Nuke 13.2 sees updates to the CopyCat node including single GPU speed improvements by up to 30% and multiple GPU support enabling users to speed up training by using all GPUs simultaneously or to run different training sessions on each GPU, allowing you to iterate faster. Users can now also train more than four channels to allow for the training of more advanced model datasets, or empowering artists to train one network for multiple use cases. We have also removed any limitation on the number of training images and enabled the ability to train on headless Nuke with the -X flag.