Download
1 variant available
LoRA for Z-Image generating in the style of artist Picturd.
Works with strength between 0.7-1, 1 can be glitchy depending on complexity of the prompt.
All of examples are made in 0.9-1 and tiled upscaler - euler_a+simple 12 steps.
Workflows are imbedded in the pics.
Fist LoRA trying 2d/cartoon/anime image training, still experimenting with params.