Star-Lord (Peter Jason Quill) is a fictional character and superhero appearing in American comic books published by Marvel Comics.

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

A textual inversion embedding for generating straitjacket bondage.

Use Tips

Add str41tj4ck3t in your prompt.

Customize it by writing something like "wearing white linen str41tj4ck3t"

28 year old Russian nude model.

Appreciate my work? Can you buy me a coffe please :) , If you want to know any of my models visit me at here

Monica Maria Raymund: (born July 26, 1986) is an American actress, known for her roles as Maria "Ria" Torres in the Fox crime drama Lie to Me (2009–2011), Dana Lodge in the CBS legal drama The Good Wife (2011–2012), Gabriela Dawson in the NBC drama Chicago Fire (2012–2019) and Jackie Quiñones in the Starz crime drama Hightown (2020–present).

Used model: Realistic Vision v1,3

recommended parameters:

Prompt:

RAW photo, a close up portrait photo of 26 y.o woman in wastelander clothes, long haircut, pale skin, slim body, background is city ruins, (high detailed skin:1.2), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3

Negative Prompt:
(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck

QR to my page buymeacoffee

(This is a commission I received through my website.)

Vicki Li is an American model and social media personality with 1.3M followers on Instagram.

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 (v1ck1li: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)"

This is an Helper Pack for triggering season option.

Use it in top of prompt for better result.

In the sample i have use same prompt for all image, by changing season trigger word.

Trigger word:

kkw-Spring

kkw-Summer

kkw-Autumn

kkw-Winter

Rus

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. 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.

This textual inversion is based on Smart Doll created by Danny Choo.

Because most character are female, is difficult getting male and creature characters. Some times weight it help.

Use it with Easy Photorealism for better result.

Update May 18th added Older Negative

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 for younger, and 4 for older, check the version tabs at the top.

These embeddings make people/creatures/characters younger.

• AS-Young-Neg: Place in your negative prompt at strength of 1.0 to 1.3, generally removes adults from the scene.

• 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

These embeddings make people/creatures/characters adult or older.

• AS-Adult-Neg: Place in your negative prompt at strength of 1.0 to 1.3. This will remove any young people and/or youth from the scene.

• AS-Adult: (Coming Shortly)

• AS-MidAged: (Coming Shortly)

• AS-Elderly: (Coming Shortly)

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

Exusiai, my first successful embedding. Trained over 16 images. Please give feedback if you have issues.

Cara Gee

Meiyu 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 for Automatic1111's webui is MeiyuCipher which you can use in your prompt. (It should be <meiyucipher> for InvokeAI). 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 the work that I have put the most effort into, with a very rich and varied tongue stretching action. It took almost three months from preparation to training. In the future, I will consider continuing to train the iterative version to increase the weight of this EMB, in order to cooperate with some poorly trained or poorly generalized characters EMB or Lora and also be able to stick out their tongues well.

这是我花费精力最多的一个作品，具有非常丰富多变细节的伸舌头动作。从准备到训练花费了几乎3个月的时间。后续会考虑继续训练迭代版本来增加该EMB的权重，以达到和某些训练不好或泛化差的人物emb或lora配合也能伸好舌头。

800 Step TI

Kylie Minogue is an Australian singer and actress who rose to stardom already in the late 80s. She's often referred to as the Princess of Pop and is one of the best selling artists of all time. With this embedding I'm trying to capture her looks in the late 80s and early 90s era.

Updated: So... I was having a look at my Tiffany Keller TI, one of the first I published on this site, and I was a bit amazed at how good it still looked. I ran a few tests and man, even if there are some issues (I still upscaled the pics for my dataset back then, and it shows in a little bit of saturation and some slight problems with the eyes)... almost every image I generated with that TI looked awesome, to be honest. I wondered why... What was the main difference compared to my current embeddings? The only possible answer was the vector strength, which in Tiffany's TI case was of 0.198. The perfect vector strength, basically. But how did I manage such vector strength with only 1500 steps, I asked myself... Well, again, there was only one possible answer: the learning rate was way different back then. It was a flexible one and, apparently, it quickly pushed the vector strength much higher than my most recent settings do.

So I decided to try to apply that learning rate to Kylie and stop the training process at 1500 steps. Vector strength is slightly over 0.2, but yeah... the results look great, in my opinion, so I'm probably sticking to this new process from now on. :)

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 (t3stkyli3:0.99), 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"

Christine Lampard is a television presenter and personality from Northern Ireland. She gained fame through her work as a presenter on various TV shows in the United Kingdom. Lampard has hosted programs like "The One Show" and "Dancing on Ice" and has appeared as a guest panelist on talk shows.

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

This is a textual inversion model for character caraVoxel. To use just place file in your embeddings folder and use term "caraVoxelSd15" to call it in your prompt. I generated all my sample images with deliberate v2 checkpoint and this embedding.

Tina Ivlev

Tina is an American actress who was in some Star Wars things

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 ]

Rachel Zegler

Rachel is an American actress and singer

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, 5100 steps, v/s .199* ]

Alyssa Wapanatâhk

Alyssa is a Canadian actress and a member of the Cree (Nêhiyaw) First Nation.

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, 5100 steps, v/s .201 ]

Trying to copy the blacked_clothing tag from r34. Sadly the text is messed up because stable diffusion does not handle it well. Use your imagination that it works.

Alissa Skovbye

Ali is a Canadian actress and model.

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, 4200 steps, v/s .201 ]

Do you like Nendoroid figures?

Make your own with this Textual Inversion.

This ti was requested by @Neeco

Morgana Robinson is a prominent British comedian, actress, and impressionist known for her remarkable ability to embody and impersonate a wide range of characters. With her incredible versatility and spot-on impressions, Robinson has made a significant impact in the comedy world. She has appeared in various television shows, including "The Agency" and "Morgana Robinson's The Agency," captivating audiences with her hilarious portrayals and comedic timing.

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

Not one of my best train, but sharing ror who like Splatoon.

Use it weighted because seem little overtrained. Maybe it work's better on other models.

📸 The Belinda Face Model is an AI marvel that revolves around the captivating visage of the famous Mexican celebrity, Belinda. 🇲🇽😍 Powered by the stable diffusion version 1.5, all centered around Belinda's beautiful face.

💡 Utilizing Textual Inversion, I've trained the Belinda Face Model to generate stunning and realistic images showcasing Belinda's facial expressions and features.

Imagine generating unique snapshots of Belinda, with her dazzling smile, enchanting eyes, and iconic style. The possibilities are endless! ✨ And remember, with great power comes great responsibility. Let's use this tool respectfully and honor the essence and beauty of Belinda.

This ti was requested by @Neeco

Aisling Bea is an Irish comedian, actress, and writer who has gained recognition for her comedic talent and versatile performances. Born Aisling Cliodhnadh O'Sullivan, she adopted the stage name Aisling Bea for her career. She has appeared in various comedy shows, including "8 Out of 10 Cats" and "Live at the Apollo," as well as acted in television series such as "The Fall" and "Living with Yourself." Aisling has also written and starred in her own comedy series called "This Way Up," showcasing her skills as a writer and actor.

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

22 year old Canadian Influencer.

Also check out her twin sister.

22 year old Canadian Influencer.

Also check out her twin sister.

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.