear in the right place sometimes. Unsheathing Sword is currently very unstable. Use pointy ears in Neg, if you are using Link Master Sword. Yor Knife gives normals knifes for some reason on my End.

Trigger Words:

Link Master Sword, Lightsaber, Dual Wielding Swords, One Handed Sword, Unsheathing Sword, Scythe, Sword and Shield, Staff, Trident, Planted Sword on Hand, Yor Knife, Unlimited Blade Works, Bow with Arrow.

I want to add these Concepts in the future as well:

Weapon Classes:

Axe, firearms, arc, Knife, hammer, rods, throwing stars, sickle, whips, guns, grenades, shields

Subcategories:

one-handed, Two handed, pistols, guns, machine guns, shotguns, grenade launcher, rocket launcher, sniper rifles, brass knuckles, throwing axes, spears, javelins, arrows, crossbows, Sling, sniper, bazooka, Foal

Variations:

warhammer, tomahawk, short sword, broadsword, rapiers, longsword, dagger, Kukri, katana, tanto, wakizashi, naginata, quarterstaff, war spear, double axe, hatchet, baton, Shield with integrated weapon, Dual wielding of other weapons

How to use LoHA's in auto1111:

• Download LoHA

• Copy the file to stable-diffusion-webui/models/lora

• Select your LoHA and use the triggerword

• Make sure to change the weight if needed (by default it's :1)

• Have Fun!

This LyCORIS has been trained after carefully selecting 55 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.

The material comes from the Internet.

Any requests can be made in the Telegram group @me. https://t.me/stabledchat

LyCORIS of Katerina Hartlova. Trained at 768x768 with 117 images, a mix of close-ups, waist up and full body shots.

Use katerina_hartlova as the trigger word.

Sample images were generated with realisticVisionV20, with 0.85 strength then inpainted at 1.0 strength.

👑 Milking Table LyCORIS👑

🔧Model base: sd1.5

_____________

📝🌟 Trigger: MilkingTableQuiron pose, 1boy, penis, licking penis, cum, tongue out, lips, saliva, uncensored, erection, oral, fellatio, handjob, cum in mouth, <lyco:quiron_MilkingTable:1.0>

_____________

📝 Variation: <lyco:quiron_MilkingTable:Y>, Y=0.7 to 1.0

📝 Denoising strength: 0.30 to 0.8

______________

🗒️💡Sample:

(best quality:1.35), (masterpiece:1.45), (detailed:1.15), (realistic:1.2), 1girl, MilkingTableQuiron pose, 1boy, penis, licking penis, <lyco:quiron_MilkingTable:1.0>

______________

🚀 This LORA likes:

(best quality:1.35), (masterpiece:1.45), (detailed:1.15), (realistic:1.2),

👇 Negative Prompt: (worst quality:1.2), (low quality:1.1), (normal quality:1.1), lowres,

bad-hands-5, bad_prompt,

💡Sample steps: 20 to 55

💡CFG Scale: 5.0 to 13.5

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 )☕🌟

We introduce a LoHa file that aims to incorporate the Interior Japandi style into a regular bedroom. While the result images may appear oversaturated, we believe this is due to the color scheme of our dataset. To address this issue, we recommend using the Lora name Saturation Tweaker with a negative weight to adjust and tone down the saturation accordingly. Rest assured, we are dedicated to ongoing research and will continue to provide architectural Lora or checkpoints whenever possible. For more information, please contact us at: https://www.facebook.com/aiplusvn

For a change I used a locon as it is supposed to be good at recreating artstyles and it certainly delivered. Although I could probably create a similar LoRA with the same dataset.

This model was trained for AOM3 using the collab/guide by holostrawberry [Guide] Make your own Loras, easy and free - colabs | Stable Diffusion Other | Civitai

While it was optimized for AOM3 it should work with most anime based checkpoints

Check out the artist:

Twitter: Nyantcha (@ThiccWithaQ) / Twitter

Patreon: ThiccWithaQ | Creating illustrated art | Patreon

Expect nsfw content with a tendency towards thick thighs and large breasts.

Use a weight of 1.0. Go a bit lower (I used 0.8) for character loras. As usual I have included an XYZ plot for reference.

Landscapes aren't really an upgrade compared to AOM3. A bit less detail and a bit more focus on lighting. Check out the examples

Please leave a review if you enjoyed this LoRA or have problems with it. I'd also be interested in how the lora behaves with other base checkpoints so why don't you give it a try and throw some images down below!

please do not use commercially and support the work of the original mangaka

Since I can't find any LORA/LyCORIS of ZUN's style, I made my own one.

It's seems good at pencils sketches:

(traditional media, colored pencil \(medium\)), (pencil sketch:1.15)

It's trained on 184 images using this guide: https://civitai.com/models/22530

Why the LyCORIS says v2a, because this is my 2nd version of my 2nd version. The v1 only had art made by ZUN from Th14 onwards, and it weighed 144mb (overkill!). The v2 includes ZUN-styled fanart that include earlier games (at least Th8 onwards), but weighed 144mb too. So this v2a reduces it at 29mb, and I will update it when Th19 gets released and/or enough new ZUN-styled fanart appears.

Feedback would be appreciated, I'm still novice at this.