tends to not look at view if not prompted

use tags

1girl, white hair, long hair, ribbon, red eyes, two side up, hair ribbon, hair ornament, black ribbon, ahoge, very long hair, bangs,. add large breast if u want

leave some results for me to see

Trained with NSFW images

Trained on NAi 20 images × 10 repeats × 10 epochs ÷ 2 batch size = 1000 steps

Kinda under trained Use Strength 1.0 -1.3, use tags

1girl, blonde hair, long hair, ribbon, red eyes, two side up, hair ribbon, hair ornament, black ribbon, ahoge, very long hair, bangs,. add medium breast if u want

leave some results for me to see

Trained with NSFW images

Trained on NAi 40 images × 3 repeats × 10 epochs ÷ 2 batch size = 600

👑 Licking Penis POV LyCORIS 👑 V1F

🔧Model base: AngrA_RealFlex_v02

__________________________

📝🌟 Trigger: (LickingPenisQuiron pose),<lyco:quiron_LickingPenis_V1f_Lycoris:1.0>, blowjob, licking penis, tongue out, vein penis, fellatio, penis, pov, erection, oral, licking penis, foreskin,detailed vein penis,

__________________________

📝 Variation: <lyco:quiron_LickingPenis_V1f_Lycoris:X> , X=0.2 to 0.9

📝 Denoising strength: 0.4 to 0.70

__________________________

🗒️💡Sample:

<lyco:quiron_LickingPenis_V1f_Lycoris:0.9>, (1girl), (licking penis:1.2), fellatio, 1boy, penis, blowjob, masterpiece, 8k uhd, realistic seflie, (selfie:1.1), depth of field, physically-based rendering photo of 35 y.o mature female, caucasian, brown hair, brown eyes, freckles, body freckles, forehead pimples, RAW photo, best quality, detailed background, realistic lighting, ultra-detailed, naked, medium breasts, puffy nipples, detailed face and body, award-winning photography, detailed face, backlight, ultrarealistic, ray tracing, intense gaze, looking at viewer, cinematic lighting, bathroom, showering, lickingpenisquiron pose

__________________________

🚀 This LORA likes: (best quality:1.1), (detailed:1.1), (photo-realism:1.1),

👇 Negative Prompt: (low quality:1.1), (worst quality:1.4), (monochrome:1.1),(bad_prompt_version2:0.8), (bad-hands-5:1.1), lowres,(Bored pose), static pose, busty bad hands, lowers, long body, disfigured, ugly, cross eyed, squinting, grain, Deformed, blurry, bad anatomy, poorly drawn face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, disgusting, poorly drawn, mutilated, ((text)), ((centered shot)), ((symetric pose)), ((symetric)), multiple views, multiple panels, blurry, multiple panels, blurry, watermark, letterbox, text, easynegative, ((legs)), asian, loli, , child, childish

💡Sample steps: 18 to 35

💡CFG Scale: 5 to 8.5

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 )☕🌟

Please check out my Ko-Fi page if you are interested in supporting me.

LoRA commissions open! -> Fiverr

This is a LoHa LoRA! You need the extension! Why? They do a lot better with multi-concepts.

No trigger word. Just call the lora at 0.5-1 weight, I recommend 0.75!

NOTE: I will be training a normal LoRA version soon so it can be used in merges!
I'm commited to making this amazing cus I loved the results.

Follow the steps in the Model Version notes to reproduce my images.

Sample images generated from Nothing model and CyberRealism.

All negative embeds should be easy to find. and Prompts should be included in the sample images! Click the little icon in the bottom right to see it.

It was trained on 61 512x512 images scraped from the internet and 20 epochs using animefull_final.

Danbooru tags generated by Waifu Diffusion 1.4 Tagger and fine tuned for specific tags.

大胸下垂是非常合理的！

Big breasts sagging is very reasonable!

早有人做过这个概念了，但是那个locon非常倾向于生成弯腰前倾的姿势，所以我做了这个。

Someone had done this concept before, but that locon was very prone to generating a bent forward pose, so I made this.

如果你对这个概念有兴趣也可以试试下面这两位的作品

If you are interested in this concept, you can try the following two works

与Sagging breasts - v1.0 | Stable Diffusion LoRA | Civitai相比，本版本更加下垂明显

Compared with Sagging breasts - v1.0 | Stable Diffusion LoRA | Civitai, this version is more sagging.

与長乳locon / hanging breasts locon - v1 | Stable Diffusion LyCORIS | Civitai相比，本版本不会明显倾向弯腰姿势

Compared with 長乳locon / hanging breasts locon - v1 | Stable Diffusion LyCORIS | Civitai, this version does not have a significant tendency to bend over

我的这个版本相对来说更擅长生成又大又垂的胸部（即使你不写相关tag），小胸就算了……

And this version of mine is relatively good at generating big, sagging breasts(even without related tags).Farewell to small breasts...

各个角度都适用（大概）

All angles are applicable(perhaps)

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<<

Lycoris Temptations - by EDG

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<<

Lycoris Hoodies

As technology progresses, one must make experiment and try new things.

Try out LoCon, it's nice and it makes great hoodies!

Download this LoCon, and be sure to give me your feedback!

Recommend to use with suggested model below especially henmix or chillout mix

use lora weight 1

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<<

Lycoris Couture

This model explores what we can do with Lycoris and fashion design.

The suggested weight is 0.5 - 0.7

Based on nai

Get early access to build and test build, be able to try all epochs and test them by yourself on Patreon or contact me for support on Discord

Recommended settings:

• Make sure you are aware on the usage instructions of LORA

• Sampler: DPM++ SDE Karras (Recommended for best quality, you may try other samplers)

• CFG Scale : 5 to 10

• Lycoris weight for txt2img: reccomended 0.35

Those are a Lycoris, to use it you need to install the proper extension on Stable Diffusion.

My advice is to start from the prompt of the posted images on civitai, or in any case use most of the keywords with 1.2-1.3 weight.

In general if you want a classic ironman suit you just need to use the keyword "wearing irongirl_suit" maybe with a weight if necessary.

If you want a mix like irongirl|ballet or irongirl|spider you should use both keywords, in this cases i have an important advice, play with weights! mostly when adding a particular color to the suit. I make you an example, most of the training ballet dress images are white, most of the training irongirl suit are red, so if you write "(wearing ballet dress with tutu, wearing white irongirl_suit:1.3)" SD will probably generate a normal white ballet dress, so in this case it's better to lower the weight for the ballet dress to have the mix you want, like "(wearing ballet dress with tutu:1.1), (wearing white irongirl_suit:1.3)". Opposite case if you want a red irongirl ballet dress suit.

Enjoy!

If you'd like to support my efforts and have access to early and bleeding edge builds, please think about joining my Patreon: https://www.patreon.com/betterCuteAsians

Model made from Playboy Centerforl dataset from 1950s to 2000s

shinko windy (umamusume) Lora (LYCORIS - loha) ver.3

※Please do not post NSFW content in places where it can be seen by many people, such as on social media.

I promise! 😁👍

※NSFWはSNSなど、多くの人目につく場所に公開しないようお願いします。

約束だよ😁👍

I'd be happy if you could follow and support me to increase my motivation.

モチベーション向上のためにフォローや支援してくれると嬉しいぞ。

👇😎👇

https://twitter.com/oLAcle1220

https://patreon.com/olacle

Prompts

• Trigger word

  • shinko_windy

• character base

  • horse girl,horse ears,horse tail,short hair,brown hair,white hair,purple eyes,streaked hair,multicolored hair,sharp teeth,

• race clothes

  • fur trim,fur-trimmed jacket,cropped jacket,crop top,fur-trimmed shorts,short shorts,thigh strap,black thighhighs,torn clothes,fingerless gloves,torn thighhighs,black gloves,black shorts,belt,necklace,choker,boots,

• old race clothes

  • black jacket,hooded jacket,hood down,black necktie,black socks,white shirt,collared shirt,black skirt,miniskirt,long sleeves,backpack,sneakers,zipper

• plain_clothes

  • white sweater,clothes writing,red shorts,white socks,black footwear,

• tracen uniform

  • tracen school uniform,school uniform,summer uniform,sailor shirt,serafuku,purple shirt,puffy short sleeves,white skirt,white thighhighs,purple bowtie,purple bow,horseshoe ornament,brown footwear,zettai ryouiki,

Recommended settings（おすすめ設定）

weight 0.65~

If you want to emphasize your upper body, it may be better not to use words related to socks and shoes.

上半身を強調したい場合は靴下、靴系のワードは使用しないようにするといいかも

If other clothing options are not appearing frequently, please adjust the weight by decreasing it.

その他の服が出ずらい場合はweight を下げて調整してください。

Space heists and gay times in space base lounge,

Exploring the debris of space battles for forgotten salvage,

ACTION ! ADVENTURE ! and only one planet...

MARS!

This lora puts the pulp back into... pulp space ladies ?

All samples are raw output, don't count the fingers :D

(REVanimated, 840000 VAE)

Prompting

Keyword sp4c3w0m3n

Just using the keyword will make you a sexy space lady in a pulp costume

Words such as sexy, seductive, pinup, smile, suggestive will add to the pinup look

Planets will be orange, there is only MARS !

Helmets can be prompted on or off space suits

Clothing style and color can be changed no problem but will have a pulp space vibe

Hair color and length no worries !

adding Pulp Style can enhance the style a bit, as can increasing the keyword strength.

Will it NSFW ? No it's a classy lady ! Yeah it will, it's 1.5 based.

If you like it, please review it or;

squeeze me some carrot juice - https://ko-fi.com/bunnyviking

V5:

This version use noise offset，Improved the effect of light and shadow.Works well with Hires.Fix. Do not need face editor any more.

As for the model recommendation, Basil_mix_fixed is suggested for this version. Although Perfect World hasn't been tested, it should theoretically work well.

使用了金字塔噪声，提高了光影的效果。搭配Hires. Fix使用效果不错。无需face editor.

该版本推荐使用Basil_mix_fixed,至于Perfect world没有测试，理论上应该可以。

V4:

Finally, we've reached this version. It incorporates various action elements and reduces the issue of limb distortion in multi-person scenarios. You can combine this Lora with various poses to achieve the desired posture (based on testing, the results with 3D Lora are better). However, the trade-off is a slight decrease in facial similarity at longer distances. I recommend using a face editor to improve it significantly.

Unfortunately, I cannot view or process images. As for the model recommendation, Basil_mix_fixed is suggested for this version. Although Perfect World hasn't been tested, it should theoretically work well.

终于到这个版本了，加入了很多动作要素，减少了多人情况下的肢体崩坏情况。可以结合各种pose lora做出你想要的姿态（测试来看三次元的lora效果会好一些）。

但是代价是在远距离脸的相似度略微下降了，建议使用face editor修复，可以大幅度改善。

图片不好发，你们懂的。

该版本推荐使用Basil_mix_fixed,至于Perfect world没有测试，理论上应该可以。

V3:

If the facial effects are not satisfactory, you can increase the weight to improve them.

I recommend using Basil_mix_fixed, followed by Perfect world.Currently, the following models can be used:

提升了面部效果，难度比想的大了很多，鬼知道我做了多少个版本才有现在的效果。感谢朋友的帮助。

该版本推荐使用Basil_mix_fixed,其次是Perfect world。

效果不够的话可以提升权重。目前可以用的：

• crying

• grin

• tongue out

• naughty face

• tongue out

• angry

• pain

• fellatio, open mouth, tongue out,

• (gloom:1.4)

NEW VER:

This version has been retrained and it is recommended to use Perfect World with a weight of 0.6-0.8. I tested some clothes and poses that were not in the data set, and they turned out decently. The next step will be to consider adding more expressions and actions.

该版本重新训练，推荐使用Perfect world，权重0.6-0.8.

测试了一下不在训练集内的衣服和动作，姑且还行。下一步考虑加入更多的表情和动作。

****

Why is it called Almighty, because I hope the Lora can be used with pose and clothing.

The current version: more than 300 pictures, a dozen Concept. recommended with realistic. Can be combined with pose lora, using Basil_mix_fixed can reduce limb collapse. Clothing lora need to increase some weight.

I recommend using Basil_mix_fixed, followed by Perfect world. other models are also available, but I still prefer Basil_mix_fixed, because the most restored. Weighting 0.6-0.9.

为什么叫万能，因为我希望该Lora可以搭配各种动作和衣服使用。

目前版本：300多张图，十几个Concept。推荐搭配realistic使用。可以结合动作lora，使用Basil_mix_fixed可以减少肢体崩坏。衣服lora需要加大一些权重。

推荐使用Basil_mix_fixed,其次是Perfect world。其他模型也可以，但是我还是更喜欢Basil_mix_fixed，因为最还原。权重0.6-0.9。

内置的衣服： Included clothing:

1.Advent_Children_costume,midriff, crop top,skirt, swept bangs, bare shoulders, sleeveless, black skirt, gloves, bangs, collarbone, belt,

2.chinese_dress_purple,thighhighs, double bun, hair bun, chinese clothes, dress, china dress, jewelry,

3.chinese_dress_dragon,double bun, dress, jewelry, hair bun, cleavage cutout, chinese clothes, earrings, gloves, bracelet, cleavage,

4.clothes_lift,nipples, breasts, shirt lift, large breasts,

5.sliver dress,

6.golden dress,

7.Honoka_costume,swimsuit, breasts, bikini, torn clothes, shorts, torn thighhighs,navel, front-tie top, belt, short shorts, front-tie bikini top, bikini top only, jacket, cleavage, open clothes, open jacket,

8.Maid,breasts,maid headdress, cleavage,alternate costume, apron, enmaided, ,jewelry, earrings, leotard, wrist cuffs

9.Standard_clothes,crop top,gloves, suspenders, elbow pads, midriff,  fingerless gloves, red footwear, black thighhighs, black skirt, elbow gloves, suspender skirt, boots,  tank top, navel,sports bra, abs, bare shoulders, zettai ryouiki, pleated skirt, toned, miniskirt

10.nsfw,bondage, bound, arms behind back, nude, nipple rings, rope, pubic hair

We will comply with the with the secondary creation guidelines.
https://vspo.jp/guide/
Please read the secondary creation guidelines.

The digital twin of not so well-known beautiful Asian celebrity

--

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 Onlyfans Goddess Vol. 1 [Fin] - 10. Coconut Kitty [Final] | 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.

Because it is based on LoRA but is trained with Conv2D
Conv2D requires need extensions
https://github.com/KohakuBlueleaf/a1111-sd-webui-locon
or
https://github.com/kohya-ss/sd-webui-additional-networks

Makoto Niijima from Persona 5, trained as a LyCORIS network. Retrained my old LoRA with updates to the dataset and using new training techniques introduced over the past few months.

Requires extension for use:

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

Version 2 is now out!

This is an updated model with a larger dataset, including the metaverse outfit separately tagged for prompting.

Recommended tags are:

Makoto: dsmakoto, brown hair, short hair, crown braid, red eyes

Queen: dsqueen, brown hair, short hair, crown braid, red eyes, bodysuit, shoulder spikes, scarf, white gloves

Check out my HuggingFace repository:

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

Check out my Pixiv:

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

Style LyCORIS trained on screencaps from Persona 5 The Animation. Yes, I know Lykon already made a LoRA (which I do recommend you check out by the way). But I had this dataset sitting around and some older variants of this have made it into the example images for my character models, so I thought I'd share for anyone interested in trying to recreate the look.

Requires extension for use:

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

No activation tag is required for use, just activate the network and set the desired weight.

Check out my HuggingFace repository:

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

Check out my Pixiv:

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

英语(English): This model does not come with clothing information, but it has correctly memorized the body data through regularization, so the character proportions are perfect. You can dress her in any clothes. A weight of around 0.6 is recommended.

中文(Chinese): 本模型不带有服装信息，但是通过正则化正确地记忆了身体数据，因此人物比例完美。你可以给她穿上任何衣服。推荐权重0.6左右。

日语(Japanese): このモデルは服の情報を持っていませんが、正則化を通じて体のデータを正しく記憶しているため、キャラクターの比例は完璧です。彼女にはどんな服でも着せることができます。推奨される重みは約0.6です。

韩语(Korean): 이 모델은 의류 정보를 포함하고 있지 않지만, 정규화를 통해 몸 데이터를 올바르게 기억하고 있으므로 캐릭터의 비율은 완벽합니다. 그녀에게 어떤 옷이든 입힐 수 있습니다. 권장 가중치는 약 0.6입니다.

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

One of the four Battle Chatelaine that were introduced in the 6th gen and where not really part of the main storyline more of a post game challenge if i remember correctly.

I dont know if i will make all four of them but I will do at least one more.

Keyword is Evelyn will work strength 1.0 just fine adjust if you need to or if you mix it with style lora. Look at the metadata to get her default outfit. Most of the picture were in her default outfit so it might be difficult to dress her up but be my guest to try.

If you like it leave a comment, like and rate it but please if you have something that is wrong write it into your review or comment so i can do something about it.

Have fun generating.

Fiend Satella from Rance Series

I recommend to put next tags for clothing:

black leotard, elbow gloves, thigh boots, black cape

英语(English): This model does not come with clothing information, but it has correctly memorized the body data through regularization, so the character proportions are perfect. You can dress her in any clothes. A weight of around 0.6 is recommended.

中文(Chinese): 本模型不带有服装信息，但是通过正则化正确地记忆了身体数据，因此人物比例完美。你可以给她穿上任何衣服。推荐权重0.6左右。

日语(Japanese): このモデルは服の情報を持っていませんが、正則化を通じて体のデータを正しく記憶しているため、キャラクターの比例は完璧です。彼女にはどんな服でも着せることができます。推奨される重みは約0.6です。

韩语(Korean): 이 모델은 의류 정보를 포함하고 있지 않지만, 정규화를 통해 몸 데이터를 올바르게 기억하고 있으므로 캐릭터의 비율은 완벽합니다. 그녀에게 어떤 옷이든 입힐 수 있습니다. 권장 가중치는 약 0.6입니다.

We will comply with the VERSE secondary creation guidelines.
https://verse-n.com/guideline/
Please read the secondary creation guidelines.
二次創作ガイドラインをご一読お願いいたします。

Please check out my Ko-Fi page if you are interested in supporting me.

LoRA commissions open! -> Fiverr

This is a LoHa LoRA! You need the extension! Why? They do a lot better with multi-concepts.

Trigger words for V1.20:

<lora:mothPeoplev120:0.7>(moth woman, insect wings, antennae) or (moth man, insect wings, antennae) with a lower LoRA weight for man!

You can also try "extra arms", "arthropod limbs", "monster woman", "arthropod woman" and "fur trim".
NOTE: It helps a lot to give a use to the "extra hands" like "holding" or "hand on own breast" or "masturbation" or anything really, most of the images in dataset had some use to the extra hands.

Follow the steps in the Model Version notes to reproduce my images.

Sample images generated from Nothing model and CyberRealism.

All negative embeds should be easy to find. and Prompts should be included in the sample images! Click the little icon in the bottom right to see it.

It was trained on 93 512x512 images scraped from the internet and 20 epochs using animefull_final.

Danbooru tags generated by Waifu Diffusion 1.4 Tagger and fine tuned for specific tags.

The girl from Fairy Tail: Mirajane Strauss

Enjoy!

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

Important notice: This model got review bombed by an idiot who didn't even post anything and just left an awful review. If you want to do me a solid one try out this model and post some cool pictures with a rating you see fit to combatant this buffoon.

Thank you for your help

Trial captain Acerola from Sun and Moon is here.

I haven't had much time to test it but from my limited time it seems to work well

Keyword is Acerola dataset contains other outfits as well but its best in creating her default outfit. If you cant get her right look at the metadata for guidance but it should be very easy to get her i only used like 3 prompts including the activation token.

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

Have fun generating.

Celebrity Request. Enjoy the legend himself.

A bright, colorful fusion of anime and western art styles, with awesome hair. Makes sexy, heroic characters with exaggerated proportions.

This is a mix of a locon extracted from DucHaitenNiji and a number of my own mixes.

The suggested weight is 0.5 - 0.7

Based on nai

Checkpoint - henmix_real V30

Res - 512 x 768

Lora weight 0.9-1

Well this is the fruit of my inpaint LORA. With that i spent several days inpainting a mostly synthetic dataset. It was kind of awful as i had almost no confidence in the result of the project. That particular LORA and then LOCON ended passing through 20+ iterations with dataset cleaning and tags pruning and modification. This one on the other hand as i spent so much time making the dataset seems to have come out ok if a bit overbaked (maybe)

For recommended setting it can vary depending on the LORA mixture you are using.

A suggested trigger seems pretty much useless as this is not really a stand alone LORA but if you are using without anything else you can try: <lyco:Tanetsuke:.6>, Tanetsuke,

It seems to vary from as little as .35 to as high as 1. Al lower strengths it might no put the bubble pointing at the character belly.

I'll add a SFW gallery and a NSFW one so people can see how the bubbles appear with different sex poses.

In the dataset i included the following poses which i hope will be correctly displayed with their bubbles

• reverse cowgirl facing viewer

• reverse cowgirl facing away from viewer

• standing leg up facing viewer

• doggy from behind facing away from viewer

• Some prone bone position

• mating press

• A couple after sex poses

Hopefully it should be flexible enough.

I will add the full dataset including the raw before inpaint with the masks included. So if someone wants to train a lora and turn all the fertilized ova into penises or apples or whatever they should be able to generate a similar dataset using batch inpaint.

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

I had this datset on my hard drive for quite some time and ready to go into training.

When im doing some things like cooking and stuff I start training things. (Have to start collecting again soon though)

There is already a model for her but if you take mine because it has a smaller filesize maybe or because you like lycors models more than lora be my guest

Keyword is Rinkah_(fe), dark skin is pruned so you don't have to tag it but for some models you might have to add it.. like the one i was using when generating the preview pictures. Also her pants dont work quite right she prefers to not wear them if you dont prompt them. If you need help with the prompts look at the metadata or leave a comment.

Works fine on strength 1.0 you can go lower if you need to.

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

Have fun generating

The dataset for this one is 20 images from pixiv.net.

All of them are fanart of Remilia Scarlet from the Touhou Project game series.

Come to think of it, I should have thrown in her official art as well.

Well, anyway, all the dataset images are of Remilia, but since it's a LoCon, it can actually be pretty flexible and make any character look like they're from a 2009 fanart image.

It can work well combined with my HL2 Concept Art LoRA.

This model can be a bit picky; when I tested it on profantasy_v2, it would only work with a unet weight of 0.5 or lower, but on dreamshaper_4BakedVae, it would work at any weight.

I created this model - and the HL2 concept art one! - because I love the various art styles of the 2000s, and even before the advent of NovelAI I was lamenting at how art had become so homogenous in style and flatly lit.

You even see it in video games these days. A wall texture is no longer a detailed surface, it's just a solid colour with some faint brush strokes. It may be easier to pick out players this way, but it's also stylistically bankrupt while claiming to be the opposite. Just criminal.

About this Model

This LyCORIS:Locon model, eyedirectionV1.8, is for orienting the direction of the eye without using the popular keywords "looking away" in the positive prompt. The model changes eye direction while minimizing large head turns. "looking away" is not bad if we want significant head turns, but for subtle turns it is too much for some of our setups.

How to Apply

Trigger: eyedirection

Settings:

Weight: 0.3 - 0.5

Methods: DPM++ 2M/2Sa/SDE Karras

Steps: 25 - 30

CFG: 7-14

Positive prompt keyword options:

eyes up, eyes down, eyes up left, eyes up right, eyes down left, eyes down right, eyes left, eyes right, looking above, looking below, looking sideways, eyes left looking sideways, eyes right looking sideways, eyes up looking above, eyes down looking below, eyes up right looking above, eyes down right looking below, eyes up left looking above, eyes down left looking below

ex. <lyco:eyedirectionV1.8:0.3> eyedirection, eyes left looking sideways, (solo, portrait:1.4)

For random eye direction, at least the word "eyes" must be present in the prompt:

ex. <lyco:eyedirectionV1.8:0.3> eyedirection, brown eyes, (solo, portrait:1.4)

Negative prompt:

(eye contact, eye to eye, looking at viewer, looks at viewer:1.5)

Limitations

It will work in models with realistic or photorealism in them, and since this is my very Very VERY first model, there are still room for improvements and upgrades, so expect for next versions. Also, use this model responsibly and within legalities.

Donate Coffee for Gtonero

==model content Use the model carefully towards those around you==

• reduces the amount of juice to drip instead

• Not recommended for realistic model

• Tag : drip, for nude or bottomless

• Tag : drip clothes, for underwear or panties

Since training with Conv2D requires
https://github.com/KohakuBlueleaf/a1111-sd-webui-locon