Trouvez ce dont vous avez besoin pour votre flux de travail.

Maddie Jean MXAI

Maddie Jean does not exist, but has been created for your pleasure. She can be a bit of a minx, but don't worry, she has no soul. And not because she's a redhead.

Daria MXAI, Supermodel

Daria and Daria2 are a bit of an experiment in how different body types affect training. Daria is skinny like a heroin-chic supermodel, whereas Daria2 is more in the Playboy model category, but they do have quite...

Signe Larsson MXAI SD 1.5, SDXL & Pony

A lovely woman who doesn't exist. Plays nicely with Pony. While there is a strong resemblance between this one and Sigrid, they aren't the same mode, but more of a test to see which words changed them when I prompted...

Joker The Movie Style Embedding

This textual inversion is not focused on Joker as a subject, but rather on visual style, colors, and lighting. There are two ways to use it:

Shadowverse Kyrzael, Killshot Enforcer / 弾哭の執行者・キルザエル (シャドウバース)

Train based on AnyLora model. Training resources include official arts , leader's spine animations and some fanarts from Shadowverse.

Keira : The Alluring AI Mistress

Keira is an AI model crafted to embody elegance, dominance, and sensuality. Her creations exude an irresistible allure blending seductive charm with commanding presence. Perfect for generating sultry portraits,...

Alice Nakiri (LOCON version) - Shokugeki no soma

This is the LOCON version of my Alice Nakiri LORA . The Nakiri cousins are hot, especially the Mix Fry version of them. Sadly i had to pad the dataset with screencaps otherwise i wouldn't get enough color stuff....

Zola Vicious

ZOLA VICIOUS Zola is a professional didgeridoo maker from Australia (Kangaroos not Mozart) and obviously part of the gigantic Vicious family. They are nice people and gave birth to a lot of pretty daughters, the best...

KOH Minagi / 海凪コウ【KOH】 Style

If the original artist requests a takedown, I will immediately remove this model off of CivitAI. Thank you. Please support their work here. Meanwhile, please do not monetize your generations.

Lilith Calah - Dreamkeepers

Character belongs to David & Liz Lillie Dreamkeepers Graphic Novel Saga - Support Dreamkeepers on patreon -

[SDXL] Artist Style: Tokkyu

SDXL LoRA/LyCORIS works best on the model that it was trained on. I will release multiple versions for a few popular models. Feel free to request for artist or model.

AG: Bael - Midjourney Realistic Style

Ars Goetia is series of loras made on a whim, on variety of images, made from mix of Midjourney, Tumblr, NijiJourney and many more things. Each Demon brings something different. Quality might vary between loras -...

[PonyV6 XL DoRA] Vivid BAD SQUAD Miku | Project SEKAI COLORFUL STAGE! feat. Hatsune Miku

This is a DoRA , not your typically made LoRA . A1111 v1.9.0 and up is required to use this. Forge users must download two files, which can be found here . Go to stable-diffusion-webui\ldmpatched\modules and replace...

[IllustriousXL v0.1 GLoRA] Channel (_CastStation) Animation Style

If the original artist requests a takedown, I will immediately remove this model off of CivitAI. Thank you. Please support their work here. Meanwhile, do not monetize your generations.

Evina Mix

So I wanted to do something different and take all these different images I’ve collected in different trainings and create something. This became the Mix person series.

Vetehine ┃ Plastique (ILL & ANM)

moescape.ai is the primary home of this model and a broader collection of additional models. Many of these releases are exclusive to this platform and are not available elsewhere. More information and related work...

Very approximately Japanese / 日本っぽいぐらい(かな)

I was training a model with kimonos, and this came out in the first training steps, it is as vaguely Japanese as possible.

Vash the Stampede - Trigun (2023) - (LyCORIS/LoCON)

Decided to try and train this on AnyLoRA (found on this website). This is a LoCON, so please install the appropriate extension to be able to use it.

Semi-Realistic Concept Render - [STYLE] [LORA] [FLUX]

Latest page update: Updated recommended workflow again to a version 2, which is slightly even better.

K-beauty

I asked grok to describe a reference Korean beauty, and then, based on this description, I generated a dataset, which I used to train LORA, using the main points of the description as trigger words. You can see the...

LORAAnima