Kiana Davis is a model and social media personality with more than 1M followers on TikTok.

2100-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 (k1d4vis-2100:0.99), a woman, RAW, close portrait photo, long brown coat, (turtleneck sweater:1.2), trousers, curly hair, (high detailed skin:1.2), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3 sharp focus, f 5.6"

[This is a request] Katy perry

Key word: Katy perry

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..

Jasmine, known as The Jazzy Golfer, is an English Presenter, Social Media Influencer and Women's Golf Advocate. She can be found on YouTube or Instagram, where she has over 60k followers! And she hosts CNN's "Living Golf."

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

Chinese bridge (拱桥)

lora用处：中式拱桥

建议配合: hanfu https://civitai.com/models/15365/hanfu

More embeddings : https://www.deviantart.com/fantasyhot/subscriptions/962601398

Erica Durance is a Canadian actress known for her roles as Lois Lane on the superhero television series Smallville (2004–2011) and as Dr. Alex Reid on the medical drama series Saving Hope (2012–2017)

A favorite actress of mine and I primarily used images from her Smallville days to train with. Hope to see what everyone comes up with using this TI so until next time!

More embeddings : https://www.deviantart.com/fantasyhot/subscriptions/962601398

More embeddings : https://www.deviantart.com/fantasyhot/subscriptions/962601398

More embeddings : https://www.deviantart.com/fantasyhot/subscriptions/962601398

Sara Patricia Pascoe is an English actress, comedian and writer. She has appeared on television programmes including 8 Out of 10 Cats Does Countdown for Channel 4, QI for BBC and Taskmaster for the digital channel Dave.

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

This Textual Inversion is made for make HDR like effect.

This is made for working with Easy Photorealism TI

Because is trained with some b&w photo, on some concept you get b&w result.

Down Weight value on these concept maybe help.

Lizz Adams is an American actress of South Korean desecent and can also be found on Instagram. She has almost 20k followers.

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

Just an attempt to train the 80s model "Maria Whittaker" as textual inversion.
Have fun!

Karalea Pleau-Pior is a Tiktoker with over 2 million follwers. She also has an an Instagram with just over 340k followers.

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

Hanako Montgomery is a reporter for VICE World News. She also has an an Instagram with just over 11k followers.

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

I needed an Erich Zann (known from Lovecraft's story - The Music of Erich Zann) for some of my projects. So here we are.
Trained on SD 1.5 with 25 handpicked images I've generated with Deliberate V2, which means no real world likeness has been used.

Works well with realistic and general models. I also recommend to use the Detail Tweaker LoRA to add even more wrinkles.

Based on classic race queens from 2000s-2010s

Place in negative prompt field. DO use negative_prompt with a VERY strong negative TEXT prompt- DO NOT use on its own. DOES NOT combine well with other bad image negative embeddings. DOES work with bad hands v5 on standard sd 1.5 and haven't tested anything on other sd models.

Liv Tyler is an american actress best known for her role as Arwen in the Lord of the Rings Trilogy.

The embed has been trained on SD 1.5 and works well on most 1.5 based models.

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

Courtney Halversen

Courtney is an American television actress

This is a textual inversion, if you'd rather have a LoRA of Courtney, 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, 4100 steps, v/s .199 ]

Lula Cipher is a person who doesn't exist. You can use her if you need a consistent character. She has a tendency to wear hoop earrings (because her creator forgot to caption them!), so you may need to stick "earrings" in your negative prompt. I might re-train to remove them in future.

Please have a look at other Nobody models for contributions by other folks including those created with the LastName and NBDY tags.

Follow me if you'd like to be notified of future models!

Installation

To install, download the .bin file and then place in the stable-diffusion-webui/embeddings/ folder. Then you'll either need to restart WebUI or tap the Refresh button in the Textual Inversions tab in the Extra Networks tab.

To Use

The trigger word is LulaCipher which you can use in your prompt. See the gallery below for some examples.

A note about what I use to generate images

• My main go-to photorealistic model is Avalon TRUVision V2 but I also might use RealisticVision 2.0, Protogen Infinity, or HARDBlend

• Many of the images in the gallery use TRUVision for the initial txt2img and then RealisticVision/Protogen for a quick img2img pass with denoising set to .10 - .15 to add some additional skin texture. Unfortunately that first generation information isn't embedded into the PNG.

• I always use the vae-ft-mse-840000 as my VAE. You can find it at HuggingFace. You can enable the VAE dropdown menu in WebUI by going to Settings -> User Interface -> Quicksettings list and adding "sd_vae"

• When I use Hires Fix to upscale I usually use 4x-UltraSharp for the Upscaler and enable Tiled VAE which is part of the Multidiffusion Upscaler package

• If I upscale even further in img2img I'll use a combination of ControlNet 1.1's tile_resample/tile model and Ultimate SD Upscaler

[This is a request] Karen gillan

Key word: Karen gillan

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..

XXLayna Marie

XXLayna is an adult film star with a ridiculous name - lazy, really.

This is a textual inversion, if you'd rather have a LoRA of XXLayna, 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, 4000 steps, v/s .200 ]

Lyra Law

Lyra is an adult film actress

This is a textual inversion, if you'd rather have a LoRA of Lyra, 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 .200 ]

Lily Larimar

Lily is an American adult film star.

This is a textual inversion, if you'd rather have a LoRA of Lily, 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, 4100 steps, v/s .199 ]

Cadey Mercury

Cadey is a magnificent adult film superstar

This is a textual inversion, if you'd rather have a LoRA of Cadey, 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, 4700 steps, v/s .201 ]

kinda looks like her. A fashion model turned actress, then business women.

Learn how did I trained this embedding on Gumroad

A StableDiffusion 2.1 Pastel style embedding

delicately enhance your model with some pastel touches ! Really good when it comes to objects or architecture.

Can bring some really cool lofi vibes aswell

I would suggest forAnalogPortrait for a really strong digital/painting antagonist, and Neg - Contrast if you want a less pruned/heavy negative. For both negatives, colors will have reduced vibrancy

Note : demo pictures was generated from Providence - Anchor.

Happy tuning everyone !

romerorz.art - Twitter - DeviantArt - Gumroad

Helper for splatter.

Using it at start of prompt.

Weight it for different result.

A commission of @Zorglub.

Dominique Tipper is a British actress, dancer and singer mostly known for her role as Naomi Nagata in the TV sci-fi show The Expanse.

This one trained fast... It's a 600-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 (dt1pper:0.99), a woman, RAW, close portrait photo, long brown coat, (turtleneck sweater:1.2), trousers, slim body, (high detailed skin:1.2), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3 sharp focus, f 5.6"