(Anima 1.0) I don't need to test distribution training anymore, so I shifted the lora dataset to fully using umyonge_ikakeu

Skilled former eromangaka, please support his works.

(Preview 3) Mixed dataset, a test of training different distributions, pretty ero biased.

Disclaimer

I respect the artists who honed their crafts for years to achieve these styles among all else, if any artists whom LoRA i've made from shown displeasure/objection to their arts being used as AI training material or if they request a takedown notice on Danbooru , I'll delete the LoRA with no further notice.