TextualInversions

This TI is for making really fat peoples/concept.

All sample image done with only trigger word in prompt and no negative, excpet the last one for showing how it work in photorealism.

Also use it in negative to get slim.

23 year old Ukrainian nude model and pornstar.

Over the last 6 months, I've created quite the collection of helper and tool embeds for doing things like fixing faces, pushing realism, creating anime scenes, making subjects smile, or cry, or face the camera, whatever. Rather than creating separate listings for the literal dozens of tools I have, I've decided instead to just create a "master" listing for all of my tools that I can then update whenever I have new tools to add.

Unlike some of my more grand embeddings out there, many of these serve simple purposes and are of limited effect by themselves. Some are little more than funny experiments that turned into something useful, while others were created as helpers as part of a larger project.

I will continue to update this listing as I create more tools. I'm not planning on exposing my ENTIRE toolbox, just the ones I use and share with friends most frequently.

Don't expect a lot of demo images or a lot of fanfare on this listing. This is my toolkit. If you want to use my tools, please, be my guest, but I make no guarantee of results - Sometimes they work great, sometimes they don't, the fun part is finding the best mix to get the results you want!

As with all of my other embeds, my tools are designed to be mixed with my other 1.5 compatible embeds available on my profile page. Mix and match for some really interesting outputs, and follow me here on Civit to be notified when I release new embeddings!

--------

To use these embeddings in AUTOMATIC1111, copy them to your embeddings folder in your stable-diffusion-webui directory. No need to restart, just invoke the embedding from your prompt. Make sure you are using a 1.5 version compatible model or you will get errors!

--------

***This Textual Inversion works well in SD 1.5 checkpoint. If you are planning to use this Textual Inversion with other checkpoints, you'll need to add Henry Cavill to the prompt as well as influence the trigger word with more weight, for example ((hnrycvllti)) or (((hnrycvllti)))*** This will influence the image more to Henry's features.

Example Prompt (when using some other checkpoint): henry cavill, ((hnrycvllti))

RECOMMENDED SETTINGS Model Checkpoint: SD 1.5

Steps: 25

CFG: 3

Trigger word: hnrycvllti

Tip#1: Try to use the above Steps and CFG settings first and tweak from there.

This is a follow up to the "Ultimate Henry Cavill Model Checkpoint". This package is trained on 15k steps with a whopping 170 images and includes autocaptioned + fine tuned information.

As a favor, please let me know your thoughts, feedback and give a review rating. I would truly appreciate it!

This ti was requested by @themonkeysaur

Maria Bello is an American actress. She has appeared in numerous films and television shows throughout her career. Bello gained recognition for her roles in movies like "Coyote Ugly," "A History of Violence," and "The Cooler," for which she received a Golden Globe nomination. She has also appeared in TV series such as "ER" and "Prime Suspect."

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

一些画图辅助工具

some drawing aids

A textual inversion embedding for generating 80s style erotic photos of nude women.

Use Tips

Add vintbabesq to your prompt. Add to start of prompt for strong effect. Add to middle or end of prompt for lessened effect.

Keyword: Menasaurio SG
Checkpoint: analogMadness v40 for all the photos.

Guide to do models like this, Super easy to follow with pictures. > Here <

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..

Keyword: Lynienicole SG
Checkpoint: analogMadness v40 for all the photos.

Guide to do models like this, Super easy to follow with pictures. > Here <

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..

Keyword: Eveel SG
Checkpoint: analogMadness v40 for all the photos.

Guide to do models like this, Super easy to follow with pictures. > Here <

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..

Keyword: Catarina SG
Checkpoint: analogMadness v40 for all the photos.

Guide to do models like this, Super easy to follow with pictures. > Here <

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..

Textual Inversion embedding I did of singer Lana Del Rey. Most of the photos used where from her early career days when she first broke out.

Textual Inversion embedding I did of actress Sofia Vergara from Modern Family.

This one took me a couple of runs but I got it down pretty well.

Sophie Amanda Howard was born and raised in Southport, England.

She later moved to Ellesmere Port. She attended Christ the King Catholic High School and was in the Salvation Army until she was 16.

• Howard studied English at Edge Hill University. During this time, she signed to the IMM modelling agency and subsequently appeared in Loaded in its "Almost Famous" and "Sauna Babes" sections. She was discovered by Loaded after she sent the magazine amateur photographs of herself wearing a PVC catsuit. A growing fan base meant that by December 2005 Howard had risen to the cover of the magazine.

Sophie subsequently signed a contract with Loaded, resulting in a relationship advice column and a regular feature called "Sophie's Choice". As of 2006, She was signed to Nuts magazine for about 18 months. In 2006, Sophie's management (IMM) also signed an exclusive, 12-month deal (for 2007) with Dennis Publishing for Sophie to frequently feature in Maxim and Bizarre.

In 2009, Sophie returned to Edge Hill University to study for a degree in mental health nursing. She took a break from modelling in December 2011 in order to focus solely on her studies, before returning to modelling in March 2013.

If you like my work and you feel like it, you can invite me to a Ko-fi!

Keyword: Lass SG
Checkpoint: analogMadness v40 for all the photos.

Guide to do models like this, Super easy to follow with pictures. > Here <

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..

Jaslyn Ome, stunning Actress and Playmate of the Month April 2013.

Trained on 1.5 model, but the examples are from Analog Madness and Consistent Factor

Textual Inversion of Rosie Huntington-Whiteley

Rosie Huntington-Whiteley is a british model and actor mostly known from her appearances in Transformers 3 and Mad Max.

Trigger word is rosie_hw_TI

v1 was trained with 21 images for 3000 steps

Keyword: Waikiki SG
Checkpoint: analogMadness v40 for all the photos.

Guide to do models like this, Super easy to follow with pictures. > Here <

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..

A commission of @Zorglub.

Chyler Leigh is an American actress, singer and model, mainly known for her roles in TV shows such as Grey's Anatomy and Supergirl.

1020-step TI trained on a dataset of 18 images with my usual settings.

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

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

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 beautiful (chyleigh:0.99), a woman as a movie star, hair upsweep updo, sweater off-shoulders, trousers, at a movie premiere gala, dark moody ambience (masterpiece:1.2) (photorealistic:1.2) (bokeh) (best quality) (detailed skin:1.2) (intricate details) (nighttime) (8k) (HDR) (cinematic lighting) (sharp focus), (looking at the camera:1.1), (closeup portrait:1.1)"

A request fulfilled for a supporter :)

Gina Valentina is a Brazillian adult actress from Rio de Janeiro. She's worked at for major labels in the industry such as Brazzers, Vixen and Tushy.

The embed has been trained on SD 1.5 and works well on most 1.5 based models, though during testing it became clear that low-step sampling rates are not gonna work for the Babes 2.0 model, I recommend at least 30 steps for that model.

If you enjoy my creations and want to support me or have a face you'd like to commission, consider supporting me on Ko-Fi :)

Currently Ko-Fi has suspended my page, which prevents me from responding to supporters using that platform. If you who are reading this and me had unfinished business on Ko-Fi, please consider mailing me at sdkoh@proton.me instead so we can stay in touch untill this has been resolved.

HannahOWO aka NotAestheticallyHannah is a Twitch streamer, Onlyfans model and TikTok celeb.

Created this before realizing there's already a solid looking LORA model published by Shurik. Consider this an alternative take, with more focus on face shape and less on details like piercings! 😅

Here is my first try at making a TI. Inspired by the great work of @JernauGurgeh, @ElizaPottinger and many others.

Lani Todd, model, hair stylist, and Playmate of the Month December 2002. It was trained on 1.5 base model, but the example pictures are from AnalogMadness, & Consistent Factor Euclid.

As you might suspect with a Playmate, the TI skews NSFW, but there is enough training that putting her in clothes is not much of an issue.

Please let me know what you think. Any Feedback is super useful.

When used in a prompt, the women will be in jeans and heels. SD does it easily if put it in the prompt but sometimes, TI models refuse to comply. This TI when used with other TI will help if you want your models wearing jeans and heels. Still new at doing things like this. If you have any suggestion on decent online howto for clothing concepts and please comment.

Info about the person:

Julian Titanium is an Instagram fitness trainer.

Note about the model:

This model was requested from here. He likes to be topless, so be careful.

To request a Textual Inversion:

It's too hot on Civitai, feel free to get me a drink!

Retired JAV star -- Working Courtesan

This ti was requested by @es69

Aliya Wolf is an American model known for her work in the late 1990s and early 2000s. She gained recognition as a Playboy Playmate of the Month in February 2004.

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

early attempt at training a pattern, it likes white objects to impart its blue pattern onto.

but can add itself to other objects too.

single training image.