Djdefrag / NiceScaler

NiceScaler - image/video deeplearning upscaler (OpenCV)

Image/Video deeplearning upscaler app for Windows (OpenCV)

Credits.

ESPCN (https://arxiv.org/pdf/1609.05158.pdf)

FSRCNN (https://arxiv.org/pdf/1608.00367.pdf)

LapSRN (https://arxiv.org/pdf/1710.01992.pdf)

How is made.

NiceScaler is completely written in Python, from backend to frontend. External packages are:

• AI -> OpenCV
• GUI -> Tkinter / Tkdnd / Sv_ttk / Win32mica
• Image/video -> OpenCV / Moviepy
• Packaging -> Pyinstaller

Requirements

• Windows 11 / Windows 10
• RAM >= 8Gb
• OpenCL compatible gpu
• CPU

Features.

• Easy to use GUI
• Image/list of images upscale
• Video upscale
• Drag&drop files [image/multiple images/video]
• Different upscale factors:
  • x2 - 500x500px -> 1000x1000px
  • x4 - 500x500px -> 2000x2000px
• Cpu and Gpu backend
• Compatible images - png, jpeg, bmp, webp, tif
• Compatible video - mp4, wemb, gif, mkv, flv, avi, mov, qt

Next steps.

• New GUI with Windows 11 style
• Include audio for upscaled video
• Update libraries
  • Python 3.10 (expecting ~10% more performance)
  • Python 3.11 (expecting ~30% more performance, now in beta)

Known bugs.

• GPU upscaling does not work correctly with some gpus (use CPU instead)
• When running NiceScaler as Administrator, drag&drop is not working

Example.