As usual: Trained on Anything v3 with its respective vae Images were generated using Corneo's 7th Heaven Mix and a blend of Anything v3 and AOM2-Hard with Anything v3 vae Used a weight of 1 for image generation. Highly recommend using a style LoRA as otherwise the images might come out a bit dull. Sooner or later I'll increase the quality of the dataset and release an updated version. Check out my other Fire Emblem/ファイアーエムブレム LoRA: Celine | セリーヌ Anna | アンナ |