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.😊

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

You can always drop model suggestions in the comments, both for styles that are missing on civit or those that are outdated

About the artist:

Patreon: Kumiko Shiba | creating art,drawing,painting | Patreon

Gumroad: kumikoshiba (gumroad.com)

As Kumiko Shiba is a ???? artist the model has a strong bias towards nsfw images.

Most of their art is of Syndra from League of Legends - using the prompts in the first example image can consistently create her.

Weights & Prompts

The only necessary prompt is:

kumiko_shiba

LoCon:

I recommend a weight of 0.5-1.0, adjust to taste and depending on the checkpoint used.

At 1.0 the characters start getting paler while you still get most of the style elements at lower weights like 0.7.

LoRA:

A weight around 0.6 is recommended and compatible with most character lora.

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! 👇