ModelsThere are currently 4 different SR models supported in the module. They can all upscale images by a scale of 2, 3 and 4. LapSRN can even upscale by a factor of 8. They differ in accuracy, size and speed.EDSR [1]. This is the best performing model. However, it is also the biggest model and therefor has the biggest file size and slowest inference. You can download it here.ESPCN [2]. This is a small model with fast and good inference. It can do real-time video upscaling (depending on image size). You can download it here.FSRCNN [3]. This is also small model with fast and accurate inference. Can also do real-time video upscaling. You can download it here.LapSRN [4]. This is a medium sized model that can upscale by a factor as high as 8. You can download it here.For more information and implementations of these models see the module’s GitHub README file. For extensive benchmarks and comparisons go here.