Size output
#2
by SOleLuch - opened
Hi! Thank you for your work. I have a question about the output image. Does it need to be the same size as the input image, or did you train the LoRa model so that the zoomed-in image maintains a specific aspect ratio?
@SOleLuch
It is expected to work fine with variable aspect ratios on image inputs, and yes, the part of the scale you choose in the input image will be zoomed in and result in the same aspect ratio as the image.
And it is trained that way.
prithivMLmods changed discussion status to closed