Version 2 has been precision block-merged to weed-out some less desirable features of v1. Much effort has been put into making sure that the style remains similar to version 1 at its core, and this works well enough that existing seeds should work quite similarly in both versions, just with higher clarity in v2. Here's some of the details:

• Improved line clarity - lines should be slightly less weighty which should allow for finer details (such as hands)

• Improved general clarity - shading in v1.0 tended to look rather chaotic. This has been cleaned up in this version so that shading looks better, though emphasis was put on ensuring that style remains consistent

• Improved resolution - perceived resolution is increased due to the before-mentioned clarity improvements.

• Lower config scale requirements - this model will now work better with generating images that are not too peaky or corrupted without the dynamic thresholding plugin. Config scale of 5-6 will work without dynamic thresholding. Do note that this also means that when using dynamic thresholding the values will need to be tweaked lower than v1.0 to avoid a "washed out" look. Specifically, ~11 instead of 13.5 for config scale and ~7 instead of 4.5 for mimic scale.