Update (9-2-25): I added more images to the dataset, removed a couple of 'eh' images, changed the tagging slightly, and added about 1k extra training steps. V2, from quick tests, does a better job at replicating the anime as a result!
HUGE Greek booba!
➼Obligatory self-promotion: consider supporting or commissioning me at https://www.fiverr.com/metalchromex/make-you-a-stable-diffusion-anime-character-model or https://www.patreon.com/MetalChromeX so I can continue making cool crap for you all to enjoy for free!