a quick 2nd go at a LORA + a friend of mine asked if I can share it so here it is for anyone else to mess with愛.. This was trained and tested on Anything v4, this may work on other derivative models. A weight of 0.7 or lower is recommended. dont forget to put <lora:giornogiovanna:0.7> in the prompt as always. Training images: Danbooru |