A style LoRa trained on a dataset of cute drawings (mostly furry/kemono) I've collected over the years, with emphasis on outlines, expressiveness, and appealing colors.
This LoRa also serves as the foundation for uwumerge.
Description
V3 is trained on an updated dataset of 74 images at multiple resolutions up to 1024, with revised training settings. This one has a stronger look than v2.