orrinj's picture
Update README.md
be7ba90 verified
metadata
license: openrail
datasets:
  - orrinj/janeycat2ndrun
base_model: stabilityai/stable-diffusion-xl-base-1.0
vae_path: madebyollin/sdxl-vae-fp16-fix
instance_prompt: janeycat girl
tags:
  - text-to-image
  - text-to-image
  - diffusers-training
  - diffusers
  - lora
  - template:sd-lora
  - stable-diffusion-xl
  - stable-diffusion-xl-diffusers
widget:
  - text: janeycat girl, walking, open mouth, side view, white background
    output:
      url: images/janecat_test.jpg

Use "janeycat girl" to activate.

Probably a bit over-fitted and the quality isn't great unless turned down to .3-4.

Trained with dreambooth again but this time using 4 epochs, reg images and a different script to allow for keep_tokens and other helpful options - more importantly it has the correct metadata and actually works when I apply it on Automatic1111 locally!!! Shame it's 115MB...