LoCon

Use these keywords to activate "Kyoto Animation screencap" "Anime screencap" recommended weight: 0.5~0.7

Suitable Model: anything, anylora, dpepmkm, detailed project v4

HiRes Fix: Latent - AnimeSharp - ESRGAN

LoHA

Use this word to activate "kyoto style", in an another note it may give bad results because it was under trained, and had a bad config. The LoCon may give you better results.

Recommended weights : 0.4~0.7(1 works too)

Hires Fix Upscaler: (?)

Suitable Model: (?)

这个味道，是说谎的味道！

This taste is the taste of lying!

它有一点过拟合，请酌情调整

It is a little overfitting, please adjust accordingly

触发词二选一写一个就行

Just choose one of the two trigger words

可以写1girl,1boy也可以写2girls

You can write 1girl, 1boy or 2girls

要同时控制两个角色的表情不是特别现实，如果你要求较高最好使用局部重绘

It is not very realistic to control the expressions of two characters at the same time. If you have higher requirements, it is best to use inpaint

licking face和licking ear其实分的不是太清，还是随缘吧

In fact, licking face and licking ear can't be strictly distinguished, let's just let it happen

👑 Sheila (Dungeons And Dragons) LyCORIS👑

🔧Model base: sd1.5

_____________

📝🌟 Trigger: SheilaDDQuiron character, <lyco:quiron_SheilaDD_Lycoris:1.0>

_____________

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

📝 Denoising strength: 0.30 to 0.8

______________

🗒️💡Sample:

SheilaDDQuiron character, cape, orange hair , thigh boots, blue eyes, breasts, brown footwear, freckles, purple cape, hood, cloack, short dress, retro artstyle, <lyco:quiron_SheilaDD_Lycoris:0.9>

______________

🚀 This LORA likes:

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

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

bad-hands-5, bad_prompt,

💡Sample steps: 20 to 45

💡CFG Scale: 5.5 to 13

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 LyCORIS has been trained after carefully selecting 73 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.

Trained on nearly 100 images, please do not use commercially and support the work of the original mangaka

It's a experimental work,which purpose is to simulate the effect of light scenery.

This is a LoCon model that trained by 100+ img,and it's the noise version, I dropout some elements to improve generalization.

This model can achieve more detailed shadow segmentation effects and the purple reflective light after the rain.

This will make the lighting effect more similar to Single-lens reflex photo.

weight 1.0 maybe generates better img,trigger is glimmer.

A model for adding a bit of hell to your pictures. Fire, skulls and atmosphere.

Thanks to konyconi for this nice guide: https://civitai.com/models/52697/tutorial-konyconi-style-lora

I'm still new to creating models, but I love it. If you like what I'm creating feel free to buy me a coffee. Good coffee is the best:

https://www.buymeacoffee.com/donmischo

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

I had to delete the metadata from some pictures I will upload new pictures with metadata in the near future.

Next on the chopping block is another character i totally forgot but remembered after collecting a dataset and saw her in one of the pictures.

I didn't finish the Anime i dropped it after a certain point because it became unbearable.

Keyword is Chaika Bogdan works on 1.0 is not very happy about outfit changes but i guess it can be done but it will always look similar to her default if the outfit contains similar parts to her default outfit.

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

Have fun generating.

anime model with 0.5-0.7 weight

A model featuring the spectral colors of light.

Thanks to konyconi for this nice guide: https://civitai.com/models/52697/tutorial-konyconi-style-lora

I'm still new to creating models, but I love it. If you like what I'm creating feel free to buy me a coffee. Good coffee is the best:

https://www.buymeacoffee.com/donmischo

一个适配各种类型底模的lora模型，二次元，2.5,3d，真实类型的底模都有不同的表现，

服饰细腻逼真，附送两条小蛟随机出现

This LoRa model that is compatible with various types of base models, including 2D, 2.5D, 3D, and realistic types, each with different representations. The clothing is delicate and realistic, and two small dragons are included as bonus, randomly appearing.

参考prompt

xhuoguo, 1girl, scroll, solo, moon, dress, black hair, holding, long hair, jewelry, long sleeves<lyco:XhuoguoV1:1>

Negative prompt: bad-artist bad-hands-5 easynegative_2 修手脚NG_DeepNegative_V1_75T

Steps: 25, Sampler: Euler a, CFG scale: 7.5, Seed: 460887228, Size: 768x960, Model hash: 969673ad74, Model: darkSushiMixMix_colorful, Denoising strength: 0.5, Clip skip: 2, ENSD: 31337, Hires upscale: 2, Hires steps: 13, Hires upscaler: 4x-AnimeSharp, Version: v1.3.0

Welcome to Beautiful Pornstar Series Vol. 2! Let the beauty continues

--

If you love my work, you can buy me a coffee to help me stay awake and cope with life to create more lora and stuffs : ko-fi.com/tauron

Check vol.1 --> Tau's Beautiful Pornstar Vol. 1 [Fin] - 01. Gloria Sol | Stable Diffusion LyCORIS | Civitai

Best to use with my mix: Tauron Hybrid Mix - TauHybrid_Anime_Final | Stable Diffusion Checkpoint | Civitai

--

DISCLAIMER:

I'm doing this for fun and not for commercial motive, My main purpose is to compose a fictional character using AI with the beauty of all persons above, please support them if you love their works. i do not support any indecent images generated of all persons in this model, I do not support selling generated images of persons in this model. please refrain to what they have been posting online.

All persons in this models are 21+ and not a minor, please DO NOT post explicit nudity, suggestive content, or pornographic content online using this model. Refer to CivitAi TOS for more details.

===

Request or Suggestion Rule:

1. No request of minor!

2. The requested should have public data (no private)

3. Should have more than 30 good quality images

4. Since all requests or suggestion are free, I will still need to like your request, otherwise its a work not a hobby for me.

5. Be a decent human being and leave a review if your requests is up It takes you only 5 mins while it takes me hours, electricity, and efforts to do your requests.

6. If you don't get what you want, do not review bomb, there could be other creators models or lora that can get better results than mine, use theirs instead, and leave a good review on them too, support any other creators for their hardworks!

NOTE : I will keep updating more actresses in versions update

===

Usage Guide

--

A. Lora Weight

• 0.1 ~ 0.4 -- is to combine multiple faces or features, or if you experience overbaking

• 0.5 ~ 0.7 -- is a balanced weight to get still accurate feature but with more flexiblity

• 0.8 ~ 1.0 -- is to create accurate representation of the features.

B. CFG Scale

• Lower CFG Scale means AI gets more creative and less overbaking problems.

• Higher CFG Scale means results get very accurate with training sets and more prone to overbaking problems.

• Dynamic CFG Threshold, using this method allows you to bump up quality and achieve photorealistic easily, but with lycoris i found out recently that this method actually lower success rate, so only use when you are composing with a Lora / model that works fine with this method.

C. Sampling Steps, High Res Fix & Upscaling

• I like to use sampling steps at 50, with high res step at 20, or 1/2 of sampling steps.

• I find that 2M Karras works better and faster than SDE Karras. with ERSGAN 4x+ method + ERSGAN 4x for Upscaling. This method actually gives quite good result without being too sharp or too plasticky

• Upscaling - GPFGAN @0.25, Codeformer @0.3 & Codeformer Weight @0.15 seems to yield superior results to me.

--

Combining with Attribute LoRa / LyCoris

You may need to do your own testing, but using character at weight -0.2 below attribute lora weight yields superior results, if for some reason one features persists not showing or overbake, you may want to lower the weight of the overbaked feature Lora, and then use emphasis () to boost the specific attribute you want.

DDetailer / ADetailer Script

If subject face is small / far away use: DDetailer Script with bbox anime face with default settings except denoiser at 0.2-0.3. You can combine this LoRa with a lot of other Style / Attire / Pose / Acts LoRa, Also works well with character LyCoris.

How to install this script? I kinda forget how because its a bit complicated beacuse you need to install stuff from venv. but a quick google search will land you somewhere in tutorial page.

Enjoy.

"I like my beer like I like my women -- stout and bitter!"

- Every World of Warcraft dwarf ever

Makes strapping dwarven lads and lasses -- at least, the body types anyway. It's up to you to put them in the right setting and clothe them (which can be difficult, as this LoCon is weirdly horny, even for one of mine). If you prefer more practically dressed dwarves, I recommend pairing this with Envy Cold Shower.

Trigger words are optional.

👑 DAP double anal penetration LyCORIS👑 v2

🔧Model base: sd1.5

_____________

📝🌟 Trigger: (DAPQuiron pose), <lyco:quiron_DAP_v2Lycoris:1.0>, hetero, double penetration, 2penis in 1anus, double anal, multiple boys, penis, anal, threesome,

_____________

📝 Variation: <lyco:quiron_DAP_v2Lycoris:Y>, Y=0.7 to 1.0

📝 Denoising strength: 0.30 to 0.8

______________

🗒️💡Sample:

(best quality:1.33), (masterpiece:1.42), (detailed:1.15), (DAPQuiron pose), hetero, double penetration, 2penis in 1anus, double anal, multiple boys, penis, anal, threesome, , <lyco:quiron_DAP_v2Lycoris:1.0>

______________

🚀 This LORA likes:

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

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

bad-hands-5, bad_prompt,

💡Sample steps: 20 to 45

💡CFG Scale: 5.5 to 13

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 lora was created to incorporate the characteristics of the character kousaka_honoka from the love_live series and the art style present in the series at the same time. recommend using with anime style models.

It's an experimental LoHa model trained with HD dataset& noise,mainly red theme dataset from img generated with NijiV5.

This model can generate ornate decorations with a shiny finish, including East Asian clothing and architectural backgrounds, and this name is a description of tone of color, trigger is sinsya.

weight 1.0 maybe generates better imgs.

example prompts: sinsya, hair ornament, red eyes, hair flower, lantern, black hair, paper lantern, looking at viewer, bangs, floral print, red flower, red kimono, 1girl, wide sleeves, east asian architecture, long sleeves, upper body, outdoors, tassel

This LyCORIS has been trained after carefully selecting 92 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.

Fucked silly after sex LoCon

LoRA request queue: https://docs.google.com/spreadsheets/d/1DXjs-96citoEa4NPWWxm4o92kQyrJpgdXQGWQg65oiM/edit?usp=sharing

This model was trained using images on the NAI model. All of them were nsfw duh. I used a LoCon this time because I wanted to see how well they work for this type of thing and the results were fine. Don't expect perfect results on their own, some post processing is required.

Tested by itself and in combination with other character LoRAs. The results can look a bit weird so I recommend using either hires fix or inpainting on the generations.

I got the best results with a weight around 0.7.

Trigger words are fucked silly, ahegao, cum in pussy.

Example images were generated using AnyHentai on Euler A with 50 steps and then hires fix. on 0.5 denoising strength.

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

So i was training some Pokemon models and they kind of didn't come out as i wanted to so I needed some new inspiration.

I haven't really played Princess Connect I only watched some of the episodes from the Anime but there are a lot of cute character present and they are presented very well

So the model this time is Muimi from Princess Connect. keyword is just her first name as well. Gets her default outfit right most of the time if you want to changer her outfit i would recommend changing the strength to something below 1.0 and if it's not accurate enough for your taste raise it to above 1.0 but I think 1.3 is max for this model.

If you like it leave a comment and a like and if you are really generous take some time to review it that would be appreciated.

Have fun generating.

👑 Cheetara LyCORIS👑

Cheetara from Thundercats series

🔧Model base: sd1.5

_____________

📝🌟 Trigger: (CheetaraQuiron character), <lyco:quiron_Cheetara_v1:1.0>, retro artstyle, cartoon, facepaint, skintight bodysuit, makeup, leotard, muscle body,

_____________

📝 Variation: <lyco:quiron_Cheetara_v1:Y>, Y=0.7 to 1.0

📝 Denoising strength: 0.30 to 0.8

______________

🗒️💡Sample:

(best quality:1.33), (masterpiece:1.42), (detailed:1.15), (cartoon:1.5), facepaint, skintight (bodysuit:1.2), makeup, floating hair, leotard,retro artstyle, dithering, day,photoshoot of amazing the (CheetaraQuiron character), muscle body, muscle legs, abs, Standing in the doorway pose, cinematic, ( sidelighting, finely detailed beautiful eyes: 1.2), hdr , exaggerated features, A vast archaeological site located in the south region of Italy that was buried by meters of ash and pumice after a catastrophic eruption, new weird fantasy, <lyco:quiron_Cheetara_v1:1.0>

______________

🚀 This LORA likes:

(best quality:1.35), (masterpiece:1.45), (detailed:1.15), (cartoon:1.5),

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

bad-hands-5, bad_prompt,

💡Sample steps: 20 to 45

💡CFG Scale: 5.0 to 11.5

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 )☕🌟

触发词split，左右差分的效果，一般用960方图或者宽度略小于高度。

通过服装描述+nsfw可以实现表里差分，如果不加nsfw，也会得到有些微妙不同的两张图，因为是很久之前炼的了，存在画风影响。

配合角色lora可以实现角色差分，需要针对lora的不同调整不同权重，一般要使split权重大于角色lora，补充角色失去的特征应该使用增加tag描述而不是增加lora权重。

AI可以在同一张图中保持角色同一性，差分叠图相似度一般可以达到百分之九十以上

The following is from the machine flip:“Split” trigger word, the effect of left-right difference, generally using 960 square map or width slightly less than height.

Through clothing description + nsfw can achieve table and inside difference. If nsfw is not added, two pictures with subtle differences will also be obtained. Because it was refined a long time ago, there is a style influence.

With the role of Lora, the role difference can be achieved. Different weights need to be adjusted for different Lora. Generally, the weight of split should be greater than that of Lora. To supplement the lost features of the role, tag description should be added instead of increasing Lora weight.

AI can maintain the identity of the character in the same picture. The similarity of differential superimposed images can generally reach more than 90%.