bonlime
Results
83
comments of
bonlime
@hzwer in your opinion what is the most robust/safe to use model for now? Which one was trained the most?
Tried different input and upscale factors, CCSRv2 seems to be generating too much of gan artifacts and deviating too much from the input image. v1 seems much better in comparison
+1 for this idea. For me random shuffling of `all` vectors with probability of 1 gives the best results.