A Character LoCon for Saria (Saria)

• Recommeneded prompts: Please check my sample works!

• Trigger word:

  • Default: default outfit,black belt, black skirt, long hair, long sleeves, looking to the side, orange eyes, white shirt, grey hair, dragon horns, earrings,high-waist skirt, dragon tail,

  • the law: black footwear, black gloves, black headwear, black pants, black shirt, boots, orange eyes,cowboy shot, dragon horns, gloves, knee boots, long hair, plate carrier, police hat,orange eyes, grey hair, bangs, police uniform, knee pads,the law, official alternate costume

• Recommeneded Weight: 0.6-1 (You can adjust it by your perference.)

• CFG scale: 5.5-7

• Check point recommendation: Anything V5

• Some sample figures were generated with my Vivid Impactful Style - LoRA

• How to use LoCon/LyCORIS? Please read instruction of a1111-sd-webui-locon.

• This version still have some small problems, I will publish a new version soon....

STOP: This is NOT GOING TO BE JUST ONE LYCORIS, this based on alters in our system and other system - and we wanted to share the faces.

LORA EDITIONS OF THE OG KIND:https://civitai.com/models/16763/virtual-worlds-lora-set

"Matoya'iivi Na'agora Solas doesnt work in A111 so we've renamed it, Kitch and Tobias as well were struggling, we're trying to fix this with the new renaming format"

virtualWorldsPeople_matoyaiiviNaagora Type format worked for backwards compatibility for those of you that have this downloaded rather than CIVIT AI extensions.

SOME OF THIS IS STILL EXTREMELY IN WIP mode because with TOBIAS there is clipping issues because I need to EDIT the data in clip studio as they're just RAW unedited Virtual Worlds (SECOND LIFE) shots from last year.

Kitch's one didn't finish training, so the hands are WILD right now.

PLEASE feel free to still USE these regardless of the fact they're not entirely finished, but because you can't always add updated models to a lycoris/lora we WILL be deleting the original files (and keeping them on huggingface for those who need them) and updating them as need be :3.

That way we have space for the reset of the fam.

CURRENTLY WE ONLY HAVE STARTED:
Tobias

Kitch (Christina)

Matoya

Maverick (IS A LORA AT THE MOMENT ON THE OTHER MODEL CARD)

WHY THE GENDER DIVERSITY TAG:

Tobi is considered Nonbinary, and Kitch I beleive is considered to be Transfemme. :3

Now clearly in SL it take a shit ton of work and money to do things super realistic, and we LIKELY wont be going back on any time soon unless we need to.

Any edits to the data are gonna be manual.

IF YOU NEED THE OTHER EPOCHS OF ANY OF THE FAMILY VALUES SET PLEASE GO HERE: https://huggingface.co/Duskfallcrew/Lycoris_Dump_V2

Alex Brightman

"Oh, man, here comes Ann
She's the athlete from 12 G
She's the knees of the bees
Always makin' eyes at me
It would seem such a dream if I asked her for a dance
But I just blew a rail and I'm gonna shid my pants"

Y'all, don't ask, just review and give it a like if you enjoy this wonderful weird ass man.

Works well on illustration models, was likely trained on an anime waifu model.

BECAUSE HE IS THE ULTIMATE WAIFU.

...yes. I said it.

If you're the real Alex Brightman, please don't make me take this down please XD it's meant to create LOVE, JOY AND - while ok you're on here twice cause of beetlejuice - just --- LEAVE ME TO MY FANJOY!

A horse costume that gives you a lot of energy.

A cheerleader costume worn by horse girls that helping you jerks your densest vigor out.

This is a headso be sure you have the requirement installed.

• Base model : Anything-v3.0

• Trigger Word：run and win costume, cheerleader,

• Optional：cheering, sleeveless shirt, open jacket, pom pom (cheerleading), sailor collar, bike shorts under skirt,

• Comparison of optional prompt and weight :
  https://imgur.com/a/CyF3ieF

• Since this costume is belong to Nice Nature originally, she will show up surpriselly when some of your prompts contains traits about describing her.(e.g. streaked hair, high ponytail, pom pom) Lowering the weight or NG will be helpful.

• Slightly support NSFW I guess? (is clothing sex include?)

• Not sure about it will work on 2.9D model or not.

4/14: Reconstructed by excluding materials that affect the lower body. (delete and fix gape image)

Perhaps a classy lower mouth is summoned. Naughty things should be just nipples and areolas... Please try v2.0!

4/14:Reconfigured to exclude material that would affect the lower half of the body. (gape image removed and corrected).

Presumably a classy lower mouth will be summoned. The only naughty bits should be the nipples and areola. ...... v2.0Try it!

LoRA that makes your nipples and areolas plump and sharp.

Recommended for those who complained that the nipples output by Stable Diffusion are too beautiful and tasteless.

This LoRA makes nipples and areola plump and pointed.

This is recommended for those who have been saddened that the nipples output by Stable Diffusion are too beautiful and tasteful.

Produced by Locon. I think a weight of 1 is fine.

It can be used with both live-action and anime models.

It is produced in Locon. weight is fine for 1.

It can be used for both live-action and animated models.

I think that those who understand Japanese will understand, but originally LoRA has pointed small breasts, but due to various circumstances, even big breasts like the sample image are made to have puffy nipples without any problems.

As those who understand Japanese will understand, it is LoRA that originally makes tippai pointy, but for various reasons, we have made it so that even big breasts like those in the sample image can become puffy nipples without problems.

This is a LoHa LoRA! You need the extension!
Why? LoHa have virtually no effect in output art style and they do a lot better with multi-concepts.

Trigger words for V2.20:

(double-buns) or (buns-cover)
This version is a little better with differentiating between covered and uncovered.

You can try "double-buns"for uncovered buns, "buns-cover"or "white buns-cover"for covered buns (these 2 are mutually exclusive, chose one!), "hair ribbon", "hair ornament".

Notes: It doesn't do very well with the buns color! Its almost always white since that's mostly what the dataset was! You might get different colors, you can try very basic ones. If its failing to generate "buns-cover", prompting for "white buns-cover" increases the chance of it generating the cover variation.

Follow the steps in the Model Version notes to reproduce my images.

Sample images generated from Grapefruit.

All negative embeds should be easy to find. and Prompts should be included in the sample images! Click the little icon in the bottom right to see it.

You might want to add somenegatives,for example:

It was trained on 211 512x512images scraped from the internet and 13 epochs using animefull_final.

Danbooru tags generated by Waifu Diffusion 1.4 Tagger and fine tuned for specific tags.

Kelsey's loha is made with NAI 7g version, pursuing better versatility.

It is recommended that the weight be <=1. When the weight is 1, the screen will generally not crash, but it will have a great impact on the style. If you want to keep the style of the bottom model as much as possible, then you should lower the weight, and the most appropriate value needs to be combined with the specific model test. 0.7-0.8 is probably a good range.

In order to facilitate the modification of various features, this loha does not delete any feature tags, so please copy the feature vocabulary in the version description according to your own needs when using it. This is also a new attempt I made.

Loha by kal‘tsit was made using NAI 7g version, aiming for better versatility.

Recommended weight <=1. When the weight is 1, the image is generally not prone to breakage, but it has a significant impact on the style. If you want to preserve the style of the base model as much as possible, it is recommended to lower the weight. The most suitable value depends on specific model testing. 0.7-0.8 may be a good range.

For the convenience of modifying various features, this Loha has not removed any feature tags. Therefore, when using it, please copy the feature tags from the version description according to your needs. This is also a new attempt that I have made.

Weight: 0.75-0.80
Model used for samples: Erotic Vision v3, should also work well with Realistic Vision.

Dim/alpha/conv are all 128, tried with lower for smaller file size but results weren't as nice.

Open to suggestions for other concepts/positions!

Ai Hoshino

More variations for this + v2.5 https://huggingface.co/KoRo8888/ai_hoshino

recommended for v2.5: very hard → hard

model: detailed project v4(on closertodeath profile on huggingface), animefull-latest, anything v4/3 Recommended VAEs: clearvae(best), klf8anime

tokens: ai hoshino, animescreen cap(optional but gives better results) [use image filters and enable it then raise the "colors" on it to git rid of the desaturation 2~8]

V2.5 is out

https://huggingface.co/KoRo8888/ai_hoshino/tree/main/Ai_Hoshino_v2

Just nape

adjusting hair\tying hair\hair lift and so on

Please generate small images, close-ups, don't expect it to be helpful for perfect fingers

Please generate small pictures, close-ups, don't expect it to help perfect fingers

Note #1:This is a Locon. Install the extension to get it to work. I've found them to do better when working on ideas that I want easily added to one of my LORA characters. Also, they're WAY less damaging to images, even at high weights.

What does it do you ask?Part of my CAC series, this one focuses on a symbiote taking over and infecting your waifu. It has a couple different trigger words that have various effects, as well as some recommended general tags if you want to emphasize certain aspects that I have found fun. I didn't hard bake them into the Locon but let them be easily called. Please read the next section for information.

How to use it: First we have the core triggers baked into the Locon.

TOver- Main trigger word.

NOMASK or WMASK- Choosing one of these tries to get the Locon to emphasize mask or not.

Optional but tags that are powerful in here:

mask, skin tight, bodysuit, slime (substance), covered eyes, no eyes, monster girl, tentacles, torn clothes -All these tags have a powerful effect in this Locon and work well thematically. Pick and choose which ones (if any) you want to use in a given picture. There are definitely a lot of other tags to use though, just some recommendations!

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

Picture Descriptions:

1-3: AnythingV3 using just this Lora with simpler prompts.

4: AnythingV3 combo'd with my released Amiri (Iruma-Kun) Lora.

5: AnythingV3 combo'd with my released Rozalin (Disgaea 5) Lora.

6: AnythingV3 combo'd with my released Catherine (Catherine Full Body video game) Lora and with the mask on.

7: AnythingV3 combo'd with my in progress Pet Play Locon.

8: AnythingV3 combo'd with my in progress Knight-ify Locon..

9: AbyssOrange with just this Lora.

10: PerfectWorld 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?

Hopefully this one is better, if not I'll update it again.

What's next that isn't this?

More character Loras. (Zephia Fire Emblem Engage, Ivyfrom Soul Calibur 5, Heinefrom Combatants Will Be Dispatched, I conquer Lilias from E7, Evelynnfrom LoL (both base and All Out version), Dry from Fire Emblem, Catherine from Catherine Full Body, Mikufrom Idaten Deities, Kuribayashi Shino from GATE, Sohma too from Fruits Basket, Kasumi from P5, Ann from P5, Ikumi Mito from Food Wars, Alice I confess from Food Wars, Chika Fujiwara from Kaguya-sama, Lulu from FF10, Momo from My Hero, Sheik from Zelda,Vivi from Vivy, Lucoa and Tohru from Dragon Maid, Dominique de Sade from Vanitas, and Of the from One Punch Man.) And maybe William of Astrea, my favorite Re:Zero husbando or aPrinny 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, Demonic Transformation, being stepped on, Robotification, 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), Brainwashing Machine, 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, Jiangshi(Transforms into a Jiangshi), Mind Flayer Defeat, Blacked, Harem Outfits, Hourglass Figure(just to make your waifu curvy),andHolding a Leash.

And, uh, I want to make a few "normal" Locon's so I have an "knight-ify" your character one coming up. And a forest fairyone as well. And a officer one. And a barbarian one.

Additionally, I love the style of Defaultz_17, so I'm making a Locon to mirror that.

Or just give me some random suggestion or priority opinions. That works too.

Lively Mezarance lora, Len

Legal & Risk

It is prohibited to use this model for commercial purposes and any scenarios of illegal acts and purposes.

In principle, I do not support the use of this model to generate any adult content. When using this model, users must abide by laws and regulations, and do not infringe other people's reputation, privacy or portrait rights.

Usage

ATTENTION, YOU NEED TO INSTALL THIS EXTENSION TO USE THE LyCORIS VERSION!

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

WARNING!!! Due to the datasets nature, it's really hard to generate SFW image.

Any Sd1.5 based model will produce good results

• 512,768 image

• DPM++ SDE Karras

• Use 20-30 sampling steps

• Weight: 0.5-0.8

• CFG: 4.5-7

If using Hires:

• Hires step: <20

• R-ESRGAN 4x+ or Latent variants

• Denoising: 0.3-0.7

After download this model, try to share with us about your findings.

Please give star reviews with your picture creation if you like it.

But, don't use this for commercial use and she is not an existing person!

p.s. It's not necessary but If you like my LoRAs please consider to support me to create more projects by donate in here:

https://ko-fi.com/gorillamonsooniii

I'm also accept commisioning for LoRA

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

Using Fix itinstead of Gal to trigger.

because the model I use for training prefers the former.

• This LyCORIS can help generate anime Gal/Gyaru characters. Please note that it may create a strong NSFW vibe even if you don't intend to.

• Clothing include Tied_shirt Open_clothes Leopard_print Bikini Microskirt Swimsuit Shorts

• Known issue: Gyaru may tend to make a "V" sign or various hand gestures near their faces, and sometimes shirt knot may appear below the breasts.

trigger word : aunt cass

recommended strength : 0.85 toi 1, do not use below 0.75
use lower strengths only if model is not following the prompt.

I recommend using Dream Shaper 5
you need this extension to run this file

then load like a normal lora file

if you like my stuff pls consider supporting me on Kofi

Convex (☎︎ω☎︎) Convex Convex (☎︎ω☎︎) Convex

Kuso Model.

poptepipic 1st season opening concept.

Introduction

This model aims to restore the details of the human design as much as possible, and has good generalization performance.

Introduction to trigger words

ayakalora is added when representing the official setting clothing

ayakacustom is added when expressing other custom clothing, and corresponding clothing descriptors need to be added

Introduction

This lora aims to restore the details of the character as much as possible, while also having good generalization performance.

Trigger Words

Ayakalora: when presenting official set clothing

ayaka custom: When presenting other custom clothing, corresponding clothing prompt words need to be added as well

Note:

This is a LYCORIS/LoCon model, and you need to install a1111-sd-webui-locon/lycoris extension to use this model.

This is a gouache style LoRa that I created to make the style generated by the anime model look like a gouache painting.

There are two versions available here, namely the trim version and the original version. Generally, downloading the trim version is sufficient.I have already adjusted the Trim version to the weights that I consider appropriate using SuperMerger. The original version has not been adjusted in any way. You can adjust the weights yourself using the lora-block-weight.

Trigger words:gouache

Suggest weight:0.5-1

Use highres fix. to get better results.

based on AnythingV5V3_v5PrtRE

Prohibition of bussiness use.

Prohibition of any use that compromises personal rights and privacy.

Commercial use is prohibited.

Any use that compromises individual rights and privacy is prohibited.

If there is any infringement, please contact me to delete.

Model

用ACertainty训练的，推荐0.6-0.9强度。

Trained In ACertainty.Recommend strength is 0.7-1.0.

Works best on ACertainty series such as: bp_mk5, bp_nman_e29, but still good on Nai based models.

Work best onACertainty series such as: bp_mk5,bp_nman_e29,but still works well on Nai based models.

Generalization tests

Test on anythingV5PrtRE,0.8 weight.

LyCORIS of Lake Bell

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License

the regular creativeml-openrail-m license isn't applicable for this work

04/13/23 update

see About this version

==================

well well well....

I'm honorable represent to you my first published creation at the Ai theme, i'll asking you to be kind and do not judge strictly. So first things first lemme tell you a little story just real quick)

I've tamed a beast that made by Kohya(finally that unuser-frendly bunch of scripts have worked just fine.... so far). I spent 4 days to figure it out how works all of it, chose a character, scraped some pics(man... there are not so much of them, especially quality ones), and here i am! After a third run i've got decent(to me) model's result. (yeah this is 4th attempt)

What's this model capable of you might ask?

• Portraits

• Full shots

• and of course, classics cough....

cough...

cough(hysterically)....lewd i've meant, but it highly depends on what model and tools(controlnet etc.) u'll be using and what your power in prompt's knowledge.

About resolution: model's been trained on pics with res. 768x768 so it's mean that not all model will be working properly above that resolution, in my case 768X1024 worked just fine by some tests(yep +1 day wasted on hundreds tests), but then i got encountering anatomical errors and deviations. so go ahead play with it as much as u want🧡

and share with your results cz that will help to improve the current state's model(probably)

Most importantly weights: around 0.9 will be more then enough but you always capable to push through the limits.

For example, for your images, actually just use prompt that shown in the preview or start with these ones: 1girl, jewelry, hair over one eye, dress, bracelet, blonde hair, black dress, long single braid, large breasts, ring, circlet, necklace, armlet, yellow eyes, parted lips, bare legs, single braid, backless dress, hair ornament

P.S. for fuck sake Kohya would u might make that shit much easier to work with, huh? there are fuck 4 days needed to it had worked, fuck...

9th cycle of hell has been passed

LyCORIS of Juliette Lewis

LyCORIS of Jenna Fischer

NOTE: I am not as happy about this model as the other ones. Something is not quite there (and I mainly mean LyCORIS, since the Dreambooth was rather good).

You can still produce interesting results but not as often as with other models. I may revisit this model and provide a second version if people will struggle to get something good with V1.

LyCORIS of Halle Berry

NOTE: I am not as happy about this model as the other ones. Something is not quite there (and I mainly mean LyCORIS, since the Dreambooth was rather good).

You can still produce interesting results but not as often as with other models. I may revisit this model and provide a second version if people will struggle to get something good with V1.

LyCORIS of Gwendoline Christie

LyCORIS of Freema State

Lycoris of Carla Gugino

LyCORIS of Bruce Lee

LyCORIS of Anya Taylor-Joy

Lycoris of Alessandra Torresani

LoHa Lycorismodel trained using images of Gibi Asmr.

This is a locon of the anime character Hoshino Ai. I have trained her star-shape pupil in this model, so you can get a perfect star shaped pupil via inpanting.

Recommand strength:0.6~0.8

No trigger prompt

How to generate Star-shape Pupils:

To get her special pupil shape, please inpanting with the prompt: starpupil, close-up, eye focus

select "Only masked"

denoising stength 0.4~0.6

————————————————————————————————————————

This is a locon anime character Ai Hoshino. I trained her star pupil with this model, so you can get a perfect star pupil by inpanting.

Recommended strength: 0.6~0.8

No trigger word

How to generate a star pupil:

To get her special pupil shape, follow the prompts for inpanting: starpupil, close-up, eye focus

Select "Only masked"

Denoising intensity 0.4~0.6

————————————————————————————————————————

This is the locon model of the anime character Ai Hoshino. I used this model to train her stellate pupils so I can get perfect stellate pupils with inpanting.

Recommended strength: 0.6-0.8

No trigger prompt

How to generate star eyes：

To get her special eye shape, follow the tips and enter: starpupil, close-up, eye focus

Select "Only masked"

Noise reduction strength 0.4 ~ 0.6

Have you heard the news that you're dead?

This model is designed to emulate the look of the band My Chemical Romance while promoting the album "The Black Parade." It's one of my favorite albums of all time and I've been a bit obsessed with it lately so I thought I'd make this. Model was trained on both photos and illustrations of both official and "good" unofficial versions of the coat. I retrained the model about 6 times before finally using the model NeverEnding Dream, which gives it an amazing consistency in both illustrated and realistic models. I'd recommend not going higher on 0.8 with this, as it can get a bit quirky at higher weights.

While this was trained a lot of pictures of Gerard Way, its not designed to replicate him specifically. I've had good results just giving it a brief description and mentioning his name, if you're into that. The model is a LoHA which is supposed to be good at capturing concepts, but you need the Lycoris extension for A1111 in order to use it. The models used to generate images were Analog Madness and MeinaMixV8.

(The Gardevoir girl who shows up in all my gens is an OC of mine named Sonia. She's basically my mascot at this point. She uses thesauceer's Gardevoir Lora)

Reposting it since the website didn't want to upload my model due to bug of browser...

Whatever weight pleases you, trigge'r is Kirari.

Trained with novelai best result with it but you can use others models.

Give me your feedback~

/!\This is a LyCoris/Loha not a lora sorry for the mistake!

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

Then put your model in \stable-diffusion-webui\models\LyCORIS

Finally use the lycoris tab and choose the model you want to use :

I apologize for the mistakes, if you need help just ask in the discussion.