This LoRA was trained (with consent) on 36 images by the legendary master of prompts @CranialOrigami. It does not exactly duplicate his numerous styles, it is more of a creative tribute to his vision that you can play with.
Description
Trained for 2000 steps using the prodigy optimizer with a batch size of 4 and a grad accum of 4, offers a slightly different take on the style, perhaps a bit more faithful to the training material.