This LoRA generates women in the face-down-ass-up position, seen from the back. Trained on AnimeFullFinal with 100+ images. This is a difficult LoRA to use - as are most position-focused LoRAs. If you enjoy this LoRA you could buy me a coffee: https://chownyou.gumroad.com/l/coffee

This LoRA works best from 0.6-0.8. you MUST use a model that understands hardcore - revAnimated will generate monstrosities. Lower weights sometimes generate a woman in the position by herself, and sometimes floating penises - or attached penises.

The activation word is fdauposition, but there are a host of related words you can use to nudge SD in the right direction: 1girls,all_fours,anus,ass,ass_focus,ass_up,balls,bent_over,big_ass,big_penis,bottomless,curvy,dat_ass,doggy_style,duo,erection,feet,female_focus,female_penetrated,female,femsub,from_behind_position,from_behind,huge_ass,huge_cock,kneeling,large_penis,looking_back,male_penetrating,male/female,male,maledom,penetration,penis,pussy,sex_from_behind,sex,spread_legs,testicles,thighs,vagina,vaginal_penetration,veiny_penis,

face_down_ass_up, bulldog_position, backsack and top_down_bottom_up were all cleaned from the tag lists; their combined influence should be represented in fdauposition.

I can't get this position to show up normally, and the openpose preprocessor doesn't like to work on similar images, so this LoRA is the best way I've found to generate them.

A lora for generating all kinds of vacuum fellatio from normal to EXTREME SUCCTION

Trained on 104 images

Image info

• Model used abyssorange2hard

• Model used kotosmix

Notes

• Vary the length of the mouth by modifying the trigger word (anteater face) and penis size

• dimension of the image has an effect on penis/face length

Training settings?

The most important part of training is getting a good dataset!

Training settings can be found by installing the additional networks extension in auto1111

Extensions -> available -> load from -> additional networks

Restart webui

place lora into stable-diffusion-webui\extensions\sd-webui-additional-networks\models\lora

To view the training settings

Go to additional network tab -> choose model -> training paramters

Let us embark on a journey to embrace some thot. Sometimes they are simply breath-takingly beautiful.

If you love my work and wish to buy me a coffe: ko-fi.com/tauron it helps me stays awake and get more content up

My model is out: Tauron Hybrid Mix - TauHybrid_Anime_Final | Stable Diffusion Checkpoint | Civitai

DISCLAIMER:
I'm doing this for fun and not for commercial purpose, I do not support selling imageries generated with all subjects inside this model. I do not support indecent generation images of all subjects used in this model. DO NOT post online explicit nudity, sexual or suggestive images using this model. All subjects are 21+.

===

Open to suggestion or request

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 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 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.

Please leave a review if you have any critiques or if you find this LoRa good.

This LyCORIS has been trained after carefully selecting 44 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.

真正的琉璃艺术风格，古代传统文化与现代艺术的结合，也可以出人物，具体效果可以参考图片

The real silver art style, the combination of ancient traditional culture and modern art, can also be out of character, specific effects can refer to the picture

材质模型的正确使用方式是图生图，效果贼拉棒

The correct way to use the material model is image to image, It works really very well

1.0:

这个版本的颜色淡一点

This version color it's not that dark

1.1:

这个版本的颜色会更深

This version color it's going to be a little darker

新人练手，不喜勿喷，谢谢

Rookie practice. Don't abuse if you don't like it. Thank you

This is a LoHa model trained from 100+ images, which trained with multires noise.

You can use the LoHa to design girl,& machine.

Can't draw kos-mos like choco,Can't draw fairy knight lancelot \(fate\) like choco.

Weight 0.9-1.0 will perform better,also you can try new way to use,lol

Simply Dark Cyborg in apocalypse background

If you'd like to support me and do more:
https://ko-fi.com/edgonkofi - commissions open! I can make a model for you!

Royal Gowns

We do like to dress to impress, don't we? What's more, we are lacking in beautifully detailed clothing.

Fear not friends. I've got your back.

More beautiful clothing is incoming, beautiful royal gowns to please your eyes and dress your women with style!

Special shout out to @Zovya, I am very impressed with the results of the clothing on her model as I am showcasing it here.

I highly recommend you download either her model A-Zovya RPG Artist Tools - V2

or my Amixx - v1.0-pruned-fp16

when prompting with these models.

Have fun!

Download this LoCon and get some gowns!

Trigger world - ColourfulCartoon
every second immage is the model and the first immage is without

Strength from 0-5
You can go higher in some promts and it still looking good

Can generate mature content but is a bit on the rought side still need some data on that if i make a 2nd one

I personaly use
AbyssOrangeMix2 Diffusion model

pastel-waifu-diffusion vae

on all on my generations

Would love to see what other will make with other examples

This LyCORIS has been trained after carefully selecting 46 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.

Information

weight: 0.7~0.8±1

trigger: jigita

option: fang, fang out

default costume(looks like):asymmetrical_clothes, asymmetrical_gloves, asymmetrical_legwear, bare_shoulders, belt, black gloves, boots, bracelet, chain, crop_top, detached_sleeves, earrings, elbow_gloves, fingerless_gloves, frilled_skirt, hairclip, hooded_jacket, navel, miniskirt, mismatched_legwear,short pants, plated_skirt, red_footwear, red hair, red_pantyhose, red_skirt, red_thighhighs, shirt, short_hair, spiked_bracelet, uneven_gloves,

bikini: bikini

first:Trigger is set. But you can call it without it. why?

1:トリガーは設定しています。ですが無くても呼び出せます。なんで？

second:By entering everything, something like a default costume will be output.

Some prompts may not be necessary.

2:全部入力することで標準コスチュームっぽいものが出力されます。

必要ないプロンプトもあるでしょう。

Third:The expected bikini is not output easily. weight set to 0.9, it is a little easier to output

3:想定されたビキニはなかなか出力されません。強度を0.9にするとやや出力されやすいような。

fourth:Surprisingly good?

4:意外といけるやん？

You can also generate Midori and Momoi with 2girls.

Enjoy the new Riju Model from Tears of the Kingdom.

Dataset was very limited (about 25 pictures) but every day new picture are being released so i will retrain it eventually when enough pictures are present.

Activation Token is Riju and if you want to get her default outfit you can use tags like crop top, skirt, bracelets. Her lipstick is kind of weird though and always present maybe you want to put "lipstick" in negatives or just prompt it, it works most of the time.

I haven't tried generating her in different outfits but i think it's possible. You can always change the strength and then it should work.

If you need guidance while prompting you can look at the metadata

If you like the model you can leave a comment with your pictures and i would appreciate if you could leave a rating or feedback.

Have fun generating.

I asked a friend of mine hey which armor should i do next and I expected some popular ones and then he said what about Anjanath and i thought okay i like the design but what about the dataset....

I searched for an extend amount time and i only found 16 Images that I could use and from these 16 I wouldnt have used half of them if i had a choice.

No activation token just prompt it all pictures contain anjanath (armor) that might help. Also because of the scarcity of images random monster might appear in the background.

So the Locon works good I guess im not entirely happy with its performance I trained it on higher Alpha and Dim settings because of the lack of pictures if you combine it with other lora/Lycoris some pieces of the armor might not work properly (the helmet in particular).
I wouldnt recommend using it on more than 0.9 or 0.8 it also depends on some factors like:" Are you using it together with another locon/lora ?"

I will upload all the epochs that I deem usable just test them out and take the one you like best I will include pictures from all of them in the preview

Also I was lazy with the preview picture prompts

Have fun generating.

Minase Iori from IDOLM@STER, trained as a LyCORIS network.

Requires extension for use:

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

Recommended tags are:

dsiori, brown hair, long hair, pink eyes, hairband

Check out my HuggingFace repository:

https://huggingface.co/Doctor-Shotgun/ds-LoRA

Check out my Pixiv:

https://www.pixiv.net/en/users/90447503

This LoHa lets your models make guns instead of abominations with geometries beyond the comprehension of mortal men, as well as pose said guns a bit. It's not perfect, but it's improved exponentially by a basic knowledge of inpainting. All my examples include both the raw image and the image after a very quick cleanup with inpainting. Generally I get something usable with inpainting in most batches of 6 images.

Currently it's been tested with my personal model, but it should help others along as well. Make sure you have lycoris set up in order to use it.

Current keywords:

(useful helper keywords to go with the main terms are in parentheses. Terms marked with an asterisk were trained, but do not currently work to my satisfaction. They are included because they may be helpful in nudging the generation, or they work, but unreliably)

General concepts:

• holding weapon

• scifi gun

• trigger discipline

• woodfurniture

• aiming

• rifle in one hand

• gun pointing up

• gun pointing down

• slungrifle* (weapon on back*)

• weapon over shoulder*

Weapons:

• heavy weapon (gatling gun, cannon*)

• assault rifle (rifle, ar-15*, bullpup)

• handgun (revolver*)

• antique firearm (musket, flintlock, handgun*, steampunk*)

• flamethrower (backpack)

• bolt action (rifle, bayonet*)

• submachine gun

• shotgun* (pump action*, double barrel*, rifle)

• machine gun* (heavy weapon*, assault rifle*)

Additionally, I'd like to thank everyone in the CIVIT discord for all their help, and particular EDG.

Quannah Rose Chasinghorse-Potts is an American model. Born in the Navajo Nation in Tuba City, Arizona, Chasinghorse is Hän Gwich'in of Eagle Village, Alaska

Based on the concept of breasts so large, the girl can only be seen from behind.

Please combine with either Thojm's hyperfusion or my Locon expanded model, or else the breast and body shapes will be very off.

*faces will look awful due to being quite small in txt2img gens, so you will NEED to clean it up with inpaint

DISCLAIMER: I am NOT affiliated with Majalis in any way. I just liked the game, scraped a bunch of images from the internet and created this model.

This is a style/characters from the game Tales of Androgyny by Majalis duo.

Please share your images here, as I would love to see what people can create with this.

This is my second attempt at creating a model for this game style, it turned out quite well and can it definitely generate Hiro in various context, because he had the most images, but as you can see from examples you can also get decent examples on other characters. I can already see the reason why characters like Trudy or Alma are harder to generate, but it will take a lot more work on the dataset preparation and proper tagging. So, there will probably be a V2, if find the time for it.

The model was trained mostly on NSFW images (it's an erotic VN, duh!), but it's capable of generating SFW images of characters as well.

It was trained on AnyLora, but it turned out to be pretty portable to other models, so far I've successfully tried FantasticChix-HR and Perfect World.

You should use CLIP Skip 2 (that's what AnyLora uses). You should start the prompt with "majalis style" followed by the character you want like "kylira". You can also add "toa" to your prompt if you want to add strength to the model, because this tag was present in every training image. For optimal results, use "1girl" + "futanari" for all the futa characters (Alma (warlock), Urka (orc), goblin, Merrybelle, Quetzal, demon king, dark knight, Dullahan, and much more...) and "1boy" + "otoko no ko" for the boys (Hiro, Kylira, Trudy)

You can find all of the tags used (and their frequencies) in the metadata of the model.

It's capable of generating penis instead of vagina for futas and traps in sexual positions even without external LoRAs.

警告：成功率不高。只能生成固定角度的图片。

Warning: low success rate.Only images with fixed angles can be generated.

我不了解射箭，所以可能存在技术错误。

I don't know archery, so there may be a technical error.

箭支断裂非常常见，弓弦问题也无法解决，我其实建议后期用ps修正。

Broken arrows are very common, and bowstring problems cannot be solved. I actually recommend using PS to correct them later.

如果你想使用人物lora但是遇到困难，可以尝试先不使用人物lora生成一张好图，然后用controlnet引导

If you want to use the character lora but encounter difficulties, you can try to generate a good picture without using the character lora first, and then use controlnet to guide it

... and the god of Ai said: Let there be waifus! and there were Ai waifus.

There are anime loras out there what is the difference?

My version focused heavily on cosplay -- this means that it has a bulk of cosplayers data sets in instead of arts / illustrations - the ratio in general are 60-40. Secondly, with Lycoris we only need 11MB, more space for more waifus! Third, there are NSFW datasets mixed in, so have fun and enjoy!

===

If you love my work, and want to treat me a coffee : ko-fi.com/tauron you dont have to, but if you do, it helps me stay awake until midnight (which is the only time im able to work on these stuff lol) and cope with life..

My model is out, check out: Tauron Hybrid Mix - TauHybrid_Anime_Final | Stable Diffusion Checkpoint | Civitai

--

DISCLAIMER:
All of my models are to be used with 21+ subjects only, I'm doing this for fun only, DO NOT use for commercial purpose. Nudity generated with this model DOES NOT DEPICTS REAL PERSON.

===

NOTE : I will keep updating more actresses in versions update

Open to suggestion or request

Request Rules:

1. No requesting minors or anything that has underage as their datasets! please don't make civitai or ai in general into trouble.

2. If requesting a person, that person should have a public images (ex. no private instagrams), they themselves has to consented sharing their images online for public

3. Be a decent human being, if you requested, please at least give a review, since I'm doing this for free. and dont be a dh and review bomb if you don't get what you want, not all lyco is perfect.

4. Do not start discussion that is pointing towards anything illegal.

5. The requested subjects has to have adequate datasets available online

6. Put a link to the requested subject datasets.

===

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 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 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.

Please leave a review if you have any critiques or if you find this LoRa good.

Sticky slime trained on 432 sticky pictures at NAI model.

Trained trigger words:

black slime | pink slime | white slime | green slime | yellow slime | transparent slime | mud slime

Updated with further training on 1024res + 2 more classes.

So, I played in Persona again, and make this. Enjoy!