If you enjoyed this model, why don't you check out my other works? I put a lot of effort into correctly recreating artist styles and making the occasional character LoRA.😊

You can also buy me a Coffee ☕ at https://ko-fi.com/stickyricky or StickyRicky (buymeacoffee.com)

This model was trained using the collab/guide by holostrawberry [Guide] Make your own Loras, easy and free - colabs | Stable Diffusion Other | Civitai

Recommended checkpoint (used in examples):

model.ckpt · a1079602570/animefull-final-pruned at main (huggingface.co)

It also sort of works with AnythingV5 Ink (example post down below)

I am once again open for suggestions for other styles, SFW and NSFW.

You can always drop model suggestions in the comments, both for styles that are missing on civit or those that are outdated. No guarantees but if it interests me I'll give it a go.

The same goes for character LoRA.

About the artist:

Twitter: (1) 米山 舞 Yoneyama Mai (@yoneyamai) / X (twitter.com)

Youtube: Yoneyama Mai - YouTube

Yoneyama Mai is an animator and illustrator who worked on multiple anime including Kiznaiver, Kill la Kill, and Promare as an animation director and character designer. In recent years she has started publishing illustrations that are detailed and visually busy, sometimes utilizing vivid colors, sometimes almost entirely in grayscale.

Illustrations always have a character focus with little to no background and prominently feature fantastical elements and a strong sense of flow, whether visible in the hair, flowers, water or light.

Weights & Prompts

Due to the large variance in available art the model is really unstable.

That also means that hands are almost guaranteed to turn out deformed.

The activation prompt is:

yoneyama_mai

Some more prompts I personally enjoyed using:

floating hair,liquid hair
chromatic aberration, paint splatter, paint
greyscale, spot color
flower, greyscale, blurry
colorful
surreal, abstract

Use a weight of 0.7-1.1, adjust to taste and depending on your checkpoint. If you want to use it for landscapes I recommend going lower as the model will add excessive clutter.

As usual I have included an XYZ plot for reference.

For this one in particular I'd like to see what other people can make. Using different elements, mechanical parts, skeletal characters,

Please leave a review if you enjoyed this model or have problems with it. This helps me with improving future models and finetuning them in general. Give it a try and throw some images down below! 👇