Yamashiro Takane from Touhou Project 18 Unconnected Marketeers as the second stage.

Training Model: AbyssOrangeMix3 (AOM3)

The weight should not be too high, which is around 0.8

Recommended weight: 0.7~1.0; CFG Scale: 6~8

You can try different weights for different models.

You can try these words for the prompt:

key,

camouflage, camouflage_shirt, camouflage_skirt, camouflage_headwear

green_skirt, green_shirt,

green_hair, green_eyes, boots,

mountain, forest, trees

Without giving the camouflage indict, the output might be pure green clothes.

This is an embedding instead of a Lora.

Rebecca Quin (born 30 January 1987) is an Irish professional wrestler. She is signed to WWE under the ring name Becky Lynch where she performs on the Raw brand. Lynch is one of WWE's most recognizable and highest-paid wrestlers.

This is a textual inversion trained on pictures of wrestler Triple H, aka Paul Michael Levesque, with his now iconic shaved head. Here you can get him with his old school mane!

I am not quite sure what's going on but there seems to be something off every now and again. Hope you like it nevertheless!

Please let me know and showcase some images.

Still learning and improving the progress of the training, any feedback is welcome.

Feel free to leave me a tip if you like what I am doing :)

26 year old American pornstar.

This is my first attempt at making a male Ti. Any criticism is appreciated.

Mark William Calaway (born March 24, 1965), better known by the ring name The Undertaker, is an American retired professional wrestler. Widely regarded as one of the greatest professional wrestlers of all time, Calaway spent the vast majority of his career wrestling for WWF/WWE and is best known for his critically acclaimed "Deadman" Undertaker gimmick, for which he was inducted into the WWE Hall of Fame in 2022.

A request of @DCl.

Sofía Gómez is an American social media personality and influencer, with more than 5M followers on Tiktok.

1000-step TI trained on a dataset of 18 images with my usual settings.

Curious about my work process? I have summarized it here.

Appreciate my work? My TIs are free, but you can always buy me a coffee. :)

How to create a good prompt using my TIs

You're obviously free to experiment, but bear in mind that my TIs are trained with a more or less fixed phrasing, that normally starts with:

"photo of EMBEDDING_NAME, a woman"

So I recommend always starting your prompt like that and then building the rest of the prompt from there. For instance, "photo of (s0fiag0mez:0.99), a woman, RAW, close portrait photo, long brown coat, long haircut, pale skin, slim body, (high detailed skin:1.2), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3 sharp focus, f 5.6".

This is a textual inversion trained on pictures of wrestler Triple H, aka Paul Michael Levesque, with his old school long hair. You can find his newer look here.

I am amazed on how good the images came out in my test runs, hopefully you have as much fun as I have.

Please let me know and showcase some images.

Still learning and improving the progress of the training, any feedback is welcome.

Feel free to leave me a tip if you like what I am doing :)

Underboob cloth mod for Stable Diffusion 1.5

Works best for CG\Comic, The class of real photos is prone to NSFW pictures, but most likely only on SD 1.5. Other versions have not been tested, No bias in terms of eyes and face and also not mimicking an individual person,But it affects the size of the breasts as well as the shape of the cloths and hair. So this is the first beta version, comments welcome!

How to use

Simply download and put into your /embeddings folder. Then use 'under-boo' in your prompt. Reduce or increase the weight of the embedding by using this syntax:

(under-boo:1.2) increases the weight, or values below 1 to decrease (such as 0.6-0.8), Too high a weight will affect the overall clothing and hair performance

I recommend putting under-boo to words the end of the prompt, it's strong enough.

This is a textual inversion trained on pictures of wrestler Carmella, aka Leah Van Dale.

I am pretty happy with the way this TI works.

Still learning and improving the progress of the training, any feedback is welcome.

Feel free to leave me a tip if you like what I am doing :)

5 images crop of the face, all from the famous painting (3 using codeformer at 95% fidelity to upscale, since all images are the same but only on slightly different lighting, quality and colors, background was blurred/altered deliberately on 3 or 4 of the images so that the training would focus on the face, then trained at batch 2 and 3 of the other stuff to about 2200 but realized it was garbage after 1700 decided to seletect 475 (550 was decent too) to upload

31 year old Russian nude model and singer.

This is a textual inversion trained on pictures of wrestler Liv Morgan, aka Gionna Daddio.

Still learning and improving the progress of the training, any feedback is welcome.

Feel free to leave me a tip if you like what I am doing :)

Textual Inversion of a Porsche 911 Turbo 2022

Its not perfect but it can create nice advertisement images of a Porsche in the following scenarios:

• moving car with motion blur

• parked car at all angles

• backgrounds that work best are mountains, forrests, parks, racetracks

• studio environment (white cove)

• different car paints as the color was not trained

still needs lots of inpaiting to fix rims, wheels or wrong logos

however i edited out the license plates in the training data so sometimes they still show up but best case they are empty.

Trigger word is porsche911_ti

v1 was trained with 18 images for 1050 steps

This is a textual inversion trained on pictures of wrestler Rhea Ripley, aka Demi Bennett.

This TI was requested by a buddy of mine.

Still learning and improving the progress of the training, any feedback is welcome.

Feel free to leave me a tip if you like what I am doing :)

A request of @TheEliteChief01.

Nina Dobrev is a Bulgarian/Canadian actress known for her roles in films such as The Perks of Being a Wallflower or The Final Girls.

1500-step TI trained on a dataset of 18 images with my usual settings. Most of the dataset was provided by @TheEliteChief01 himself. :)

Curious about my work process? I have summarized it here.

Appreciate my work? My TIs are free, but you can always buy me a coffee. :)

Key word: heroes claire

Using ChilloutMix for all the photos.

DMP++ 2M Karras

20-30 steps

Use as you wish. Asking permission for AI generated material is stupid. Since everything is taken from someone else. Long live pirates! F them greedy..

Key word: The 100 john

Using ChilloutMix for all the photos.

DMP++ 2M Karras

20-30 steps

Use as you wish. Asking permission for AI generated material is stupid. Since everything is taken from someone else. Long live pirates! F them greedy..

Key word: The 100 bellamy

Using ChilloutMix for all the photos.

DMP++ 2M Karras

20-30 steps

Use as you wish. Asking permission for AI generated material is stupid. Since everything is taken from someone else. Long live pirates! F them greedy..

Charlotte Ann McKinney (born August 6, 1993) is an American model and actress who first gained attention as an Instagram personality, eventually achieving wider recognition for her appearance in a Carl's Jr. commercial which aired regionally during Super Bowl XLIX in 2015.

You can invite me to a Ko-fi if you want!

TI for Kat Dennings from the tv show "2 Broke Girls" between some others.

Use: just type "katjen_h" or click on your TI tab.

Commissions are welcome! :)

TI for Dana Scully from the tv show "The X-Files", played by Gillian Anderson.

Use: just type "scuxfi_h" or click on your TI tab.

Commissions are welcome! :)

Hi guys!

This is the same history of the SD 1.5 embedding , so ejoy it!!!!

If you wanna test it, you can put this word on the prompt: avGdnr .

Sommer Ray is an American fitness model, social media personality, and YouTuber. She gained fame for her curvaceous physique, particularly her well-toned butt, which she often showcases in her social media posts. Sommer has over 25 million followers on Instagram, where she shares photos and videos of her workouts, modeling shots, and personal life.

This is a 2275-step embed that uses a dataset of 48 images. While I plan to update it later, for now, I am satisfied with the results. I have not tested this model in a NSFW environment, but I believe it will perform well if prompted properly, please remember hiresfix will affect image ouput. MODEL USED IN IMAGES | VAE USED

About

A style for generating pictures of abandoned things and abandoned places. It adds a touch of rust and decay to everything and everyone. It wasn't intended for generating pictures of people, it will generate pictures of people with rust and decay on their skin (this is known issue - you have been warned). Useful for surreal, horror, post-apocalyptic scenes.

Trained from a single photo of a rusted car in field. This is my first thing I've trained using DreamArtist, constructive feedback is appreciated. I may look at fixing the issues with generating pictures of people in a future version.

Installation

Place in the directory where you keep your embeddings

Usage

use style-abandoned2 in your prompt, experiment with placing it at the beginning, middle or end of your prompt.

29 year old American actress.

A commission of @Zorglub.

Lucy Liu is a Chinese/American actress, known for her roles in the Elementary series or the Charlie's Angels films, among others.

1200-step TI trained on a dataset of 18 imageswith my usual settings.

Curious about my work process? I have summarized it here.

Appreciate my work? My TIs are free, but you can always buy me a coffee. :)

This is a textual inversion trained on pictures of wrestler Kelly Kelly, aka Barbara Blank Coba.

I hope you enjoy this textual inversion as much as I do.

Still learning and improving the progress of the training, any feedback is welcome.

Feel free to leave me a tip if you like what I am doing :)

A commission of @Springbok707.

Emma Watson is a British actress who needs no introduction. For this embedding, the idea was to capture her 2010 looks, with that famous pixie haircut.

It's a 1500-step TI trained on a dataset of 18 images (part of them provided by @Springbok707) and with my usual settings.

Curious about my work process? I have summarized it here.

Appreciate my work? My TIs are free, but you can always buy me a coffee. :)

Textual inversion of Hermione Granger played by Emma Watson trained solely on images of her from the last two movies. However in some generations she still looks younger. I ask you to not use this model for porn

Lana Rhoades

Lana is an American adult film actress

This is a textual inversion, if you want a LoRA of Lana look HERE

Like my work? Buy me a beer!

[ SDv1.4, 4e-03, 4600, v/s .199 ]

This is a textual inversion trained on pictures of wrestler Nikki Bella, aka Stephanie Nicole Chigvintsev.

I hope you enjoy this textual inversion as much as I do.

Still learning and improving the progress of the training, any feedback is welcome.

Feel free to leave me a tip if you like what I am doing :)

30 year old Ukrainian Youtuber, Onlyfans model.

Kassiopeia is a custom character embedding for generating consistent character.

Kassiopeia is an african beauty with long wild dreadlocks.

This embedding is trained with dataset images that is generated by AI. She's not based on any existing person or character.

Key word: The 100 raven

Using ChilloutMix for all the photos.

DMP++ 2M Karras

20-30 steps

Use as you wish. Asking permission for AI generated material is stupid. Since everything is taken from someone else. Long live pirates! F them greedy..

Salma Hayek Pinault born Salma Valgarma Hayek Jiménez; September 2, 1966 is a Mexican and American actress and film producer.

You can invite me to a Ko-fi if you want!

A commission of @Wiggyfreak1.

Fuki (aka Fuki Commune) is a Japanese singer, the vocalist of DOLL$BOXX and Unlucky Morpheus.

1500-step TI trained on a dataset of 18 images (kindly provided by @Wiggyfreak1) with my usual settings.

Curious about my work process? I have summarized it here.

Appreciate my work? My TIs are free, but you can always buy me a coffee. :)

Jackie is a custom character embedding for generating consistent character.

Jackie is a blond male model with androgynous features. He has an athletic male body and feminine face and hair. He works well for elf and vampire character generations.

This embedding is trained with dataset images that is generated by AI. He's not based on any existing person or character.

Training Info

Training Jackie was more difficult than training a woman character as AI loved converting Jackie into a woman. So I used an aggressive training with 5 images instead of my usual 25 and used a lower training step to end training before AI could turn him into female.

Key word: The 100 clarke

Using ChilloutMix for all the photos.

DMP++ 2M Karras

20-30 steps

Use as you wish. Asking permission for AI generated material is stupid. Since everything is taken from someone else. Long live pirates! F them greedy..

This inversion of Kaylin Slevin (Instagram Bimbo) was trained on 18 images (including flipped ones) at 2600 steps on v1.5-pruned and pairs very well with Fake Lips: https://civitai.com/models/18264 for a bit of 'authenticity'. I got best results with s1dlxbrew: https://civitai.com/models/4717/ as a checkpoint.

This is my first upload, feel free to be cruel. I may modify the dataset at some point to include some bodyshots as it's a bit 'head-centric' at the moment and with the tokeniser set to 8 so you may need to (full body:1.6) or more to get past south of her navel in your pics. Best results at 768x768. Best placed early in prompt for accuracy. (note in the second 768x1024 pic her iris' are InPainted blue)

Corinna Kopf is a social media sensation with a massive following. With over 6 million Instagram followers, she has become a household name in the influencer world. Corinna first gained fame on Instagram by sharing her stunning modeling photos and daily life updates. She also collaborated with popular YouTubers and content creators, which helped her gain even more followers and exposure. As her popularity grew, Corinna started an OnlyFans account where she posts exclusive content for her fans.

This is a 1550 Step embed, using dataset of 30 Images. I will update it later, for now this looks good to me, I have not tested this model in a NSFW environment but I am sure it will work just prompt properly. MODEL USED IN IMAGES

31 year old American pornstar.

Based on the visual essence of an adult streaming personality who looks similiar. Not the best, but good enough for a meme or two.

This is not plug and play. Always use a good negative embedding and these strengthening keywords: redhead hair, wavy redhead hair, long redhead hair, evocative, alluring, posing for a picture.

I used redhead so the color red/orange wasn't heavy.

Others: bikini, inflatable pool, staring at the camera, excited, cute expression, smirking, exposed breasts

Without keywords it will be probably be a lookalike figure. Not all models work. If she doesn't show up, switch to other realistic vision mixes or mess with CFG between 5-9.

If you want SFW images you're going to want to use a SFW model. Theoretically this could have been trained on things from her thing.

This was trained with Tile Diffusion in mind, so it's recommended. Somewhat of an experiment that shows promise. If you don't use it you will get close ups on just her body since it was trained on square closeups of all parts of her so TD can use the references, but it still works for portraits and controlnet. Works well with img2img and inpainting if txt is not working.

Josephine Skriver

Josephine is a Danish model for Victoria's Secret

This is a textual inversion. If you'd prefer a LoRA of Jo, go HERE

Like my work? Buy me a beer!

THIS IS NOT PICKLED, IT IS A SAFETENSOR

[ SDv1.4, 4e-03, 4600, v/a .199 ]

Karolina Demy

Karolina is an American model and actress

This is a textual inversion. If you'd prefer a LoRA of Karolina, go HERE

Like my work? Buy me a beer!

THIS IS NOT PICKLED, IT IS A SAFETENSOR

[ SDv1.4, 4e-03, 5600, v/a .200 ]