Non-Square images work basically out of the box. I trained a model with the smithsonian_butterflies_subset with 32x64 pixels and compared it to 48x48 pixels to roughly have the same number of total pixels.
FID 48x48 was 50.2 after 10_000 steps with batchsize 16
FID 64x32 was 59.9 after 10_000 steps with batchsize 16
Non-Square images work basically out of the box. I trained a model with the smithsonian_butterflies_subset with 32x64 pixels and compared it to 48x48 pixels to roughly have the same number of total pixels.
FID 48x48 was 50.2 after 10_000 steps with batchsize 16
FID 64x32 was 59.9 after 10_000 steps with batchsize 16