The new version, trained for SDXL is up.
For this version, I recommend to use weight between 0.6 and 1.2.
A style LoRA to reproduce Anders Zorn's painting and drawing.
It's a merge of multiples LoRA trained with the same dataset on SD 1.5 but with different training parameters.
For the drawing style use sketch and monochrome, use painting for painting.
Use weight between 0.8 and 1.
The training data is also available to download, all the images are in the public domain.