blue archive

日本語しか話せないので英語はGoogle翻訳です。

I can only speak Japanese, so English is Google translation.

English

There is nothing I can do about finger deformation, too many/less fingers, so please gacha. About 20% of the author's experience is a feeling that a proper hand will come out.

The trigger word is penetration gesture.

I'm testing with a tag strength of about 1.1 to 1.4. If the Loha intensity is 1, it will probably have a bad effect on the drawing style, so it may be better to do it at about 0.6 to 0.8.

The model has been tested with Anything_V4.5 and kotosmix. I don't know if it can be used otherwise.

The model used for training is Anything_V4.5.→ V2 uses AnyLora

I want to do something about the influence on the style of painting
→ It may have been improved to some extent in V2

日本語

指の変形、指が多い/少ないは正直どうしようもないのでガチャしてください。筆者の体感20%ぐらいはちゃんとした手が出るかなという感じです。

トリガーワードはpenetration gestureです。

タグの強度1.1~1.4ぐらいでテストしています。Loha強度は1だとおそらく画風に悪影響があるので0.6~0.8ぐらいでやるといいかもしれません。

モデルはAnything_V4.5およびkotosmixで動作確認しています。それ以外で使えるかはわからないです。

学習に使用したモデルはAnything_V4.5です。→V2はAnyLoraを使用

画風への影響は正直何とかしたいなと思っている→V2である程度改善されたかも

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

24 Cans of Monster (METEION FFXIV)

Note: IF YOU HAVENT PLAYED ENDWALKER AND YOU PLAY FFXIV DO NOT USE THIS. SPOILERS MUCH SPOILERS. Also uh, if you just like pretty things do download cause she's fantastic!

WILL TAKE SOME PRETTY HEFTY PROMPTING TO GET World Ending Depresso Meteion either that or we're just lazy.

A meme to explain the meme:

We stream a lot of our testing on twitch: https://www.twitch.tv/duskfallcrew

any chance you can spare a coffee or three? https://ko-fi.com/DUSKFALLcrew

If you want custom LoRA OR MODEL trained an option will become available on the Patreon: https://www.patreon.com/earthndusk

This LoRA will end the world if you don't each her the proper ettiqutte.

AND NO METEION IS NOT A CHILD ffs lmao.

She's a birb.

🌟Want to buy me a coffee or commission me a lora ?🌟

There are 2 models both are nice but one is easier to use but less precise ( the 05 )

Note #1 And VERY IMPORTANT: THIS IS SUPER BETA RIGHT NOW, PLEASE BE RESPECTFUL. You will likely only get ok images one out of every 25-30 tries, depending on complexity and following my initial prompts. I'm looking for feedback on what works well and what doesn't as this one is so fucking complicated and I was getting stuck :). Let me know how your tests go, just don't blame me if you get crazy monsters. Oh, but do have fun with it! And it felt like it worked best on AbyssOrange but I could just be delirious with that after staring at so many pictures.

Note #2: A second upload for today, namely cause I'm tired of working on this one for now and need a little break and feedback. I've made too many version to count :(.

What does it do you ask? Well, 90% - 95% of the time not what you want. The 5-10% it might work, it'll give you your waifu wearing whatever you designate in front of you, while the viewer is holding a camera with her in a different outfit and state of undress. Importantly, she should be more skimpy looking on the phone then in real life. Now, is this her sending you the pic? Her new lover? I dunno. Whatever you want to RP it as.

How to use it:

(I use Sampling Method DPM++ SDE Karras and Upscaler R-ESRGAN 4x+ Anime6B) (Let me know if something works better for this Locon)

Highly recommend not using hires.fix immediately. Make a batch of like 20-40 images, fine one you like, then use hires.fix on that one to try to fix it. I didn't use inpainting in any of these images but that will obviously help a ton as well.

I have found the following prompt to give me a decent amount of success, though it needs tweaking on each model and with what you add. Please try this AND try your own versions to see if you can get a better basic prompt working. I'll thank you forever. And just give me general feedback so I can make a V2.

<lora:YourLoraNameHere:0.9>, PhonePic, (viewer holding phone, phone screen), netorare, 2boys, penis, sex, vaginal, nude, nsfw, ((sundress)), 1girl, full body

Now, breaking it down:

<lora:YourLoraNameHere:0.9>, PhonePic, (viewer holding phone, phone screen) - I've been putting some version of this in every prompt.

netorare, 2boys, penis, sex, vaginal, nude, nsfw - Put here whatever you want her to be doing on the phone. Replace COMPLETELY with just an outfit if you just want her chilling in the phone pic.

((sundress)) - Put here whatever you want her to be wearing in real life.

1girl, full body - Not mandatory. I'm just trying stuff out.

Extra, Extra!: This won't work well. I warned you :).

Picture Descriptions:

1-3: AnythingV3 using just this Lora and my prompt style

4-5: AbyssOrange using just this Lora and my prompt style.

6: RevAnimated using just this Lora and my prompt style.

7: AnythingV3 combo'd with my in progress Vivy Lora.

8: AnythingV3 combo'd with my released Tohru Lora.

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

How was it trained?

It was trained on animefull_final with variable amount of images with the usual self-pruning and tagging and a wide range of different images. This specific version has 25 images because I cut a lot of them because I think they were making it not work too often.

What's next for this?

Any sort of improvement I can squeeze out of this... Which is a lot.

What's next that isn't this?

More character Loras. (Viper and Rupee from Nikke, Spectre Tenebria from E7, Zephia and Yunaka 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, Momo from My Hero, Sheik from Zelda, Vivy from Vivy, 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, Beta Censorship (Automatically censors any images you create to make them BetaSafe), PhonePic (Thisone has been very, very hard... But TLDR, someone holding a nuder version of the waifu on the phone), Demonic Transformation, 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), 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, Hypnotized Harem, Hourglass Figure (just to make your waifu curvy), and Holding 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 fairy one 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.

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.

!! PLEASE READ !!

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

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

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

Weight: 1.0

Trigger: there's none

This model is trained on 506 images and the resolution is trained at 1024. I recommend hires fix.

This LoRA is not official or authorized.

I check Twitter every day, so I will respond when I receive a DM.
ツイッターは毎日チェックしているのでDMが来たら対応致します。

Idk what's the suitable model for this, you may get bad result, some upscalers will give also blurry images so use R-ESRGAN 6B, you explore the model yourself. I'm so tired to do that.

Trained on Anything V3 using cherry picked pictures from the Love Hina Anime adaptation (aired in 2000).

Gettings pretty good results with a default weight of 1, and then going to 0.8 (more liberty on outfits) or to 1.2 (better looking face and fidelity of the character).

As training pictures are only from the anime adaptation, you will also have a high chance to get the same "2000 anime style feeling".

Trained on Anything V3 using cherry picked pictures from the Love Hina Anime adaptation (aired in 2000).

Gettings pretty good results with a default weight of 1, and then going to 0.8 (more liberty on outfits) or to 1.2 (better looking face and fidelity of the character).

As training pictures are only from the anime adaptation, you will also have a high chance to get the same "2000 anime style feeling".

Tend to do the old trigger artstyle on Promare & Guren Laggan the most.

Animes that were used on the dataset: Guren Laggan & Promare(the most) , Kill La Kill, Darling in the Franxx, Kiznaiver,, Cyberpunk (not alot) [note: you can use lykon lora if you want to use cyberpunk artstyle]

Trigger Studio Artstyle

Best weight 0.5/0.7

Note #1: This Locon can get you good pictures just by itself BUT I do highly recommend adding other tags to the prompt to guide it in the way you desire. Please look at the "How to Use" section for some suggestions.

What does it do you ask? Sometimes you just your waifu to embrace pet play and to be excited to see you. Is that to take care of her as a parental figure? Or for more sexual devious reasons? Uh, either way, this is a Locon for that. It'll help guide your prompt to get your waifu down on the ground and wait for her master friend of course.

How to use it:

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

First we have the core trigger baked into the Locon.

PPlay - Main trigger word.

Also, add either:

PPUp, paw pose, squatting, spread legs (with 512x768 resolution but others can be used too) - PPUp is for leaning the Locon towards in a paw pose style position.

or

PPDown, all fours (with 768x512 resolution but others can be used too) - PPDown is for leaning it towards an on all-fours position.

PPB - Will allow the Locon to lean to adding bondage as well.

Here's a list of other tags that affect this Locon well. I'm sure there are other ones as well but this is just a starting off point for ideas.

tongue out, open mouth, hanging breasts, sex toy, anal tail, fake tail, object insertion, pussy juice, piercing, bdsm, bound, collar, gagged, bondage, saliva, leash, viewer holding leash, cum

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

Picture Descriptions:

1: RevAnimated using just this Lora.

2: AbyssOrange using just this Lora.

3-5: AnythingV3 using just this Lora showing the different simple prompt

6-7: AnythingV3 combo'd with my released Ghislaine Lora in different positions.

8: AnythingV3 combo'd with my realeased Ameri Lora.

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

10: AnythingV3 combo'd with my in progress Hourglass Locon.

11: AnythingV3 combo'd with my released Symbiote Taking Over Locon.

How was it trained?

It was trained on animefull_final with 56 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?

Should be good to go with this one but let me know of errors.

What's next that isn't this?

More character Loras. (Viper and Rupee from Nikke, Spectre Tenebria from E7, Zephia and Yunaka 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, Momo from My Hero, Sheik from Zelda, Vivy from Vivy, 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, Beta Censorship (Automatically censors any images you create to make them BetaSafe), PhonePic (Thisone has been very, very hard... But TLDR, someone holding a nuder version of the waifu on the phone), Demonic Transformation, 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), 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, Hypnotized Harem, Hourglass Figure (just to make your waifu curvy), and Holding 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 fairy one 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.\

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.

!! PLEASE READ !!

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

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

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

Weight: 1.0

Trigger: there's none

Doing something new which is training a new style as a LoCon! I think it came out pretty well at 10 epochs (and as of typing this, I still have more epochs to go through). The resolution trained is at 1024. I recommend hires fix.

I'm gonna use this as like a to-do list so I don't forget:

• new Ozen version, includes hat and thousand-men pins

• more Blue Lock characters

• one more Brawl Stars character

• take a break

• male Ace Attorney characters (Ryunosuke Naruhodo's gakuran outfit is super wonky)

• Kiryu Kazuma and Goro Majima (play Yakuza and Judgment, they're great franchises)

• character requests?

please ensure you read the instructions before you use it！all the pics are with generation data, just download it and see it in webui!

important

Basic setting Lora weight 0.65 and Denoising 0.2-0.3！！！

基础设置 lora权重0.65-0.8，重绘率0.2-0.3，最佳区间！

前言:

如果你要支持我，请通过tangtuanzhu的微信联系我，给我支持...，这样我才有电费和显卡继续跑图。我的其他模型都在这里：ttplanet Creator Profile | Civitai

请下载我的范例图片并从webui中获得提示词，不知道是不是bug不能直接读取！！！

if you see missing generated data, please download the pic and get it back from webui! this is the new bug of Civitai！

Hires fix is highly recommended!

推荐一定要高清修复！

介绍 Introduction:

这个模型非常的好玩，可以把你的人物塞入一个包装盒里面，如果你组合使用其他模型就会出现玩具的效果。塞入包装盒的除了人物，还有和他相关风格的装饰，衣服等，你可以自己输入关键词来添加，虽然不能精准到每一个物品，但是也基本上八九不离十了。

目前没有加入动作支持，请自行使用controlnet控制动作，将在V2版本中迭代大量的动作，让使用起来更加简单随机，但是依然推荐使用controlnet进行控制以获得最好的效果。

如何使用 How to use:

注意事项，由于webui没有内置LyCORIS使用前一定要记得安装插件,

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

然后使用传统的方式调用lora, 比如： <lora:miniatureWorldStyle_v10:0.6>

请注意使用我的tag,你记得修改lora的名字，我的tag是本地的名字，和你下载的不一样！！

Reminder: if you want to use my tag, please check the lora name, see if it is consistent to what you downloaded!!! my local file name does not match the online version!!!

根据不同的模型，建议使用权重为0.6-0.8，但是不要使用1,基本上会爆炸。

使用结构为：

inbox\(ttp\)作为触发词，<lora:loraname:0.7>作为调用词，中间放入你放入的人物行了。使用很简单，人物描述尽量使用自然语言。

use 0.6-0.8 weight based on different SD models, but don't use 1

inbox\(ttp\) to trigger，<lora:loraname:0.7> to use the lycoris, and put down the person you want to put into the box, please use nature language to describe the person.

范例 example:

inbox\(ttp\), (8k, RAW photo, best quality, masterpiece:1.2), (realistic, photo-realistic:1.37),1girl, huge breasts, (holding a guitar:1.5), (solo), blonde hair, instrument, guitar, boots, pants, male focus, reference inset, standing, electric guitar, red pants, shirt, full body, microphone, long sleeves, amplifier, looking at viewer, white footwear, holding, realistic, shoes, blue eyes, black shirt, jewelry, fashion, short hair, english text, print shirt, glasses, holding instrument, full body, simple background,

<lora:inboxgirl_V1_loha-pickup1:0.65>

权重0.6-0.8是变成盒子的最好区间，低于0.6不会进入盒子但是会提高模型的身材，高于0.8会由于lyCORIS特点出现独特的画面劣化。请注意调整。日常使用请用0.65,这是我调节过最平衡的参数

please use 0.6-0.8 weight to get the best result, any weight lower than 0.6 won't trigger the box, and above 0.8 will destory the pic. for regular use 0.65 will be the best!!!

模型本身倾向使用平坦的胸部，请使用巨大来进行平衡。

the model is with high weight to be flat breast, so use huge to balance it

如何进阶使用 How to use(advanced):

1. 使用controlnet来控制你的人物动作，记得调整骨架的大概大小和位置。please use controlnet

2. controlnet也可配合大头骨架生成Q版造型，请查看我的范例图获得灵感。use controlnet can build the chibi outfit

3. 可以和很多lora进行融合，使用的时候请注意控制权重。本模型权重较大，请适当增加你配合的lora权重, can be used with other lora together

4. face editor plugin 强烈推荐使用，脸部会因为lora变成你不喜欢的样子，可以搭配不同的lora使用face editor提高效果。就算不用lora也会更好看，使用face editor的时候请移除本lora再使用，保留其他prompt

おっぱいぶるんぶるん！！になるLoRAです。

weightは１で大丈夫だと思います。ただ当然ですが、おっぱいが小さいと揺れませんので巨乳ワードは入れてください。

Tits bouncing! This is a LoRA that will be

I think weight is fine at 1.But of course, if your boobs are small, they won't shake, so please include the big-breasts word.

おっぱいが揺れやすいモデルと揺れにくいモデルがあります。

試した中ではAOM３系とany4.5がモーションブラーも出やすくよく揺れました。

There are models that tend to make the boobs sway easily and models that do not sway at all.

Among the models we tested, the AOM3 series and any4.5 models were easy to produce motion blur and swayed well.

他のイラスト系のモデルも元気に揺れますがモーションブラーが出にくいかも。

実写系weightを上げたりすれば揺れることもありますが、おっぱいが増えたり作り物っぽくなって全然ダメでした。色々試してみてください！

Other illustration-type models also shake well, but they may not produce motion blur as easily.

If you increase the weight of live-action models, they may shake, but the boobs increase and they look fake, which is not good at all.Try different things!

Hibari from the Senran Kagura franchise

• Trained with Anime (full-final pruned) model.

• 4 variants; 8 epochs, 9 epochs, 10 epochs, Exp- 10 (10 epochs, trained with increased-weight tags)

• Good results with 0.7+ weights.

• Activation tags; hibari_sk for general info (add short hair and twintails to the prompt just to make sure.), hibari_uniform for her school uniform (add sefuruku, sailor collar, and pleated skirt in case of items disappearing.), hibari_dot_bikini for her polka dot bikini (add pink bikini, polka dot bikini, striped bikini, and frilled bikini to the prompt in case of this outfit not coming out right.)

Introduction

A Lycoris model of Emma from Sekiro: Shadows Die Twice. The trigger tag is ‘emma \(sekiro\)’. The 784mb VAEs (NovelAI, Anythingv3, Orangemix, Counterfeit) are recommended. 0.6 ~ 0.8 weights are good. The preview images are generated using 1.6 version (original) YesMix.

Cautions (Must Read)

• Some preview images are generated using hires fix. Thus, if you wanna generate the preview images, pls download the original preview images and analyze them using 'PNG INFO' in webui to get all generating information.

• The maximum of generating resolution should not exceed 1024 theoretically, otherwise extra/deformed head/limbs will be waiting for you :). Try to use 'hires fix' to prevent this problem and help to generate higher-resolution images.

• For 784mb VAEs (NovelAI, Anythingv3, Orangemix, Counterfeit) users, make sure add '--no-half-vae' in command line of webui to prevent generating black images. See voldy's log for the details of edit method. For high-performance GPU, make sure 'medvram' and 'lowvram' mode are disabled.

Requires LyCORIS extension

Trained with AnyLoRA model

I typically use this model with 1.0 weight and following prompts

• prompts: rim, multicolored eyes, yellow pupils, jewelry, earrings, jacket, blue hair,colored inner hair, red inner hair, open jacket, shirt, short hair, open clothes, hood, long sleeves, red jacket, blue shirt, two-tone hair,bangs, parted lips, hooded jacket, yellow eyes, gradient eyes, side braid, blue eyes

• negative: blurry, stomach, yellow hair

Main trigger prompt is rim.

Hair color is not stable. Need more test with hair.

I am not the artist of the character nor RIM herself nor related to thinkr incoporation.

All right reserved to RIM and KAMITSUBAKI Studio(THINKR inc)

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.

Changelogs

• v1: LoRA version

• v2: LyCORIS, retrained using Halcyon models

Usage

If you want to use as standard LoRA just install LoCon extension from KohakuBlueleaf github,, otherwise install with SD webui LyCORIS extension, also from KohakuBlueleaf github

Best outcome with Halcyon checkpoint

• 512,768 image

• Use DPM++ SDE Karras

• Use 20-30 sampling steps

• Weight: 0.6-0.9

• CFG: 4-7

If using Hires:

• Hires step: 20

• R-ESRGAN 4x+

• Denoising: 0.3-0.6

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

This LoRA is not official or authorized.

I check Twitter every day, so I will respond when I receive a DM.
ツイッターは毎日チェックしているのでDMが来たら対応致します。

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.

Changelogs

• v1 : LyCORIS, but also can be use as normal LoRA Deprecated, don't use

• v2: Fixed dataset, trained using Halcyon checkpoint

Usage

ATTENTION, YOU NEED TO INSTALL THIS EXTENSION TO USE THE LyCORIS VERSION IN SD-WEBUI EXTRA NETWORKS

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

Iif you don't want to use this model as LyCORIS, just put it on LoRA folder to use as standard LoRA

Parameters:

• 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 / others

This LoRA is not official or authorized.

I check Twitter every day, so I will respond when I receive a DM.
ツイッターは毎日チェックしているのでDMが来たら対応致します。

We will comply with the Re:AcT secondary creation guidelines.

This LORA is Misawa Maho from RO-KYU-BU!

inital tags:

"misawa maho, blonde hair, blue eyes, twintails, fang"

main costume:

"gym uniform, bike shorts"

"basketball uniform, shorts"

You may want to use 7thLayerAbyss or AOM3A.

show you guts cool say what saikou daze.

This LORA is Kashii Airi from RO-KYU-BU!

inital tags:

"kashii airi, short hair, brown hair", (large breasts)

main costume:

"gym uniform, bike shorts"

"basketball uniform, shorts"

"hoodie, shirt, shorts"

You may want to use 7thLayerAbyss or AOM3A.

show you guts cool say what saikou daze.