This is a standard negative textual inversion for fast photo result.

Use it in your negative.

Better result with photo terms in your positive.

This is powered for photo, so if you want other type of art, use this.

See sample for know how it work.

Gibi ASMR

Gina Klein, known professionally as Gibi ASMR, is an American ASMR performer, YouTube personality, Twitch streamer, and cosplayer.

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 ]

Fast Negative Embedding

Token mix of my usual negative embedding. This way it's faster to use and easier to reproduce.

I'm also working on a much stronger one that doesn't preserve styles but it's good on base models without style loras applied. I plan to upload it during the next week, so be sure to leave a ❤️ to be notified of future updates.

This is very much a work in progress, but since I'm already using it in examples, I thought I should upload it.

It should keep styles on all my style loras. If not please tell me in the comments.

Of course, don't use this in the positive prompt.
This includes Nerf's Negative Hand embedding.

Taylor ASMR Darling

Taylor, also known as ASMR Darling or simply Darling, is an American ASMR creator, Twitch streamer and YouTuber known for making ASMR videos

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, 4700 steps, v/s .199 ]

27 year old American pornstar.

Requested by @Zorglub!

Dominique Provost-Chalkley is a British-Canadian actress, activist and songwriter best known for playing as Waverly Earp in the supernatural Western horror Wynonna Earp. Dominique also played the role of Zrinka in Avengers: Age of Ultron.

As usual, the embed has been trained on SD 1.5 and works well on most 1.5 based models for which it has been tested. There is a chance that Stable Diffusion makes something weird of the nosebridge, it shouldn't happen often but if it does, changing the sampling steps or inpainting will fix it.

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

This is a NEGATIVE embed worked for keeping your prompt consistent.

It work in different type of model.

It's made because some negative waste the prompt concept.

Giving review if you try is appreciated. Show error and maybe where it waste your prompt is suggested to work in future update.

Sorry for image without data, don't know why, but civitai stripe out data where emoji is used.

Sara has many looks. This one is of her in the 9th season of Endeavour. She has photos of when she was a model and she looks way different. And she does her makeup different for the show. I have tried to stay with one style. So this may be not the model your looking for.

一些衣服样式

更容易使用的衣服召唤方法

这个版本会持续更新

为了不太干扰出图的泛化，向量为1，如果需要增强权重可以这样写 (heibai:1.30), 1girl, lace,

heibai: 黑白搭配

longpao: 刺绣样式

neiyi: 内衣样式

English

some clothing styles

Easier to use clothing summoning method

This version will continue to be updated

In order not to interfere with the generalization of the graph, the vector is 1. If you need to enhance the weight, you can write it like this (heibai:1.30), 1girl, lace,

heibai: black and white collocation

longpao: embroidery pattern

neiyi: underwear style

Leah Winters

This ti was requested by @johntable

Charlotte Ritchie is a British actress and singer. She is best known for her roles in popular television shows such as "Fresh Meat" and "Call the Midwife." Ritchie has also showcased her singing talents as a member of the British a cappella group, The Puppini Sisters.

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

Eva Jacqueline Longoria Bastón (March 15, 1975) is an American actress, producer, and director. After a number of guest roles on several television series, she was recognized for her portrayal of Isabella Braña on the CBS daytime soap opera The Young and the Restless, on which she starred from 2001 to 2003. She is most known for her role as Gabrielle Solis on the ABC television series Desperate Housewives, which ran from 2004 to 2012, and for which she received Golden Globe and Screen Actors Guild Award nominations. She has also appeared in The Sentinel (2006), Over Her Dead Body (2008), For Greater Glory (2012), Frontera (2014), Lowriders (2016), and Overboard (2018). From 2015 to 2016, she starred as Ana Sofia Calderón on the short-lived NBC sitcom Telenovela, and was an executive producer for the Lifetime television series Devious Maids. She has also been an executive producer of social issue documentaries, including Food Chains and The Harvest.

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

TI made for getting something like comic page.

Key word: Jessicalou SG

Using analogMadness v40 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..

Key word: Asia SG

Using analogMadness v40 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..

Key word: Gloom SG

Using analogMadness v40 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..

A textual inversion embedding for generating fishnet stockings.

Use Tips

Add n3tst0 in your prompt.

Customize outfit by adding more clothings in prompt such as wearing n3tst0, denim shorts, wearing n3tst0, leather skirt etc

Alexandra Botez is a Canadian chess player and streamer, and the older sister of Andrea Botez.

Update: Retrained from scratch, as this was a very old TI and my process has changed quite a bit since I created it. I think the previous version was good, but probably not as accurate as I would have desired. This new version resembles Alexandra more, I would say. I'm not totally convinced with her hair tonality, but that's easily fixable through prompting. I might revise the dataset in the future to try to solve the issue, but there's just not much good material online of hers, unfortunately.

This version is a 1500-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 (4l3xbotez:0.99), a woman with black hair, RAW, close portrait photo, long brown coat, turtleneck, long haircut, slim body, (high detailed skin:1.2), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3 sharp focus, f 5.6"

Key word: Melissa SG

Using analogMadness v40 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..

Key word: Skella SG

Using analogMadness v40 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..

Key word: NinaQ SG

Using analogMadness v40 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..

Key word: Zzef SG

Using analogMadness v40 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..

Key word: Fairy SG

Using analogMadness v40 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..

Key word: Almendra SG

Using analogMadness v40 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..

Key word: Fishball SG

Using analogMadness v40 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..

Key word: Jelly SG

Using analogMadness v40 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..

Key word: Satin SG

Using analogMadness v40 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..

This is part of some FX Textual Inversion i've made.

use it in top of prompt and weight it for different result.

For the concept is good using simple prompt.

Also work good for empathize cinematic scenary.

See sample image, for understanding what i mean.

(sorry for copy-paste description, but the FX series work's all at the same, so description is the same).

This is part of some FX Textual Inversion i've made.

use it in top of prompt and weight it for different result.

For the concept is good using simple prompt.

Also work good for empathize cinematic scenary.

See sample image, for understanding what i mean.

A commission of @psytrancehero.

Delaia González is a Spanish model with a decent following on Instagram and other social media. She specializes in "art nude" modelling.

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 (d3laia: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)"

Evelyn Lin - Twitch streamer, adult performer

One of the best known Asian American adult performers of the early 2000s. She's moved on to Twitch streaming now though she still does some modeling for car shows.

This TI should work well with most realistic models.

edit: I released a version 2, trained on the same imageset but left upscaled to 1024x1024. It seems to capture more detail, seems to work better for upscaling.

Anne McAlpine is a British television and radio presenter and known for her engaging style and warm demeanour, she has become a trusted voice in broadcasting. From hosting shows on BBC Radio Scotland to delivering insightful reporting on Reporting Scotland and Landward, Anne McAlpine has stood out from the crowd in the industry, making a real impact with her fire and determination.

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

Will try again when I have more data.

❗v1 = 10 tokens❗

❗v2 = 20 tokens❗ !The version has almost no effect, I use ussrv3!

❗v3 = 35 tokens❗

Rus (below in english)

Приветствую, товарищи, эта модель создана для генерации анимешных или полу-анимешных артов около советской тематики, она хорошо работает с чекпоинтами RevAnimated и AOM3, а вот deliberate выдаёт слабенькие 2д постеры.

Не стесняйтесь добавлять более подробное описание

У модели есть три версии: USSR, USSRv2 и USSRv3.

👇🏻👇🏽👇🏿

Первая модель обучена на 10 векторах, вторая на 20, а третья на 35. То есть v1 не всегда лучше v2 или v3!

Соответствующее количество токенов они будут занимать. Результаты у них схожи но я бы предпочёл USSRv3, также я пробовал ставить 75 векторов но результат мне показался неудовлетворительным и я даже не стал заливать это сюда.

Если вы знаете как улучшить этот эмбединг обязательно напишите в коментах! В дальнейшем я продолжу изучать токены сея тематики и соответственно обновлять модель.

Eng

Greetings comrades, this model is created to generate anime or half-anime art around Soviet themes, it works well with RevAnimated and AOM3 checkpoints, but gives weak 2d posters with Deliberate.

The model has three versions: USSR, USSRv2 and USSRv3.

👇🏻👇🏽👇🏿

The first model is trained on 10 vectors, the second on 20, and the third on 35. The corresponding number of tokens they will occupy. The results are similar but I would have preferred USSRv3, I also tried to put 75 vectors but I found the result unsatisfactory and didn't even upload it here.

If you know how to improve this embedding be sure to write in the comments! In the future I will continue to study the tokens of this theme and update the model accordingly.