language:
- en
license: creativeml-openrail-m
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- safetensors
- lora
inference: false
Multisubject LORA based on the hit series Klonoa. Trained as a request for a bro who provided the dataset.
Characters include Klonoa, Lolo, King of Sorrow and Tat, the last one has the least amount of data used though. Might need the Multisubject extension to include multiple characters in the same image.
Try tonde2.safetensors, it was trained with better settings, but tonde.safetensors gives nice results too.
Add the following to your prompts to trigger the character
Klonoa:
klonoa, klonoa1, klonoa2 (1 and 2 for specific game outfit, might not always work)
Lolo:
lolo
King of Sorrow:
kingofsorrow
Tat:
tat
How to use a LORA?
Place it in "\stable-diffusion-webui\models\Lora". Don't see the folder? git pull
Load any model, preferably an anime model, use the purple icon under the generate button to bring up the LORA list or just add it to your prompt like this <lora:tonde:1>, change the number to reduce the strenght like <lora:tonde:0.5>
You can combine it with other LORAs for cool styles.
tonde2.safetensors examples
tonde.safetensors examples
Terms and conditions
All character rights belong to their original owners. I own nothing, I only trained it.