ModelsLab/ArsMJStyles - SDXL (Style Collection) - Anime C

The Lora is trained on MidJourney Images that use my "Personalised Style" + a mix of Anime Styles. The one that can actually be labeled properly is "Blue Eye Samurai" with ~25%.Works without the trigger words ArsMJStyle, AnimeC, but gives stronger results with them.Works great in the 0.3 - 1 range, depending on the Lora Stack you use.The training images are really sharp , so you can go pretty high and still get a coherent images.Above 1.2 everything starts getting abstract.I recommend starting in the 0.8 - 1 range