27 year old Russian nude model.

A request of @Bzas76. Sorry I couldn't work with an older dataset, mate, but I hope you'll like this one!

India Reynolds is a British model and social media celebrity, known for her recent stint in Love Island, among other things.

Update: Retrained from scratch, since my work process has changed quite a bit since I did this TI. I think the previous version, even if it was only a 200-step one, was very good, but perhaps slightly less accurate than desired. India looked gorgeous in almost every pic, though, which is why I was hesitant to update the model. I think this new version (2.0) captures her looks better without losing terrain in terms of beauty.

This new version is a 1000 step TI, trained on a dataset of 18 images.

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 (1nd1areyn0lds:0.99), a woman, RAW, close portrait photo, long brown coat, turtleneck sweater, 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".

Trained using v1-5-pruned-emaonly

This person does not exist.

Katherine Victoria Litwack (born June 13, 1986), known professionally as Kat Dennings, is an American actress. She is known for her starring roles as Max Black in the CBS sitcom 2 Broke Girls (2011–2017) and as Darcy Lewis in the Marvel Cinematic Universe superhero films Thor (2011), Thor: The Dark World (2013), Thor: Love and Thunder (2022), and the Disney+ miniseries WandaVision (2021).

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

Actress/Model Persis Khambatta

This is a textual inversion of actress/model Persis Khambatta, best known for her role as the bald-headed Deltan navigator in Star Trek: The Motion Picture. She was born in Bombay, India, and was Miss India in 1965. She also had roles in movies such as Nighthawks and The Wilby Conspiracy (with Michael Caine and Sydney Poitier). She is also distinguished as the first Indian female performer to present an award at the Oscars.

I have to say I have a LOT of satisfaction finally posting this TI. I've always thought Persis was a hauntingly beautiful and sexy woman -- sadly, she passed away fairly early in life in the late 1990s. Her beauty remains with us however in a form such as this.

I'm especially glad that this TI came out to my satisfaction (and hopefully yours) as the source material for her imagery is often low resolution or in black and white. I sourced imagery from screencaps of The Wilby Conspiracy (where she has a suspenseful scene as a sexy dental assistant with Sydney Poitier), as this is where I thought she looked absolutely alluring. After a number of tries ending up with monstrosities, I finally was able to get the right settings and training to get some lovely generation going.

Let me know how you like this TI. I might give yet another go at a V2 later, or learn to do LoRAs and then try that.

Note: I don't know if this embedding works for images like NSFW. If you found on Internet an image about these words, it doesn't me or my embeddings.

This is a Stable Diffusion textual inversion about a wrestle, celebrity and model. If you wanna test it, you can put this word on the prompt: theSacs .

PS: The test images was made with 'vainilla' SD 1.5 model. I don't know if works on SD 2.1 .

All days are good with a coffee ;)

Penélope Cruz is a Spanish actress, winner of an Academy Award for Best Actress in a Supporting Role in 2008.

Even though SD recognizes Penélope quite well without the need for a specific embedding, I've always thought the resemblance was quite improvable (as is the case with many celebrities), and that's what moved me to create this TI, which I hope you'll find an upgrade compared to the "default" SD version.

It's a 1000-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 (p3cruz:0.99), a woman, RAW, close portrait photo, sexy pirate outfit, 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, bandana, holding a gun".

Anjelika (Krystal Boyd)

There are at least 10 other names she used, but these are the most common. Needless to say, it wasn't her aliases that made her famous.

Another difficult embedding to make, took me 3 tries to get it right. Her face is sneaky expressive that the AI doesn't pick up on well. If you don't have success getting a good likeness, try a different model.

Do you like my work? Buy me a beer!

[ SD 1.4, 5e-03, 4000 ]

This is a textual inversion trained on pictures of wrestler Charlotte Flair aka Ashley Elizabeth Fliehr. Testing out the results of my ti was really fun, hope you enjoy it, too.

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 :)

34 year old American actress.

________________________

Feel free to support me

Jang Won-young

Jang Won-young also known mononymously as Wonyoung, is a South Korean singer and model. She is a member of Ive and former member of project girl group Iz*One

This is a textual inversion. If you're looking for a LoRA, looky here

Like my work? Buy me a beer!

[ SDv1.4, 4e-03, 4400, v/s .200 ]

A commission of @psytrancehero.

Hailey Leigh is a Canadian adult model. Can't say I know much more about this girl, but I definitely like her looks. ^^

This is a 1500-step TI trained on a dataset of 18 images, partly provided by @psytrancehero himself.

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 (h4il3igh:0.99), a woman, RAW, close portrait photo, sexy star trek uniform, trousers, 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, red lips".

Selena Gomez

Selena is is an American singer, actress, producer, and businesswoman. I remember her from Barney, but not much after that. I hope she's doing well.

This is a textual inversion. If you'd rather have a LoRA of Selene, I got you.

Like my work? Buy me a beer!

[ SDv1.4, 4e-03, 3800, v/s .200 ]