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)

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You can always drop model suggestions in the comments, both for styles that are missing on civit or those that are outdated.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: Media posts by カーミン@よどみない (@kamindani) / X (twitter.com)

Pixiv: カーミン@やるせない - pixiv

Kaamin mostly creates extremely stylized and messy character art, both original and fanart.

Often these take the form of sketches with little detailing and a strong focus on light and dark.

Weights & Prompts

The activation prompt is:

kaamin

You can recreate the really rough style to some extent by adding

sketch

with different weights. In testing it started breaking around 1.8. Check the examples for more infos. This model works both for landscapes and character art with the most interesting results, in my opinion, obtained at a sketch weight of around 1.5.

For the LoCon itself use a weight of 0.8-1.0, adjust to taste and depending on your checkpoint.

As usual I have included an XYZ plot for reference.

As usual you should experiment with all weights as they aren't set in stone.

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! 👇