Trained on mostly Rembrandt's works, an experimental model to see how much influence of the art style or medium would affect the training. I have a few more alternative versions.
v0.5:
Medium strength and flexible version, it is the aim for catching general style but not much, so it can mix with other styles without overpowering the latent space.
And refiner really messes up this style(needs more testing), which is seen in my examples, it distorts and sometimes destroys the crosshatching lines.
Support me here if you want: https://ko-fi.com/sensai3
Thank you.