A commission of @Zorglub.

Shohreh Aghdashloo is an Iranian/American actress, mainly known for her role in the sci-fi TV show The Expanse.

Updated: Apologies for the quick update, but I misjudged step 1200 at first and it seems actually better than the previous version. :)

1200-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 (sh0hreh:0.99), a woman, closeup zoomed in tight crop portrait, sitting at a (table on a seaside boardwalk cafe bar drinks cocktails:1.2) wearing a (sexy sweater off-shoulders:1.3) (drinks on table:1.3) (Lighting-Gold:1.2) foreground objects background details (masterpiece:1.2) (photorealistic:1.2) (bokeh:1.2) (best quality) (color grading) (detailed skin:1.3) (intricate) (8k) (HDR) (cinematic lighting:1.3) (sharp focus)"

Caroline Catz

English film actress

27 year old Russian cosplayer.

A textual inversion embedding for generating virgin killer style clothing.

Use Tips

Add vksw34t1 to prompt.

Change color by adding something like black outfit, yellow outfit to prompt.

Write nipples in negative to lower chances of it making exposed breasts.

Write anime, cartoon to negative to generate realistic images.

Rosie Jones (Middlesex, july 19th, 1990) is a british model. She is know by her appearances in the third page girl of the journal The Sun and for her work in magazines for men.

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

Info about the person:

Dwayne Douglas Johnson, also known by his ring name The Rock, is an American actor, film producer, and former professional wrestler.

Note:

If you have a preference for LoRA over Embedding or if you wish to blend the two for improved outcomes, there is a fantastic LoRA created by @dogu_cat, available here.

To request a Textual Inversion:

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

Based on classic race queens from 2000s-2010s

A textual inversion embedding for generating clothing with cameltoe pussy.

Use Tips

Add c4m3lt0 to your prompt.

Add anime, cartoon to negative to make realistic images.

Nastassja Kinski is a German actress and former model, known for roles in many films, including Tess (for which she won a Golden Globe) and Paris, Texas. With this embedding I've tried to capture her looks in the 80s and 90s.

This is 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 (nk1nsky:0.99), a woman, closeup zoomed in tight crop portrait, sitting at a (table on a seaside boardwalk cafe bar drinks cocktails:1.2) wearing a (button shirt:1.3) (drinks on table:1.3) (Lighting-Gold:1.2) foreground objects background details (masterpiece:1.2) (photorealistic:1.2) (bokeh:1.2) (best quality) (color grading) (detailed skin:1.3) (intricate) (8k) (HDR) (cinematic lighting:1.3) (sharp focus)"

Frivolous Fox

Frivvy is an American ASMRtist, YouTuber, and Twitch gamer. She has amlost 2 million You Tube subscribers and well over 10 billion views.

If you like my work, I'd appreciate it if you could Buy me a beer!

If you are interested in my creative process, you can read more in my blog post HERE.

And if you're feeling particularly curious, I can create a custom Textual Inversion or LoRA just for you!

[ SDv1.4, 4e-03, 4500 steps, v/s .199 ]

Creates all different variety of masks, helmets, face/head coverings. Comes with a lot of extra details!

This ti was requested by a friend of mine who is a fan of hers.

Jackie Redmond is a sports commentator, games commentator, producer, and reporter. She currently works for both NHL & WWE. Her IG has over 139k followers.

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

建筑样式的textual inversion版本，需要大模型有才能召唤出来

介绍：

为什么：多个lora配合非常容易出错，但是Textual Inversion可以很好一起工作

例如：changting, heibai, (1girl:1.21), solo

主要模型：

changting: Chinese bridge (中式拱桥)

gongqiao: Lake and Pavilion(湖和亭)

guzhen: Chinese ancient town(古镇)

其他：

安装：放到 stable-diffusion-webui\embeddings

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

English：

The textual inversion version of the architectural style requires a large model to be summoned

Why: Multiple lora coordination is very error-prone, but Textual Inversion can work well together

For example: changting, heibai, (1girl:1.21), solo

changting: Chinese bridge

gongqiao: Lake and Pavilion

guzhen: Chinese ancient town

Suggested cooperation: hanfu https://civitai.com/models/15365/hanfu

Installation: Put it in stable-diffusion-webui\embeddings