I tried by increasing the output size to 384 & changing the encoder scaling but that didn't work.
Also tried to change the encoder to EfficientnetV2_S & changing the encoder scaling but that also didn't work.
I tested both the above settings in all (DNY 256 512 1024) disney models.
The training won't start & gives error message.
Not easily, no. There is a lot more to creating a model than just adjusting the input and output amounts. Consideration has got to be made about what this change does to the rest of the model.
There is a 384px preset with Patron's at the moment. It will be released to the wider code in due course.