How To Upscale

wtp manga cover pretrained

Purpose: pre-workout to speed up your workouts

While experimenting with color models for cugan, I just ran into problems that the official models are not imported correctly and have additional processing in addition to resizing. As a result, for my project I trained 2 x cugans for neosr; only resizing losses were applied to the dataset (“lanczos”, “bicubic”, “bilenear”, “HAMMING”, “NEAREST”)

Color Mode
Datasetcustom dataset of manga covers and color manga in equal quality with pixiv
Dataset size110730
Training iterations312000
Training epochs14
Training batch size6
Training HR size256
Training OTFNo

Similar Models