Trained on NAI with 34 pictures.
Best result with weight between : 0.8-1.

Prompt activator : impmon
Other prompt : digimon \(creature\), green eyes, no humans, tail, gloves, bandana, neckerchief, claws, standing

Disclaimer : It can do NSFW. It was trained with 5 NSFW pictures in the dataset.

Commissioned by unclemark24 on fiverr

Reviews are really appreciated, i love to see the community use my work, that's why I share it.
If you like my work, you can tip me here.

Got a specific request ? I'm open for commission on my fiverr gig *! If you provide enough data, OCs are accepted

*Any paid request will not be presented on this page, unless you give me permission to.

Please consider to support me by buying me some coffee so I can make a new LoRA faster. I do open commissions there too if you want to make your own custom LoRA: My BMAC page

-> Sumin V2: Here

Trigger word: staycsumin

Best checkpoints/models to use:

Realistic: VisionGen, ChillOutMix, ArtEros, Snapdd00, Henrealmix

Fanart/painting style: Dreamshaper, LucidMix, SunshineMix, Majicmix

Use it wisely. I don't responsible for anything you generated with this LoRa.

Join KPOP Diffusion Discord: https://discord.gg/NrBDMX79Da

Trained on NAI with 53 pictures.
Best result with weight between : 0.8-1.

Prompt activator : frieza
Other prompt : male focus, 1boy, red eyes, tail, colored skin

Disclaimer : It can do NSFW. It was trained with 5 NSFW pictures in the dataset.

Commissioned by unclemark24 on fiverr

Reviews are really appreciated, i love to see the community use my work, that's why I share it.
If you like my work, you can tip me here.

Got a specific request ? I'm open for commission on my fiverr gig *! If you provide enough data, OCs are accepted

*Any paid request will not be presented on this page, unless you give me permission to.

Ms. Fortune from Skullgirls,

First of all, thanks to holostrawberry's guide to make it.

Helpful prompts: fingerless gloves, short hair, bob cut, cat ears, pouch, cat tail, claws, blue crop top, underboob, belt pouch, collar, neck bell, blunt bangs, bare shoulders.

Personal settings/ recommend:

Weight: 0.6 - 1

CFG scale: 7 - 10

Sampling Steps: 20 - 40

i'll try to make other skullgirls models.

A Lora of Nanu from Pokemon Sun and Moon.

Please leave a review and/or comment.

other characters from anime:

Astarotte Ygvar

Asuha Touhara

Naoya Touhara

Ingrid Sorveig Sorgrims

Judith Snorrevik

Griselda Reginhard

Elfreda Mirjasdottir

Cuthfleda

Olaf Frismar

Elika Drakul Draupnils

Lucca Austri

Unnbjorg Signar

Mistrune Asgrim

Mercelida Ygvar

Ursula Sumarlidi

Isold

Sigurd Sveinnsson Svarthaed

Isadora Finnsdottir

Porhelga Svarthaed

Backgrounds

Dragon

Fii

Enja Níuhali

Teacher

Atli Reginhard

Miina-sensei

Naoya Touhara_trap

Lama

Works fine with all sd 1.5 models.

strength 0.6-0.8, hiresfix or img2img for best results(it's works for every LoRa).

Train models isn't easy, crypto donations on some coffee are welcome:

Donate

boosty

Discord: here

Disclaimer: she is a conversion from 3D asset to safetensor file, don't represent a real human, any likeness is purely coincidental and no, she is not a kpop artist or a minor.

A Lora of Alexa from Pokemon X and Y.

Please leave a review and/or comment.

Trained on multiple datasets of Mercedes EV gallery images.

A Lora of Shauna from Pokemon X and Y.

Please leave a review and/or comment.

Emma Myers

Use <lora:ememyers-20:0.7>, ememyers.

https://www.buymeacoffee.com/guluarte contact me at rodo@guluarte.com if you need a custom LoRa.

Official version released! A simple LoRA that provides beautiful realistic faces without having to use a whole bunch of random TIs like ulzang.

Models used:

• https://civitai.com/models/20865/versamix

• https://civitai.com/models/22922/lyriel

• https://civitai.com/models/10028/neverending-dream-ned

Embeddings used:

• https://civitai.com/models/23178/badpictures

Weighting: low weighting (0.4-0.6) works the best, higher strengths might reduce image quality: Latest version fixes this.

Created by GeomanticArts and please consider supporting the trainer at geoloras.com

The most helpful most adorable little doctor from Honkai Star Rail, Bailu. Got her as my first 5* before I even left the station. Little did I know this would make the entire game a cakewalk.

Example images all made with AOM2-7thV3_C_40 at weight 1

'Bailu (Honkai Star Rail), chinese clothes' - Example prompt for the normal outfit. Add 'tail' if you wish. Roughly gets the scaley tail, but like with every other tail I've ever seen the placement is entirely random.

LoRA metadata has all the tags used.

My (nsfw) Twitter

Trained on NAI.

Trained on NAI with 53 pictures.
Best result with weight between : 0.8-1.

Prompt activator : female titan
Other prompt : blonde hair, short hair, blue eyes, giantess, muscular, nude, breasts, scar, hair between eyes, abs, teeth, scar, fighting pose, flexing biceps

Commissioned by yinyama3d on fiverr

Reviews are really appreciated, i love to see the community use my work, that's why I share it.
If you like my work, you can tip me here.

Got a specific request ? I'm open for commission on my fiverr gig *! If you provide enough data, OCs are accepted

*Any paid request will not be presented on this page, unless you give me permission to.

LoRA of Serri from Atelier Ryza,linkage between Azur Lane,

Weight 0.8~1.0 ,and you can ADJUST prompt to reductive character

TRIGGER:original outfit

you may improve by prompts such as pale skin, heterochromia,

have funミ(・・)ミ

Please consider to support me by buying me some coffee so I can make a new LoRA faster. I do open commissions there too if you want to make your own custom LoRA: My BMAC page

Sihyeon V2: Here

Trigger word: egsihyeon

Best checkpoints/models to use:

Realistic: VisionGen, ChillOutMix, ArtEros, Snapdd00, Henrealmix

Fanart/painting style: Dreamshaper, LucidMix, SunshineMix, Majicmix

Use it wisely. I don't responsible for anything you generated with this LoRa.

Join KPOP Diffusion Discord: https://discord.gg/NrBDMX79Da

Shizuku Yaegashi 八重樫雫 | Arifureta ありふれた職業で世界最強

https://www.pixiv.net/users/86166786

Prompt:

地点：(day:1.7), in front of a mountain range with a wooden cabin in the background,blue_sky,
动作：sitting at attention,sitting on couch,
服饰：white_black_shirt,cleavage_cutout, clothing_cutout,Black_Long_pants,
角色：<lora:Shizuku_Yaegashi-V1:0.7>,sleeveless_shirt,animal_ears,
头发：bangs, black_hair,red_eyes, high ponytail, hair_between_eyes, hair_ornament,
角色鎖定：
1 girl, Manga,20yo,mature female,Beautiful Finger,Beautiful long legs,Beautiful body,Beautiful Nose,Beautiful character design, perfect eyes, perfect face,
眼神表情：
looking at viewer, (innocent_big_eyes:1.0),(expressionless:1.3),
畫質:
official art,extremely detailed CG unity 8k wallpaper, perfect lighting,Colorful, Bright_Front_face_Lighting,
(masterpiece:1.0),(best_quality:1.0), ultra high res,4K,ultra-detailed,
photography, 8K, HDR, highres, absurdres:1.2, Kodak portra 400, film grain, blurry background, bokeh:1.2, lens flare, (vibrant_color:1.2)
身材:
(Beautiful,large_Breasts:1.4), (beautiful_face:1.5),(narrow_waist),

Negative prompt:

EasyNegative, bad-artist-anime, bad-hands-5, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry, out of focus, censorship, Missing vagina, Blurry faces, Blank faces, bad face, Ugly, extra ear, amputee, missing hands, missing arms, missing legs, Extra fingers, 6 fingers, Extra feet, Missing nipples, ghost, futanari, Extra legs, Extra hands, panties,pants, (painting by bad-artist-anime:0.9), (painting by bad-artist:0.9), text, error, blurry, jpeg artifacts, cropped, normal quality, artist name, (worst quality, low quality:1.4),

Steps: 27, Sampler: Euler a, CFG scale: 7,

Seed: 165133424, Size: 512x768,

Model hash: 3e9211917c, Model: yesmix_v16Original,

Denoising strength: 0.5, Hires upscale: 2,

Hires steps: 18, Hires upscaler: Latent

Aerith Gainsborough from Final Fantasy VII (Remake). Trained on NAI.

Tested at 0.8-1.0 strength.

Contains her standard outfit and her red dress. Trigger word is "aerith gainsborough" for both.

• Add "choker, cropped jacket, hair bow, bracelet, pink dress, brown boots" for her standard outfit.

• Add "very long hair, hair ribbons, hair flowers, strapless red dress, high heels" for her red dress.

I'm sort of running low on ideas, so let me know if you have any suggestions and I'll look into them. Thank you.

I tried to get this result without any LoRA but it seems almost impossible, this helps a lot even if the results are not always crystalline and flawless... Better than nothing :D

Cyberdimension Neptunia: 4 Goddesses Online Angel Outfit LoRA

This model was trained using 64 images of characters from the game, mainly black heart and purple heart, wearing their angel style outfit. It was trained on the NAI model so it should work with most anime based models. Some of the training images were NSFW so you might get that, but most of them weren't.

The model is quite strong so I recommend to not go above 0.7 weight, or the rest of the image might look weird. It was specifically trained on the outfit, and not the faces or poses, so make sure to describe those in your prompt to not get weird faces. It is not perfect so it might require some inpainting. Also since most of the images used in training were the same 2 characters it is biased towards their hair colors etc.

Trigger word is nepOutfit, with that you will mostly get the purple heart version. Add either navel or underwear to get the black heart version.

Example images were generated using AOM2 hard or Anything v4.5 with 20-50 steps.

This is my first experimental LoRA, I'm not fully satisfied with the raw results but with some work it can generate workable images. I noticed that most models are incapable of producing sexy characters that still wear long skirts. This LoRA is an attempt to combat that problem. I intended for it to be highly configurable through different tags which did not turn out as well as i had hoped. But the tags are:

• lpskirt: the base tag to generate long pencil skirts (always use this one)

• short_lpskirt: for "short" long pencil skirts (ends right above the knee)

• medium_lpskirt: for medium long pencil skirts (below knee)

• long_lpskirt: ends between knee and ankle

• longest_lpskirt: ankle length

• latex_lpskirt: latex material

• leather_lpskirt: leather material

• cotton_lpskirt: cotton material

• high_waist_lpskirt: for high waisted skirts

• hobble_lpskirt: for very tight skirts that look like they are impossible to walk in (the primary reason for me to make this model was to be able to produce these)

some additional tags that were used during training but I haven't properly tried for generation (no guarantee to have an effect):

• zipper_lpskirt: for skirt with a zipper

• laced_lpskirt: for skirt with laces

• flared_lpskirt: for a long pencil skirt that ends in a flared section

• side_slit_lpskirt: for skirts with a slit on the side

• front_slit_lpskirt: for skirts with a slit on the front

• back_slit_lpskirt: for skirts with a slit on the back

RECOMMENDED SETTINGS:

• use weight 0.5-0.75

• always use "lp_skirt"

• define a length (it still struggles with longest so if you want to force it anyway you can try something like "(hobble_lpskirt, longest_lpskirt, long_lpskirt:1.7)", you can also try adding the smaller sizes to the negative prompt)

• define a material like "latex_lpskirt", additionally you can add a description like "a woman wearing a long black latex pencil skirt"

• define extras like "high_waist_lpskirt"

• optionally add something like "(leggings,pants:1.1)" to negative prompt if it does not properly wrap legs in a skirt in the produced images

• CLICK GENERATE AND HOPE FOR THE BEST (use highresfix or multidiffusion for best results)

The sample images are definitely cherry picked and some of them had extensive fixes done to them through img2img

LoRa trained on 38 images of American model Grace E. Elizabeth. Gives better results with lower weights.

Kaori Shirasaki 白崎香織 | Arifureta ありふれた職業で世界最強

https://www.pixiv.net/users/86166786

Prompt:

地点：(day:1.7), in front of a mountain range with a wooden cabin in the background,blue_sky,
动作：sitting at attention,sitting on couch,
服饰：bare_shoulders,collarbone,((blue and yellow outfit)),white_hat,detached_sleeves, pleated skirt,
角色：<lora:Kaori_Shirasaki-V1:0.7>,crown,gloves, white_gloves,boots,Cross_necklace,
头发：blue_black_hair,brown_eyes,long_hair,bangs,
角色鎖定：
1 girl, Manga,20yo,mature female,Beautiful Finger,Beautiful long legs,Beautiful body,Beautiful Nose,Beautiful character design, perfect eyes, perfect face,
眼神表情：
looking at viewer, (innocent_big_eyes:1.0),(expressionless:1.3),
畫質:
official art,extremely detailed CG unity 8k wallpaper, perfect lighting,Colorful, Bright_Front_face_Lighting,
(masterpiece:1.0),(best_quality:1.0), ultra high res,4K,ultra-detailed,
photography, 8K, HDR, highres, absurdres:1.2, Kodak portra 400, film grain, blurry background, bokeh:1.2, lens flare, (vibrant_color:1.2)
身材:
(Beautiful,Medium_Breasts:1.2), (beautiful_face:1.5),(narrow_waist),

Negative prompt:

EasyNegative, bad-artist-anime, bad-hands-5, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry, out of focus, censorship, Missing vagina, Blurry faces, Blank faces, bad face, Ugly, extra ear, amputee, missing hands, missing arms, missing legs, Extra fingers, 6 fingers, Extra feet, Missing nipples, ghost, futanari, Extra legs, Extra hands, panties,pants, (painting by bad-artist-anime:0.9), (painting by bad-artist:0.9), text, error, blurry, jpeg artifacts, cropped, normal quality, artist name, (worst quality, low quality:1.4),

Steps: 27, Sampler: Euler a, CFG scale: 7,

Seed: 1387086258, Size: 512x768,

Model hash: 3e9211917c, Model: yesmix_v16Original,

Denoising strength: 0.5, Hires upscale: 2,

Hires steps: 18, Hires upscaler: Latent

tag:1girl,cape,mask

maybe:cloak,hood,hood up etc...

Use "torn clothes" to stabilize clothing when you don't have her wearing a cape

当你不让她穿着斗篷的时候，可以使用torn clothes来稳定服装

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

I'm sorry, I trained her to wear a mask, and at the same time trained her to hold a mask, but now as long as she uses the mask tag, she is 100% holding it... Maybe using a certain tag can make her face well covered, who knows...

服了，我训练了她带着面具，同时训练了她拿着面具，但是现在只要使用mask这个tag，她百分之百是拿着……或许使用某个tag可以让她好好的把脸遮挡起来，谁知道呢……

It is a little bit hard to get her pussy exposed fully due to the lack of nsfw data, so if you want to see it, just lower the strength of this lora to around 0.7 and add more weight to pussy related tags.

由于缺失nsfw数据要完全露出浦西有点难，想看的话就降低权重到0.7左右并加大浦西相关tag的权重。

Fidget out of the game dust: an elysian tail

Based on YiffyMix 2,1 trained on ~80 SFW/NSFW images

DO NOT USE IT WITH YiffyMix 2,1

The best result will be with YiffyMix 2

Also works poorly with anime models

Promt: start with a standard insert for YiffyMix: (uploaded on e621, (by Pino Daeni:0.7), (by Ruan Jia:0.7), by Skygracer, by Alayna Lemmer, by Carlo Galli Bibiena), ((fidget (elysian tail))), dust: an elysian tail, green eyes, membranous wings,

For more correct eyes, use looking at viewer

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

Your characters may have insufficient training data! Click here.

Weight: 1.0

Trigger + Appearance: lila, ahoge

Sample Outfit: purple sweater dress, thighhighs

Add purple hair and blunt bangs if necessary.

The results of your generations are dependent on the additional LoRAs, weights, and models you use, so it may not work or come out as consistent as my sample images. Other reasons may include me using xformers, token merging, and a modified DPM++ 2M Karras sampler.

📝Biography📝

(generation advice below) 👇

🌟Rebel Lynn🌟

was born as Olivia Lee on September 10, 1996, in Aurora, Colorado, USA. She grew up in a conservative family and had a relatively sheltered childhood. However, Rebel always had a wild side and a desire to explore her sexuality. Rebel started her career in the adult entertainment industry in 2014, at the age of 18. She quickly gained popularity for her youthful looks, petite figure, and enthusiastic performances. She has since starred in numerous adult films and has been nominated for several awards, including the AVN Award for Best New Starlet in 2016.

In addition to her work in traditional adult films, Rebel has also appeared in numerous erotic photo shoots and has performed in live shows at adult entertainment venues.

Outside of her work, Rebel enjoys spending time with her pets and practicing yoga. She is also an avid traveler and has visited many countries around the world. Currently, Rebel is still active in the adult entertainment industry and continues to produce new content. However, she has also expressed an interest in pursuing other creative endeavors in the future.

💡Generation Advice💡

🔧Prompt and Sampling🔧

• Most images have been generated with LORA weighted @ 1.

• Most samples done with CyberRealistic v2.1 with sampling steps ~40.

🚀Upscaling🚀

• Sometimes I just send it to Ultimate SD upscale after a quick render and run 2x at a scale of two.

• Ultimate SD upscale script used @ ~.15 - .4 denoising using 8x NMKD Faces or 4X UltraSharp redraw upscalers.

🗒️Side Notes🗒️

• The prompts continue to evolve. CyberRealistic is a reasonably flexible model for being realism focused. I still think they have trumped the SD 1.5 game. 👑

• Leave a review if you liked using this.

• Leave a comment if you are having issues getting good output, I'll try to respond.

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

Your characters may have insufficient training data! Click here.

Weight: 1.0

Trigger + Appearance: hera, demon girl, blue skin, demon horns

Sample Outfit: tiara, strapless dress, thighhighs, elbow gloves, jewelry, earrings, necklace, bare shoulders, cleavage

Add emphasis to blue skin and multicolored hair, red hair, orange hair to the prompt if necessary. This character is not trained on a specific outfit, evolution, etc.

The results of your generations are dependent on the additional LoRAs, weights, and models you use, so it may not work or come out as consistent as my sample images. Other reasons may include me using xformers, token merging, and a modified DPM++ 2M Karras sampler.

Add a ❤️ to receive future updates.

At least I tried :)

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

Your characters may have insufficient training data! Click here.

Weight: 1.0

Trigger + Appearance: haku, multicolored hair, double bun, twin braids, tail

Sample Outfit: purple sleeveless dress

This character is not trained on a specific outfit, evolution, etc.

The results of your generations are dependent on the additional LoRAs, weights, and models you use, so it may not work or come out as consistent as my sample images. Other reasons may include me using xformers, token merging, and a modified DPM++ 2M Karras sampler.

👑LORA: Anita Blond LORA👑

🔧Version: V1

Tribute to Pornstar Anita Blond

🌟🌟🌟If you like my work please support https://www.patreon.com/VisionsofAi 🌟🌟🌟

🔧Model base: AngrA_AnimFlex_v01 , AngrA_RealFlex_v01

📝🌟Trigger: quiron_AnitaBlond_v1, <lora:quiron_AnitaBlond_v1:1>

🗒️💡Sample prompt: Photo of (gorgeous quiron_AnitaBlond_v1, (blond woman:1.2)), <lora:quiron_AnitaBlond_v1:1>

🚀This LORA likes: (best quality:1.1), (masterpiece:1.1), (realistic:1.2), (detailed:1.1)

👇Negative Prompt: paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2),

lowres

Or / And

👇Negative embbeding: bad_prompt, bad-artist, bad-hands-5,

Hire. fix: ok

Restore faces: ok

The Disappearance of Haruhi Suzumiya (Kyoto Animation / Kyoani) Style LoRA

Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕

Should work fine at around weight 1 on AnyLoRA ckpt. Use kyoani haruhi style to increase fidelity. AnyLoRA also knows the character names of the main cast, so you can also use those with my base model.

Remember this is a style LoRA. To make characters accurately you need other networks too (but it can get pretty close with accurate descriptions and character names).

How to use LoRA's in auto1111:

• Update webui (use git pull like here or redownload it)

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

• Select your LoRA like in this video

• Make sure to change the weight (by default it's :1 which is usually too high)

It makes everything like diamonds.

Created as described in the tutorial of konyconi but with some own tweakings: https://civitai.com/models/52697/tutorial-konyconi-style-lora

If you want, support me here:
https://displate.com/dervlex?art=5d91f0dbbcb29

https://www.patreon.com/user?u=90661954

Nagashino Akari 長篠赤理 長篠あかり | App Game Girl 01 王牌銀行長 Ace Banker

https://www.pixiv.net/users/86166786

This lora also is a test

I have only less picture to train

Prompt:

地点：(Night:1.7), Cyberpunk_CityView, Before Window,Office,
动作：sitting at attention,sitting on couch,
服饰：,(black_jacket:1.4), pantyhose, pencil_skirt,(white_shirt),
角色：<lora:AppGameGirl01-V1:0.5>,office lady,<lora:odaNonStyleLORA_v2:0.5>, oda Non, <lora:aiueOkaStyle_v10:0.3>, <lora:saiminSeishidou:0.3>,
头发：black_hair,brown_eyes,long_hair,glasses,star_hair_ornament,
角色鎖定：
1 girl, Manga,20yo,mature female,Beautiful Finger,Beautiful long legs,Beautiful body,Beautiful Nose,Beautiful character design, perfect eyes, perfect face,
眼神表情：
looking at viewer, (innocent_big_eyes:1.0),(expressionless:1.3),
畫質:
official art,extremely detailed CG unity 8k wallpaper, perfect lighting,Colorful, Bright_Front_face_Lighting,
(masterpiece:1.0),(best_quality:1.0), ultra high res,4K,ultra-detailed,
photography, 8K, HDR, highres, absurdres:1.2, Kodak portra 400, film grain, blurry background, bokeh:1.2, lens flare, (vibrant_color:1.2)
身材:
(Beautiful,large_Breasts:1.4), (beautiful_face:1.5),(narrow_waist),

Negative prompt: EasyNegative, bad-artist-anime, bad-hands-5, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry, out of focus, censorship, Missing vagina, Blurry faces, Blank faces, bad face, Ugly, extra ear, amputee, missing hands, missing arms, missing legs, Extra fingers, 6 fingers, Extra feet, Missing nipples, ghost, futanari, Extra legs, Extra hands, panties,pants, (painting by bad-artist-anime:0.9), (painting by bad-artist:0.9), text, error, blurry, jpeg artifacts, cropped, normal quality, artist name, (worst quality, low quality:1.4),

Steps: 27, Sampler: Euler a, CFG scale: 7,

Seed: 939430355, Size: 512x768,

Model hash: 3e9211917c, Model: yesmix_v16Original,

Denoising strength: 0.5, Hires upscale: 2,

Hires steps: 18, Hires upscaler: R-ESRGAN 4x+ Anime6B

A LoRA for creating anal missionary images.

Vaginal version here: POV Missionary Vaginal + Creampie LoRA

If you feel like supporting my work, please consider visiting my Patreon to get access to more detailed instructions on how to get the most out of my models and have a say in what's up next: Link.

Update:

Wowie, I never would've thought I'd make it to a V6 on any of my LoRAs, but here we are.

I was using this one quite a bit myself, and it had an issue which kept annoying me more and more.

The issue was, that I was using too many anime images in the dataset, making the resulting images look less photo-realistic when compared to my other models.

So this version fixes that, by having many of the dataset images exchanged.

I also worked on making the creampie/cum look more realistic, which is something I will also do on some of my other older models.

Have fun!

Recommended LoRA Strength: 0.5-0.8

Based on UberRealisticPornMerge

If you like this, you may also like my Doggystyle Anal + Crempie LoRA.

tag:1girl,aura,necklace

or

tag:1girl,black dress,cleavage,wings

I did not train the two garments separately, so it seems that the probability of appearing in different models is not the same, please use the weights of aura and black dress to try to distinguish，It's interesting that the princess in the aura skirt often has a dark face, while the princess in the black skirt is full of light

两件服装我没有分别训练，所以似乎在不同模型中出现的几率不太一样，请使用aura和black dress的权重来尝试区分，很有趣的一点是，蓝裙子的公主经常黑着脸，黑色裙子的公主则打光充足（md感觉我经常使用机翻软件自己中国话都说不利索了……）

This is a LORA of the character Emilie de Rochefort from the Tekken series. This lora is trained on Lili's appearances in Tekken 7 and 8, although her Tekken 7 outfit training primarily consists of her Tekken 6 outfit. Multiple outfits are trained in this lora, including her Tekken 6 appearance, her Tekken 7 appearance, her tekken 8 appearance, her striped bikini, and santa bikini.

To prompt her Tekken 7 appearance, enter "<lora:Liliv1:strength>Emilie T7, white frilled dress, red ascot, fingerless gloves, white boots". To prompt her Tekken 8 appearance, enter "<lora:Liliv1:strength>Emilie T8, pink frilled dress, frilled ascot, fingerless gloves, lace-up boots". Lili is partially trained on her ingame appearances as well, to prompt her 3d model appearances, use "3d model".

This LORA is usually the best looking at 0.6 ~ 0.75 strength, and was trained on AnythingElsev4.5 at Clip Skip 2.

This is my first model of any kind. Following in the style of some of the embeddings for creating a repeatable character, I've created Elena Noexiste. I originally tried doing this as an embedding and didn't have a lot of success. Took some experimenting, but I've finally come up with a LoRA that works well, I think.

It depends on the model, but anywhere between 0.7 and 1.0 weight works. With some checkpoints the color gets messed up and lowering to 0.7 or 0.8 will usually fix it.

The face is actually a face that I commonly got out of the LOFI model but I wanted to reuse the face with different checkpoints, and that was the motivation for making it.

I've tried to provide examples with a small variety of checkpoints.

Hope others like it.

This is a LoRa with the style of 果坂青 // omao

The base model is Suzumehachi.

If you are the artist whose style is conveyed in part or fully by this LoRa, I suggest that you introduce this tool into your workflow. That way you can please your fans with even more art.

Tiffania Westwood ティファニア・ウエストウッド | Familiar of Zero ゼロの使い魔

https://www.pixiv.net/users/86166786

Prompt:

地点：(day:1.7), in front of a mountain range with a wooden cabin in the background,blue_sky,
动作：sitting at attention,sitting on couch,
服饰：Green_dress,bare_shoulders,
角色：<lora:Tiffania_Zero-V1:0.85>,elf,long_pointy_ears,
头发：blonde_hair,long_hair,blue_eyes,Bangs,
角色鎖定：
1 girl, Manga,16yo,mature female,Beautiful Finger,Beautiful long legs,Beautiful body,Beautiful Nose,Beautiful character design, perfect eyes, perfect face,
眼神表情：
looking at viewer, (innocent_big_eyes:1.0),(Light_smile:0.3),
畫質:
official art,extremely detailed CG unity 8k wallpaper, perfect lighting,Colorful, Bright_Front_face_Lighting,
(masterpiece:1.0),(best_quality:1.0), ultra high res,4K,ultra-detailed,
photography, 8K, HDR, highres, absurdres:1.2, Kodak portra 400, film grain, blurry background, bokeh:1.2, lens flare, (vibrant_color:1.2)
身材:
(Beautiful,large_Breasts:1.4), (beautiful_face:1.5),(narrow_waist),

Negative prompt: EasyNegative, bad-artist-anime, bad-hands-5, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry, out of focus, censorship, Missing vagina, Blurry faces, Blank faces, bad face, Ugly, extra ear, amputee, missing hands, missing arms, missing legs, Extra fingers, 6 fingers, Extra feet, Missing nipples, ghost, futanari, Extra legs, Extra hands, panties,pants, (painting by bad-artist-anime:0.9), (painting by bad-artist:0.9), text, error, blurry, jpeg artifacts, cropped, normal quality, artist name, (worst quality, low quality:1.4),

Steps: 27, Sampler: Euler a, CFG scale: 7,

Seed: 3768029600, Size: 512x768,

Model hash: 3e9211917c, Model: yesmix_v16Original,

Denoising strength: 0.5, Hires upscale: 2,

Hires steps: 18, Hires upscaler: Latent

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

This one worked out really well. Having few images with weird anatomy or textboxes means the world to the algorithm.

Mixplin is a pure NSFW artist and unsurprisingly this lora tends to minimize clothing if not otherwise specified. They make a lot of femboy and futanari content which I mostly left out of the dataset. So it kinda works if prompted but stays out otherwise.

A weight of 1 works when used by itself. For most character lora I used 0.75 which is pretty stable. The model doesn't need a keyword. Don't ask me how that happened. I don't have a clue.

While this is an nsfw lora, don't hesitate to try it with other prompts. It's always fun to see what kind of effect it has on other images. I have attached a comparison of a simple landscape prompt with and without the model.

Please leave a review if you enjoyed this Lora or have problems with it.

Tinker bell is a well-known Disney character from Peter Pan. To create the Lora, a meticulously selected and refined DataSet was used to achieve a versatile and flexible model. So that it adapts perfectly to styles and models. It also works in 3D. Use the keyword “(TinkerWaifu:1)” for greater precision, and I also recommend using the keywords “(single hair bun), (strapless green dress), (fairy wings) to invoke her characteristic outfits. If you want to change her outfit, I recommend lowering the weight of the Lora between “1.0 - 0.4” for greater flexibility, try it out and have fun. Remember to leave a Review with an image if you liked it and comment!! HAVE FUN :D

Don’t forget to check out my other Disney Series Loras on my profile. Currently Rapunzel, Snow White, Merida, Cinderella, Pocahontas, Fa Mulan, Elsa, Anna, Tiana and Alice in Wonderland, Ariel!! From the Princess Series ;D” Also u have The Bonus Series with: Nani Pelekai, Lifeguard (lilo & stitch). And Tinker bell, Jane Porter (Tarzan),

ADVICE!! “If you want a commission of something in particular, whether it’s a style or a character on request, contact me via email: jeanc.romero.ib@gmail.com.”

Please consider to support me by buying me some coffee so I can make a new LoRA faster. I do open commissions there too if you want to make your own custom LoRA: My BMAC page

V2: Here

Trigger word: minjukarina

Best checkpoints/models to use:

Realistic: VisionGen, ChillOutMix, ArtEros, Snapdd00, Henrealmix

Fanart/painting style: Dreamshaper, LucidMix, SunshineMix, Majicmix

Use it wisely. I don't responsible for anything you generated with this LoRa.

Join KPOP Diffusion Discord: https://discord.gg/NrBDMX79Da

Mushoku Tensei (Jobless Reincarnation) Anime style LoRA

Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕

Should work fine at around weight 1 on AnyLoRA ckpt. Use mushoku tensei style to increase fidelity, use anime coloring to force flatter colors.

Remember this is a style LoRA. To make characters accurately you need other networks too (but it can get pretty close with accurate descriptions).

How to use LoRA's in auto1111:

• Update webui (use git pull like here or redownload it)

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

• Select your LoRA like in this video

• Make sure to change the weight (by default it's :1 which is usually too high)

An emblematic character of the blade and soul mmorpg the lora was training with the perfect word model apply the lora at 0.6 weight for a beautiful detail that you enjoy

Trigger words: jinsoyun

follow me on Instagram @creativehotia

Uh-oh, your waifu has been captured by a huge snake! LoRA to add a snake coiling around your character. Rate and like if you enjoyed it!

Trigger: coils / / Optional tags: snake, tentacles

For visibility of body parts, just name them in your prompt, e.g.: breasts, collarbone, navel, legs

Additional info

I make these models for fun and for the challenge and release them for free for everyone to enjoy, for non-commercial use (see license). The one thing I ask of you is to provide rating and feedback! That helps me understand where I can improve and helps me stay motivated to produce more content!

I accept suggestions or requests here or on Civitai discord server.

You can also check my more polished images and upcoming models on my pixiv profile.

Would appreciate images, feedback, requests, reviews, and of course comments in the comments. Please check out my other models if you like this one.

A Lora for Triple Paizuri.

weights 0.8 - 1.

recommended tags: paizuri, cooperative_paizuri, 3girls

optional tags: breast_press, asymmetrical_docking, symmetrical_docking, deep_skin, breast_lift, breast_hold, breasts_squeezed_together (other paizuri related tags).

probably want to use smaller width/height, but it can work at 768x768.

using weight lower than 1 and smaller dimensions will probably cause double paizuri.

character Loras should work, but probably won't be able to get two consistent characters.

there were variations in the dataset, not sure if there is a specific way to trigger them.

Elisha Elfrieden エリシャ・エルフリーデン | Realist Hero Rebuilt the Kingdom 現実主義勇者の王国再建記

https://www.pixiv.net/users/86166786

Prompt:

地点：(Night:1.7), in dark castle,purple sky,Cherry blossom rain,
动作：sitting in throne, crossed legs, looking down at viewer, legs, barefoot,(FROM_BELOW),
服饰：bare_shoulders,blue dress,cleavage,frills,detached_sleeves,pearl_necklace,
角色：<lora:Elisha_Elfrieden-V1:0.7>,Queen,blue_bow, blue_ribbon,
头发：blonde_hair,long_hair,hair_between_eyes,brown_eyes,bangs,hair_ribbon,hair ornament,
角色鎖定：
1 girl, Manga,20yo,mature female,Beautiful Finger,Beautiful long legs,Beautiful body,Beautiful Nose,Beautiful character design, perfect eyes, perfect face,
眼神表情：
looking at viewer, (innocent_big_eyes:1.0),(expressionless:1.3),
畫質:
official art,extremely detailed CG unity 8k wallpaper, perfect lighting,Colorful, Bright_Front_face_Lighting,
(masterpiece:1.0),(best_quality:1.0), ultra high res,4K,ultra-detailed,
photography, 8K, HDR, highres, absurdres:1.2, Kodak portra 400, film grain, blurry background, bokeh:1.2, lens flare, (vibrant_color:1.2)
身材:
(Beautiful,large_Breasts:1.4), (beautiful_face:1.5),(narrow_waist),

Negative prompt:

EasyNegative, bad-artist-anime, bad-hands-5, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry, out of focus, censorship, Missing vagina, Blurry faces, Blank faces, bad face, Ugly, extra ear, amputee, missing hands, missing arms, missing legs, Extra fingers, 6 fingers, Extra feet, Missing nipples, ghost, futanari, Extra legs, Extra hands, panties,pants, (painting by bad-artist-anime:0.9), (painting by bad-artist:0.9), text, error, blurry, jpeg artifacts, cropped, normal quality, artist name, (worst quality, low quality:1.4),

Steps: 27, Sampler: Euler a, CFG scale: 7,

Seed: 3153207814, Size: 512x768,

Model hash: 3e9211917c,

Model: yesmix_v16Original,

Denoising strength: 0.5, Hires upscale: 2,

Hires steps: 18, Hires upscaler: Latent

Created according to the guide provided by konyconi, cheers to them for the awesome work.

The LoRa aims to produce an art style that resembles the technology of Terrans from Starcraft. The result is something a bit different, and is often only loosely terran-like, but it is a unique aesthetic nonetheless.

• v1.0 is my first decent attempt at LoRa training, it is more generically sci-fi, than specifically terran

• v2.0 includes Midjourney generations in the training set, and is closer to the inteded aesthetic

Feel free to use either one.

随便做做，虽然还不是很像，但是以我的能力只能做到这样了

A simple Lora meant to add hand gags to a subject. Generally pretty unreliable, but makes some good results possible. Made two versions of the model with different triggers. The first uses

hand gagged

and the second one uses

hand g4g

The latter is more reliable when the model used actually has a good concept of a gag, since it will otherwise try to insert those rather than a hand gag. Otherwise, the first model should work just fine.

Recommended weight: 0.8-1.0

Potentially useful tags:

multiple boys, grabbing from behind, covering mouth, hand over another's mouth

• Trigger：rebecca

• Default Outfit：brown eyes, short hair, long hair, ponytail, braid, pink hair, brown gloves, bikini armor, loincloth, green cape, armored boots

  If a helmet is worn, enter "helmet" in the prompt

• weight：0.7~0.9（Weight varies from model to model, so try different weights.）

• The models used were "AbyssOrangeMix2_sfw_pruned_fp16_with_VAE" and "animatrix_v20

A LORA model trained on Roger Parra.

To use place the words "rogerparra person" in the prompt.

Trained on 6210 steps.

Astraea アストレア | Heaven's Lost Property そらのおとしもの

https://www.pixiv.net/users/86166786

Prompt:

地点：(Night:1.7), Cyberpunk_CityView, Before Window,
动作：Standing at attention,
服饰：blue outfit,armor,pleated_skirt,metal_collar, midriff,chest_armor,shoulder armor, armored dress, armored boots, gloves,
角色：<lora:Astraea_Heaven-V1:0.7>,angel,angel wings, chained, cleavage, collar,broken_chain,navel,
头发：blonde_hair,LONG_HAIR,red eyes, hair_ornament,handcuffs,
角色鎖定：
1 girl, Manga,20yo,mature female,Beautiful Finger,Beautiful long legs,Beautiful body,Beautiful Nose,Beautiful character design, perfect eyes, perfect face,
眼神表情：
looking at viewer, (innocent_big_eyes:1.0),(expressionless:1.3),
畫質:
official art,extremely detailed CG unity 8k wallpaper, perfect lighting,Colorful, Bright_Front_face_Lighting,
(masterpiece:1.0),(best_quality:1.0), ultra high res,4K,ultra-detailed,
photography, 8K, HDR, highres, absurdres:1.2, Kodak portra 400, film grain, blurry background, bokeh:1.2, lens flare, (vibrant_color:1.2)
身材:
(Beautiful,large_Breasts:1.4), (beautiful_face:1.5),(narrow_waist),

Negative prompt: EasyNegative, bad-artist-anime, bad-hands-5, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry, out of focus, censorship, Missing vagina, Blurry faces, Blank faces, bad face, Ugly, extra ear, amputee, missing hands, missing arms, missing legs, Extra fingers, 6 fingers, Extra feet, Missing nipples, ghost, futanari, Extra legs, Extra hands, panties,pants, (painting by bad-artist-anime:0.9), (painting by bad-artist:0.9), text, error, blurry, jpeg artifacts, cropped, normal quality, artist name, (worst quality, low quality:1.4),

Steps: 27, Sampler: Euler a, CFG scale: 7,

Seed: 2180484616, Size: 512x768,

Model hash: 3e9211917c, Model: yesmix_v16Original,

Denoising strength: 0.5, Hires upscale: 2,

Hires steps: 18, Hires upscaler: Latent

Makino from One Piece LoRA

Use "green hair" as trigger word

Weight 0.7 - 0.9 for best generation.

Welcome to the Astral Express!~

General Info

I know there are already existing Himeko LoRA's on CIvitai but they did not exactly achieve what i was looking for so i trained my own. The big advantage of this LoRA is that you only need a single trigger word to generate quality images of her. It also allows for different styles and poses of her. This LoRA is also trained on the Aurora model from Luna (https://civitai.com/models/40199/aurora), the example images have been generated using that model, too.

Usage

The model has been trained using Kohya so you probably want to use it in the same way as you use other Kohya models. If you are Using A1111's Webui you want to move the file into the models>Lora directory. Make sure to use the corresponding trigger words to get the expected results. Also i recommend a LoRA weight of around 0.8.

LORA: El Chavo Del 8 LORA

Version: V1

Model base: AngrA_AnimFlex_v01 , AngrA_RealFlex_v01

Tribute to tv serie (el chavo del ocho)

Trigger: quiron_elchavodel8_v1, <lora:quiron_elchavodel8_v1:1>

Sample: quiron_elchavodel8_v1, a happy man, <lora:quiron_elchavodel8_v1:1>

This LORA likes: (best quality:1.1), (masterpiece:1.2), (realistic:1.2), (detailed:1.1),

Negative Prompt: paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2)

lowresOr / And

Negative embbeding: bad_prompt, bad-artist, bad-hands-5,

Hire. fix: ok

Restore faces: ok

Actress

the training was on a model - CyberRealistic 2.0.

I'm Render on - EndlessReality

• if you want to get speed, drive a sports car

• if you want to drive off-road, take an SUV

• if you want to hammer a nail, take a hammer

• it's the same here - if you want to get results, read the recommendations and follow them

I do not recommend using my LoRA with model RealisticVision

personally, I most often perform generation with parameters: DPM ++ 2M Karras, Sampling Steps 35, Denoising strength 0.35, CFG Scale 3.5-4.5

American actor, star of the series 'The Walking Dead'.

I hesitated for some time and decided to make a 40+ model. He is much more interesting and handsome at this age.

Handsome, charismatic, courageous.

Hibari from One Piece LoRA

Weight 0.6 - 0.75 for best generation.

"А она может сгенерить такую же кофточку, но с перламутровыми пуговицами?"

Моя 4ая lora, и кажется скоро за такие модельки меня забанит комитет по цензуре civitai. Посмотрим сколько превьюшек останется после модерации, делаем ставки...

Тренировал на deliberate-v2 https://civitai.com/models/4823?modelVersionId=15236

Для темного эффекта использовал lowra-v2 https://civitai.com/models/48139/lowra

Все превью сделаны на Realistic Vision V2.0 https://civitai.com/models/4201/realistic-vision-v20

А теперь к моим наблюдениям, демагогии, возможным проблемам и как их избежать:

1)Мои жалкие оправдания:

Мучился с моделькой я долго, с ней кстати та же проблемка что и с предыдущей lora, при генерациях вы так и будете смотреть на красный интерьер номера отеля "Атлантик". И эту чертову люстру! Но что с этим делать я говорил в описании к прошлой модели. Просто добавляйте больше описаний к локации. На самом деле такие вот недочеты есть в каждой lora, другое дело что если брать какую нибудь селебрити, то у нее миллион фотографий, с миллионом разных костюмов и причесок, в миллионе точек на земном шаре, под миллионом разных освещений итд итп. А вот с персонажем из фильма, особенно если он эпизодический то все гораздо сложнее, ведь датасет ну очень мал, поэтому все что вы можете это подбирать разные промпты, а теперь о них...

2)Промпты:

Это наверное самая важная вещь в stable diffusion. Если будет плохой промпт то будет и плохое изображение, независимо от того насколько качественная lora. Особенно это касается негативных промптов. Именно из-за того что я не мастер в промптах, пришлось убить пару дней чтобы найти лучшие промпты и негативы которые я только смог. Если вы такой же тупой пень как и я то тупо копируйте мои промпты и не парьтесь. Без них вы будете получать среднее качество а не те "шедевры" которые сверху. +Очень рекомендую использовать lowra-v2. (Кстати может красиво смотреться комбинации из нескольких lora с низкой силой, персонаж пускай другой, но стиль интересный)

3)Апскейл:

Про то как сделать конфетку из low res параши, я уже написал в предыдущей lora, но все же поделюсь еще парой наблюдений. Если вы генерите lowres (например 512x704) изображение человека в полный рост, то нейросеть в 80проц случаев сгенерит хреновое лицо, независимо от всего выше перечисленного. Хоть ты лопни, хоть ты тресни, но сгенерить хорошее лицо 100x100 пикселей, а то и ниже ну нереально (если кто то из вас шарит, то пишите свои советы). Именно поэтому даже после апскейла, лицо может быть немного деформировано. Поскольку нам нужен фотореализм, то тупо кидаем результат в инпейнт и дорисовываем личико. На превью инпейнт я использовал только в фото в полный рост, остальные фото, особенно closeup она генерит просто шикарно как по мне. И как по мне closeup портреты все таки лучше апскейлить hires fixом ESRGAN_4x с низким денойзом. А остальное я тупо кидал в img2img. Вроде всё сказал.

4)Нюдсы:

Простите пацаны, но нюдсы банят. Сами сделаете)). Увы только с цензурой, а так хотелось))). Мне вот правда интересно как советская цензура пропустила краешек бубы, сексуальные домогательства к Семён Семенычу, стриптиз и вот это вот всё. Ух непорядок непорядок!!! Мыж все таки russo turisto, obliko morale!

Как всегда ставьте лайкосики, оставляйте комменты, подписка по желанию. Не хочу превращать это в свой род деятельности, уж очень утомляет. Так что устраиваю себе майский отпуск, а Алису попытаюсь залить на недельке. До встречи!

Add a ❤️ and follow to support my future works.

Every character in a different version of this LoRa:

Ai Hinatsuru old one

Ai Yashajin

Charlotte d'Izoard

Ayano Sadatou

Mio Mizukoshi

Ginko Sora

Keika Kiyotaki

Yaichi Kuzuryuu

Ika Sainokami

complete

Additional info about choised LoRa in "About this version block"

//why i change format:

1. it's bad if your LoRa's don't sort in automatic1111 lora list by title(title need to be first);

2. it's bad if your don't see trigger word in name of model(and civitai crop's long names, but for version it have additional characters);

3. it's not so good to made 20 LoRa's for each title on Civitai, just look like spam.

4. multicharacter LoRas harder to control->it's bad.

// result is format <title name>_<character trigger word> // model can contain additional TW, like "Pajamas", but this is not necessary//

train models isn't easy and you can support me here:

❤️Boosty Donation link

LoRa trained on this model https://civitai.com/models/49608/randomizer89merge

First Lora.

Model trained from 32 ingame screenshots.

Pretty bad, but works. Feel free to experiment.

Any tips are welcome.

Made a loRA from Kuroume_1024

Includes a LoCon as well, really likes to mess up hands but bad-hands seems to help with it. AOM3 seems to keep the style the most but most checkpoints i've used have worked

Still learning about making loRA, but having fun!

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<<

Parrley's Battle Suits

Hello everyone,

I made this model to celebrate the fact that I've made a new friend today. A good lad that's soon going to be training his own LoRAs.

Let's encourage him through using and reviewing this model!

Let's go Parrley,

This model is a continuation of the series (elements) where we can make incredible elemental girls, its one of my favorite works. Basically it transforms your characters into Water in a more exaggerated way, unlike using only prompts. The model is mostly trained with images of girls, so it will be easier to create water girls.

It has not been tested on objects but I think it could work. I recommend using Lora with forces from (1.0 - 0.4).

If you want a more loquid and clean body I recommend using the following keywords (Fullwater), and also works (girl by Fullwater) for greater precision. Additionally use the following keywords to get a better water body: (liquid body, liquid, water, blue skin: 1). use the last number to manipulate the weight” ENJOY!!! :DD

Last Element --> (Fire girl).

CHECK THE OTHER LORAS!!!

⬇️⬇️⬇️⬇️⬇️⬇️⬇️⬇️

Restaurant Series: Ronald McDonald, Wendys

Don’t forget to check out my other Disney (Princess) Series Loras on my profile. YeiYeiArt.

Or

THE NEW !! Villain Collection: Maleficent, Ursula.

⬇️⬇️⬇️⬇️⬇️⬇️⬇️⬇️

ADVICE!! “If you want a commission of something in particular, whether it’s a style or a character on request, contact me via email: jeanc.romero.ib@gmail.com.”

Or check mi comissions in my Twitter account!! ---->> (1) YeiyeiArt (@jeang_c) / Twitter

Please consider to support me by buying me some coffee so I can make a new LoRA faster. I do open commissions there too if you want to make your own custom LoRA: My BMAC page

-> Yujeong V2: Here

Trigger word: bgyujeong

Best checkpoints/models to use:

Realistic: VisionGen, ChillOutMix, ArtEros, Snapdd00, Henrealmix

Fanart/painting style: Dreamshaper, LucidMix, SunshineMix, Majicmix

Use it wisely. I don't responsible for anything you generated with this LoRa.

Join KPOP Diffusion Discord: https://discord.gg/NrBDMX79Da

N°21 Release, カカリア - Cocolia from Honkai: Star Rail - 崩壊スターレイル.

You can now request a Character's LORA. CLICK HERE

Put everything in Filter for seeing all images!

Click on Show more for Weight & Trigger recommendation, Also click on About This Version at Right Corner for more Info.

Well, like Sushang it was a challenge & a request too, Cocolia was even more Harder since she's have 4 images at max in Art (Booru+Pixiv).

But i managed to get 34+ Images, I did the exact same processus for creating Cocolia that i did on Sushang: (Upscaled x4-AnimeSharp, Cropped, Flipped & Mixed with some Game screencaps) At the best quality possible.

AnimeFullFinalPrunedFP16 used, so he work with the majority of Anime Model.

Flexibility is Ok as you can see in Examples images, best is to put 0.6-0.75 Weight for Flexibility.

About Trigger Words & Prompts: CocoliaV4 (For Trigger) & for prompts just refer to examples image.

Weight recommended: Best result: 0.6-0.8, (Work at Weight 0.9-1 but i don't recommend, you will have a game feeling since Art & IA art on Cocolia is Pratically No-Existant).

Negative Embedding used: EasyNegative, BadPrompt2 and sometime negative_hand-neg.

Leave a Review & Share you're image in comments if you appreciate this Work :).

This is my very first LoRA attempt. I got up the nerve and tried my hand at making one thanks to the wonderful Konyconi-LoRA tutorial. If you haven't already seen their LoRAs, you owe it to yourself to check them out, they're fantastic and I always look forward to their next release. I also used the excellent guide and training Colab from holostrawberry.

About : My LoRA "Tigerstripe" will do just that, add tiger stripes to various objects in the image reasonably well. It excels with cars and trains and buildings but even then I find I might have to add the word "painted" or "colored" sucn as "TigerstripeAI painted dirigible" to get it to work well. can be a bit cantankerous when it comes to certain objects such as rifles or toilets or just about any object where SD expects to see a human holding it or on it. It will put one there (most often a human with tiger stripes and a tiger's head) most of the time unless you use the negative prompt to block it out. Sometimes a tiger tail might appear. I am not sure if this is SD or my failure somewhere in the settings during training - there were no images in the training set with tiger heads or tails, but I only have a thin grasp on what I am doing so it's likely me. If anyone has any ideas on what I did wrong, let me know. Trained using 100 images for 4 repeats, 20 epochs, and 2 batches.

It works best in most cases with a strength between 0.6 and 0.9

老头环风格LoRA，这个炼的比较好，是我所有模型中最满意的。

B站@GPT人工智能

This is a style LoRA (ELDEN RING Style).

Use chilloutmix or RealDosMix for 2.5D,and meinamix for 2D

Trigger Word: lalamon

Based prompt: 1girl, black sclera, blue skin, colored sclera, colored skin, huge ahoge, white hair, long hair, yellow eyes,

Outfit prompt: black scarf, long cloak, white skirt, gold and black metal armor, metal thighhighs

Should use with Black Sclera | Feature - v3.0 | Stable Diffusion LyCORIS | Civitai at low (~0.2) weights to get better eyes

A model in the style of Konno Tohiro's drawings. They usually draw extremely curvy characters in skimpy outfits, really recognizable eyes and lots of shiny highlights.

If you want to support me buy me a coffee!

Weight: 0.8-1.2 should be fine.
Triggerwords: None.

比较偏中年 不喜勿喷

Model: chilloutmix_NiPrunedFp32Fix

Res: 512 x 832

DO NOT check "Restore faces"

Test for a starspawn of cthulu lora. -Beta

0.8 is recommended

Please consider to support me by buying me some coffee so I can make a new LoRA faster. I do open commissions there too if you want to make your own custom LoRA: My BMAC page

Bomi V2, V3

Trigger word: apinkbomi

Best checkpoints/models to use:

Realistic: VisionGen, ChillOutMix, ArtEros, Snapdd00, Henrealmix

Fanart/painting style: Dreamshaper, LucidMix, SunshineMix, Majicmix

Use it wisely. I don't responsible for anything you generated with this LoRa.

Join KPOP Diffusion Discord: https://discord.gg/NrBDMX79Da