Textual inversion helper for eyeglasses

Use it with weight. Adjust in accord with your cfg scale

See sample image for better understand.

Zoë Isabella Kravitz is an American actress, singer, and model. I got to know her from her role as Catwoman in Batman 2022.

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

This is a textual inversion trained to get oliy/wet result.

Use it with weight.

Use with wet, oily , wet-skin, oily-skin make it more power.

A textual inversion for work in 2 side:

in positive make old subject

in negative make young subject.

27 year old American pornstar.

This ti was requested by @webman240130

Allie Dunn is an instagram model with over 428K followers.

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

Just an attempt to train smurfs :)
It's far from perfect, but maybe you like it ;)
Add "Smurfling" to your prompt.
e.g.: "a photo of a tiny smurf (Smurfling:1.0)"
Have smurf!

its a view about salak mountain that located in indonesia

Milana Aleksandrovna Vayntrub (born March 8, 1987) is an American actress, comedian, and activist. Born in the Soviet Union to Jewish parents, she began her career as a child actress shortly after immigrating to the United States. She came to prominence for her appearances in AT&T television commercials as saleswoman Lily Adams from 2013 to 2016 and since 2020. In addition to her commercial appearances, she was a series regular on the Yahoo! Screen science fiction comedy Other Space (2015) and had a recurring role on the NBC drama This Is Us (2016–2017). Vayntrub has also voiced Squirrel Girl in the Marvel Rising franchise since 2018 after being cast as the character in the unaired television pilot for New Warriors.

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

Embedding of pornstar Julia Ann.

Standard weight

Clip Skip 1

7 CFG

DPM++ 2M KARRAS 30 steps

Upscale through hires fix or Controlnet 1.1 tiles

I developed this age slider to work with my Children's Stories model. Some Stable Diffusion models have difficulty generating younger people. This embedding will fix that for you. It can make anyone, in any Lora, on any model, younger. Even animals and fantasy creatures.

Follow me to make sure you see new styles, poses and Nobodys when I post them. Things move fast on this site, it's easy to miss.

How to use:
Just use one of the positive prompts listed to get the desired results. Use them at strength of 1. That means to put them at the beginning of your prompt or make sure they have the appropriate modifier brackets. Example, for automatic1111 it would be (AS-Younger) or (AS-Younger:1.0). They are stackable, so you can combine them together to help with stubborn models. A negative embedding is also included for extra brute force if needed. There are 4 files to download, check the version tabs at the top.

• AS-Young-Neg: Place in your negative prompt at strength of 1.0 to 1.3

• AS-Young: Place at the beginning of your positive prompt at strength of 1.0 to 1.3. Conceptually teenager, may vary by model, lora, or prompts.

• AS-Younger: Place at the beginning of your positive prompt at strength of 1.0 to 1.3. Conceptually child, may vary by model, lora, or prompts.

• AS-Youngest: Place at the beginning of your positive prompt at strength of 1.0 to 1.3. Conceptually toddler/baby, may vary by model, lora, or prompts

• AS-Older: (coming soon)

These are the concepts for the embeddings. Some models, character LoRAs, or embeddings might be too rigid, so increase strength or stack on multiple to get the desired result. Additional prompts may help as well.

Do you have requests? I've been putting in many more hours lately with this. That's my problem, not yours. But if you'd like to tip me, buy me a beer. Beer encourages me to ignore work and make AI models instead. Tip and make a request. I'll give it a shot if I can. Here at Ko-Fi

A request by @vincentshaw. Took me a while to get it done.

Similar to my Kim Kardashian model, most models already have an idea of how Kendall looks like, but an embedding provides consistency.

The embed has been trained on SD 1.5 and works well on most 1.5 based models. There is a tendency for images to have her looking over her shoulder.

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

Has a mind of its own. Just made it on around 25 images I generated, there were no text or artist names on them but I think I used way too many (32) tokens for the embedding and it insists on putting a tag in the bottom left in the images I have made with it so far. lol, also I changed the style text and I do not know what I am doing at all hardly quite yet. I suggest using art by (cosmicnouveau:0.3) above 0.5 it just does what it wants completely. Use under 15 cfg and rather high steps probably 45+ or who knows. Made the images on my own merge model neurocontrastdream but it has models that say not for commercial use in it so I assume the ti is also not for commercial use sorry.

Key word: DotD

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..

An 8 vector embedding trained on the style of a particular Japanese artist, trained on the NAI model.

A commission of @Wiggyfreak1.

Mai Mizuhashi (aka MARiA) is the singer of Garnidelia, a J-pop duo. She's also a model, dancer and costume designer.

1200-step TI trained on a dataset of 18 images (most of them provided by @Wiggyfreak1) 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 (marigarn:0.99), a woman, RAW, close portrait photo, knitted sweater, choker, hair updo, slim body, (high detailed skin:1.2), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3 sharp focus, f 5.6"

Luna Bijl

Luna is a Dutch fashion model

This is a textual inversion, if you'd rather have a LoRA of Luna, here you go!

You can learn more about my process in my blog post HERE

I can create a custom Textual Inversion or LoRA just for you!

Do you like my work? Buy me a beer!

[ SDv1.4, 4e-03, 4300 steps, v/s .201 ]

Samaria Relagado

Samaria is an American model and actress.

This is a textual inversion, if you'd rather have a LoRA of Samaria, here you go!

You can learn more about my process in my blog post HERE

I can create a custom Textual Inversion or LoRA just for you!

Do you like my work? Buy me a beer!

[ SDv1.4, 4e-03, 4800 steps, v/s .201 ]

Luanna Perez

Luanna is a Peruvian fashion and lifestyle blogger

This is a textual inversion, if you'd rather have a LoRA of Luanna, here you go!

You can learn more about my process in my blog post HERE

I can create a custom Textual Inversion or LoRA just for you!

Do you like my work? Buy me a beer!

[ SDv1.4, 4e-03, 4200 steps, v/s .199 ]

Elizabeth Ai-Quyen

Elizabeth is a Canadian model and photographer.

This is a textual inversion, if you'd rather have a LoRA of Elizabeth, here you go!

You can learn more about my process in my blog post HERE

I can create a custom Textual Inversion or LoRA just for you!

Do you like my work? Buy me a beer!

[ SDv1.4, 4e-03, 4800 steps, v/s .201 ]

This model looks resembles Susan Misner.

Please use Responsibly.

Initialy I tried to train a real person (not known and not a public person) but with a small dataset with medium-low quality and one day I had this result. Amazing for me as I got her eyes, nose and retro style in general. Can work good with simple prompts but much better with more elaborated one as usual.
Tested with Liberty and Deliberate

That Eurasian Chick or simply Zara, is variety streamer on twitch with almost 12k followers, she also is on youtube and Instagram.

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

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

Sheila Nazarian is an Iranian-American plastic surgeon and television personality. On her Instagram she has over 857k followers.

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

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

squidinkidink or simply Syd, is Content Creator with over 130k followers across Twitch, were she streams with star of the show Planky, and Instagram.

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

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