We will comply with the ANYCOLOR secondary creation guidelines.
https://www.anycolor.co.jp/guidelines/
It seems that no particular intention is indicated. I pledge to create and publish works that respect the spirit of ANYCOLOR content.
特に個別の意向が示されていないと思われます。ANYCOLORコンテンツの精神を尊重した作品を制作、公表していく事を誓います。nui_sociere
Weight : 0.5～0.7?
The model for the illustration for the sample is based on 7th_anime_v3_A and has been merged several times, including AOM3.
7th_anime_v3_A will be a close illustration.
Please use it in an environment where LoCon is available.
ACertainThing.ckpt is used as the model for the study.
nakano yotsuba
If you'd like to support me and do more:
https://ko-fi.com/edgonkofi - commissions open!
If you're looking for a >>LoRA Making Tutorial<<
This model features a dancer of the desert (BDNC trigger word) + my lingerie models (garterbelt and dessous).
BDNCgarterbeltd2dd2c
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
see About this version
#Queen Marika, 1girl, medium breasts, blonde hair, jewelry, long hair, single braid, solo, yellow eyes, dress, bracelet, black dress, necklace, parted lips, circlet, armlet, pelvic curtain, braid, design by Mark Brooks and Brad Kunkle detailed, gorgeous lighting, wide angle, action dynamic scenery, outdoors#
==================
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
Queen marika \\elden ring\\Queen marika
Masumi Kotsu from Yu-Gi-Oh! ARC-V
Trained with Anime (final-full pruned) model.
4 versions; 6 epochs, 8 epochs, 9 epochs, 10 epochs (Feel free to combine these for different and interesting results.)
Expect good results with 0.5 - 0.7 weights (through txt2img) and 0.85 - 0.95 weights (through img2img), also you can try ALL, MIDD, OUTD, OUTALL.
masumi_kotsu
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.
v1 : LyCORIS, but also can be use as normal LoRA
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
WARNING!!! Due to the datasets nature, it's really hard to generate SFW image.
Best outcome with my own Halcyon Checkpoint, here's the link:
https://civitai.com/models/41141/halcyon
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
The model was carefully created to avoid overfitting at a resolution of 1024.
Training is done with batch size=8, gradient accumulation step=16.
It should probably work on many models.
It seems to be available for realistic models such as chilloutmix.
I recommend using a weight of 0.7 to 0.9.
LyCORIS (LoHa), please install and use a1111-sd-webui-locon or a1111-sd-webui-lycoris
Match file_name with the name of the LoHa file you downloaded.
basic example:
<lora:file_name:0.7> 1girl, solo, wamdus, thst, 1girl, solo, umbrella, thighhighs, holding, looking at viewer, purple eyes, smile, holding umbrella, dress, staff, ahoge, full body, white hair, white thighhighs, boots, holding staff, bangs, hair between eyes, blue eyes, :d, short hair, wide sleeves, white dress, long sleeveswamdusthst
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 helps leans your waifu into becoming a dominatrix. It'll give some sort of variety of clothing that you would expect from such illustrious profession but it can also be adjusted to your own preferences in the prompts. Also, I made the pictures lean towards give you one from below, as that makes more sense to me for this Locon but I think I avoided baking it into the images too much. Let me know if that's not the case.
How to use it: First we have the core trigger baked into the Locon.
DominatrixA - Main trigger word.
Then basically anything that you might find entertaining to try out. Clothing/looks/etc. I like whips, skirts, leotard, evil grin, etc. But it's all up to you. And whips notoriously take a lot of tries in SD.
Extra, Extra!: Should be well trained and usable in most models. Images shown for example.
Picture Descriptions:
1-2: AnythingV3 using just this Lora with simpler prompts.
3: AnythingV3 combo'd with my released Amiri (Iruma-Kun) Lora and my in-progress Stepped On Locon.
4: AnythingV3 combo'd with my released Rozalin (Disgaea 5) Lora.
5: AnythingV3 combo'd with my released Ghislaine (Mushoku Tensei) Lora.
6: AnythingV3 combo'd with my released Catherine (Catherine: Full Body) Lora
7: AnythingV3 combo'd with my in progress Hourglass Locon.
8: AnythingV3 combo'd with my in progress Demonic Transformation Locon.
9-10: AbyssOrange with just this Lora.
11: RevAnimated using just this Lora.
How was it trained?
It was trained on animefull_final with 32 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. (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 and Tohru from Dragon Maid, 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, Harem Outfits, 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.
DominatrixA
If you create any good images using this LoRA, please consider sharing them by leaving a review. Thank you!
For people who do not use LyCORIS, I still provide a 2.0 version of LoRA, which has a different performance.
This version includes real beach volleyball athletes, Sports_bikini to trigger.
The beach volleyball court settings are Outdoor, Beach and Volleyball_net, accessories include Sunglasses, Eyewear_on_head, Cap (or visor cap)
For indoor volleyball players, Volleyball_uniform, Indoor_stadium to trigger, accessories include elbow pad, knee pads
The training data has changed a lot, so there may be a significant difference compared to the old version.
This LoRA is mainly trained on Asian volleyball athletes and may not be suitable for generating beach volleyball images.
Volleyball uniform and Indoor stadium to trigger
If unwanted volleyball objects keep appearing, try using Sportswear instead of volleyball uniform.
Basketball objects or actions may sometimes appear and affects the image. Consider putting them in the negative prompts.
In some checkpoints, using "realistic" can make girls look TALLER (which is important).
Sometimes it may be difficult to generate multiple girls, you can try using "group selfie", "girl sandwich", or "looking at another".
The volleyball actions are still difficult to generate. You can try using "jumping" or "spiking".
volleyball uniformsports bikiniholding volleyball
Now you can omit glasses tag to not generate her glasses
Her eyes are blurry :/
reiglasses
This one was very tricky since I didn't have a lot of data to work with. Outputs may be unstable, do not use "multiple tails" as it will try to give her 9 tails instead of 3!
As always, check the preview pictures for example prompts!
I used cp decomposition to reduce the model size.
You may need to update your locon extension to fully utilise this model!!!
This model may not be compatible with the AddNet plugin.
krooskeen glinthalloweenorigenchina dress, closed eyes
Made using the Kohya LoRA Dreambooth method https://github.com/linaqruf/kohya-trainer
Trained on AnyLoRA. I've had decent results on AOM and anypastel so far.
Doesn't spawn him in perfectly, but close enough.
A couple images I trained it on had Viktor in them, so I've had Flik with a Viktor arm appear once. 😂
0.7~1.0 weight depending on style you want
I use Euler a, 32 steps, Clip skip 2, Hires fix, AnimeSharp, denoise .55 ... but use whatever you like.
Descriptive tags: Cape, boots, blue eyes, headband, blonde bangs, brown hair, etc
flik
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。kira mimi
类似手帐 / 记事本 / 图鉴的风格LoHA，建议搭配二次元checkpoint使用。
训练使用：v1.5-pruned-bakedVAE，分辨率1280*960（4:3画幅）。
A LoHA that can be used to create planners, notebooks, or picture books. It is recommended to use it on anime checkpoint. The model used for training is v1.5-pruned-bakedVAE with a resolution of 1280*960 (4:3 aspect ratio).
在prompt中添加下列提示词（🔸必须 | 🔹可选）：
The prompts（🔸mandatory kinda | 🔹optional）：
🔸HoarfrostExplorationDiary
🔸character profile
🔸LoRA引用 / <lora:xxxxx>
🔹english text
🔹description
🔹category book
可用english_text 来增强鬼画符的效果
如果你想复现示例图的效果，必须使用这个插件
You must use LoRA Block Weight extension to achieve the result in the example images.
插件预设我是用的是：Download the LBW preset I use from here
请在负面提示词中加入nsfw，因为训练图片全部包含少儿不宜内容，将导致出图的效果非常糟糕。如果你需要ai的鬼画符，请勿添加text，watermark等提示词。
示例图片使用：Dark Sushi Mix 大颗寿司Mix
建议基础分辨率与训练图像保持一致或更高，低分辨率未经过测试不做保证。
Please add "nsfw" in negative prompts, as all the training images contain very inappropriate contents which will result in very poor output of the generated images (dont ask what they are, not gonna tell you cus that's not the purpose of this model). If you need AI-generated nonsensical text, please do not add "text, watermark" to your negative prompts.
Example image using Dark Sushi Mix 大颗寿司Mix. It is recommended to use the same or higher basic resolution as the training images, otherwise I cannot guarantee the quality of your gens.
SEE DESCRIPTION PLEASE :)
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！！！
please download my samples to get the prompt in webui, for some reason, it did not show up on Civitai site!!
For the first 100 download，please redownload the right file again before you make a comment....
Hires fix is highly recommended!
推荐一定要高清修复！
这个loha可以分解或者排列物品，由于我训练专注点的问题，目前针对电子产品，机械产品有比较好的结构感，对于食物，衣服等物品，可以拆，但是效果一般。使用前请阅读Lycoris的使用说明，不要搞错了，不用通过普通的lora插件调用。推荐使用模型为：
this loha can disassemble the objects, and lay it out in 2D, because I focused on electric parts and mecha parts, it works better for these catalogs, but still it can be run on food, you may need to try to get the good results.
recommended models:
rev animated --科幻效果出众，结构一般good for scif!!! but not go for structure.
realistic vision 2/0 --排列极度规整，强迫症大爱, very well arranged lay-out!!!
Perfect world --很平衡 balanced
你可以发现更多好玩的模型并告诉我，我会测试！please explore more models and let me know, I will try it!!!
如何使用 how to use:
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>
根据不同的模型，建议使用权重为0.6-0.9，但是不要使用1,基本上会爆炸。
使用结构为：
disassemble\(ttp\)作为触发词，<lora:loraname:0.7>作为调用词，中间放入你想要拆开的物品就行了。使用很简单，物品描述尽量使用自然语言。
no humans一定需要使用！！！
no humans must been in prompts!!!
simple white background 建议使用！！
simple white background is recommended!
use 0.6-0.9 weight based on different SD models, but don't use 1
disassemble\(ttp\) to trigger，<lora:loraname:0.7> to use the lycoris, and put down the object you want to disassemble, please use nature language to describe the object.
disassemble\(ttp\)no humanssimple white background
「この姿は……ああ、そういう事なのですね。最早こうなれば、我が身に流れる鬼の血を厭うのは、今日この時を以てやめましょう。巴は、持てる力の全てを以て戦います」
CFG Scale: 5.5 - 7
Weight: 0.75 - 1
Recommended prompts:
For armored dress: tomoe gozen \(fate\), armor, japanese armor, long hair, red eyes, japanese clothes, hair between eyes, horns, oni horns, headband, kusazuri, red gloves, white hair, breasts, very long hair, hair bow, kote, sideboob, smile, ribbon, sleeveless, shoulder armor, detached sleeves
For swimsuit: tomoe gozen \(fate\), tomoe gozen \(swimsuit saber\) \(fate\), very long hair, ponytail, blue hair bow, breasts, hair between eyes, red eyes, bangs, looking at viewer, thighs, blush, grey hair, thigh strap, bare shoulders, holding energy sword, multicolored striped one-piece highleg swimsuit
For white kimono: tomoe gozen \(fate\), 1girl, solo, japanese clothes, red eyes, hair between eyes, looking at viewer, red hair ribbon, grey hair, very long hair, white short kimono, sash, ponytail, detached sleeves, obi, red fingerless gloves, tomoe \(symbol\), sleeveless, turtleneck, blue hakama pants, mitsudomoe \(shape\), headband, oni horns, bangs, black undershirt, sode
tomoe gozen \(fate\)
We will comply with the ANYCOLOR secondary creation guidelines.
https://www.anycolor.co.jp/guidelines/
It seems that no particular intention is indicated. I pledge to create and publish works that respect the spirit of ANYCOLOR content.
特に個別の意向が示されていないと思われます。ANYCOLORコンテンツの精神を尊重した作品を制作、公表していく事を誓います。suou sango
LoHa for maru
Recommanded prompts:
`grey hoodie, grey pants, `
char_maru_loha
LoHa for rk sister
Recommanded prompts:
`vest, blue vest, blue skirt, white apron, waist apron`
You may need https://github.com/hnmr293/sd-webui-cutoff to get best character style
char_rk_loha
We will comply with the ANYCOLOR secondary creation guidelines.
https://www.anycolor.co.jp/guidelines/
It seems that no particular intention is indicated. I pledge to create and publish works that respect the spirit of ANYCOLOR content.
特に個別の意向が示されていないと思われます。ANYCOLORコンテンツの精神を尊重した作品を制作、公表していく事を誓います。hoshikawa sara