First of all, the suggested weight of 1 is low: you can easily go up to 2 and above if the style does not appear, expecially for the Adam version.

Second iteration (the first, frankly, was bad).

Removed some lower quality image from the datas, added some other, splashed with personal generations, re-tagged everything, smaller tensor size, increased shadowing.

From tests, this seems a good generation improver, oriented toward a less-animesque style: the cover image is a simple prompt with high CFG to show the baseline.

As I forgot '2D' and '3D' as tags, it doesn't particularly react to that disctintion anymore. No big deal, honestly: you can prompt a 2D generation anyway with the right prompt.