This model tries to replicate the style of the Ghost in the Shell movie from 2017. It's trained on 16:9 images and works for fl2va. It seems to work also for ref2va to some extent. I added a ref2va video to the showcase which uses reference images for the court logo, the prosecutor's outfit, and the holographic gun. I also tried to use a reference image for the court but then the style didn't work well. I'm going to train a ref2va version anyway and see what happens. This is my first style lora, so it's meh, but at least it's also free ¯\_(ツ)_/¯Trigger: gits2017Strength: 0.9The showcase videos were generated without turbo loras but with the Spectrum node, using the fp8 model.

Files with SHA256: 8004165bce1dd369c279808984c9349351f333576346bebffe6ce703ee07e946