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
FAQ
Comments (5)
any boobs growth
there are already models for that I think
Having hard time activating the muscle growth... put 1 strenght nothing happen, put 1.35 strenght still nothing happen except sound is now crappy distorted... are you sure this is the right file you uploaded ?
I'm not sure what's happening on your end, because this is super overcooked and the effect is very strong. Works OK for image to video, for text to vid, you need to turn it way down
I have used the workflow in the video-file (download the video and open the video-file with ComfyUI). I give it a try with different pictures. It runs for me. Many thanks to daroth for the upload.