My first crack at a customized Anima merge. Trained on a style LoRA created with about a hundred images generated with several of my Illustrious models, this is essentially that LoRA trained into Anima Base V1, (hopefully) capturing the aesthetic style I've been gradually tuning over the last two years.
Description
V1 (not V2) expanded with more style training. As V2 was created with an experimental, very limited, set of training images, I haven't been satisfied with building on it, so V3 instead adds new training data to V1, keeping the aesthetics, shading, lighting, and textures more consistent, while adding more variety to the outputs.