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

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

About the artist:

Takehiko Inoue is famous for writing the series Slam Dunk and Vagabond, creating highly detailed art with strong contrasts. This model was made using 79 images from the second series, Vagabond.

Weights & Prompts

The only necessary prompt is:

vagabond_style

To get the black and white manga style use

monochrome

I also recommend including "comic" in the negative prompts to prevent panels.

LoCon:

For the weights use 0.6-1.0, adjust to taste.

It is pretty strong and should be tuned to a lower weight when combined with other LoRA. Female characters in particular have a limited range at 1.0 weight.

LoRA:

For the weights I recommend 0.9-1. As it was trained exclusively on black and white pages including monochrome in the negative prompts can force colorized images.

When not otherwise specified it will tend to traditional clothes and building.

As usual I have included an XYZ plot to show how the weight affects the prompt. This version is pretty heavyweight so including the lora doesn't just change the style but massively affects the composition as well.

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! 👇