My first attempt at creating a lora containing both a style and characters feedback is appreciated, I used 200 total images from the show, 75 of them being random characters, scenery, etc and 25 for each character, overall I think it turned out alright but I will train it again because some of the characters aren't consistent and sometimes the style isn't as visible. trained here on civitai using Pony Diffusion V6 XL as a training model at 1024Style info:trigger word: kan_styleweight: 1 is perfectCharacters info:Trigger word - looks tagKim: kimaps - long hair, orange hair, green eyesMonique: moniiqkue, black eyes, black hair, dark-skinned female, dark skinBonnie: bomnkinie, short hair, brown hair, green eyesAnn: ankkiin, brown hair, short hair, blue eyes, doctor, lab coatShego: shmeikgo, black hair, long hair, green eyes, gloves, bodysuit, lipstickAdditional information:Webui I useVAE I useR-ESRGAN 4x+ Anime6B upscaler for anime4x NMKD Superscale upscaler for realisticImagine dimensions vary depending on what I'm trying to doSampling steps I go 20-30hires steps I go 10-15 (I don't always use hires fix)Denoising strength I go 0.4I use 3 CFG Scale and CFG Scale Fix set at 7uddetailer for facesI do all of my lora training here, if you can spare any buzz I would appreciate it
