Train LoRa is time and resource expensive, you can support my future works here:
it would be great if you could show some of the results of your work as a post/review
Gochuumon wa Usagi desu ka?
I strongly recommend use all character model with power 0.5-0.7, cuz strikethroughed character models works isn't good(it's don't tagged and real TW is "out", don't ask me why) and i don't plan to update it, and all charas model works ~fine with power 0.6-0.7 even without hiresfix.
Kafuu Chino old
Hoto Cocoa
Chiya Ujimatsu
Rize Tedeza
Sharo Kirima
Maya Jouga
Megumi Natsu
Midori Aoyama
Moka Hoto
Tippy
// additional info in "version info block" on Kafuu Chino.
Why my LoRa's? Because it's close to anime style, and this style is ~simple in details and can change without mutating target style more easy than artistic one. And it's hard to get quality anime style pictures from LoRa's with more artistic dataset with gradients and complex lighting.