This is an experiment to train a LoRA for video, turns out for transformation only High Noise needs training for WAN. Wanted to have something that doesn't have the unwanted motion, pose changes and disappearing clothes of existing LoRAs. Sadly clothes still have a tendency to disappear
Description
This is a version for LTX 2.3. I don't know what's up with training, because it's kinda janky. Works alright for I2V, less so for T2V