Image-Super-Resolution-via-Iterative-Refinement icon indicating copy to clipboard operation
Image-Super-Resolution-via-Iterative-Refinement copied to clipboard

Published 20 hours ago • verified publisher icon Janspiry

Why I got zombie face?

Open TunKedsaro opened this issue 1 year ago • 1 comments
trafficstars

I trained with SR3 using a dataset of thumbnails (128x128) with around 70,000 images (but after the downsampling process, the images were reduced to just 46,666). After that, I trained the model with an A100 for 100,000 iterations and got /checkpoints/I100000_E35_gen.pth as a result. However, when I used it on images found from the internet, the outcome was unsatisfactory. Can you help me with a solution? Picture1

TunKedsaro avatar Sep 20 '24 12:09 TunKedsaro