metadata
license: mit
library_name: diffusers
base_model: stabilityai/stable-diffusion-xl-base-1.0
tags:
- text-to-image
- text-to-image
- diffusers-training
- diffusers
- lora
- template:sd-lora
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
datasets:
- orrinj/janeycat_sprite_2
widget:
- text: a,i
output:
url: images/janesprite_1.jpg
This is my first attempt at a lora made on kaggle so it probably doesn't work perfectly, but at least it's here so the notebook worked! The instance prompt is "a videogame character sprite of TOK janeycat" in case anyone wants to try, trained at 1024x1024. Based on my rather limited prompts, you can use letters a-h for an effect, but i seems to have more consistency!