QualityScaler

QualityScaler copied to clipboard

Image/video DeepLearning Upscaler App for Windows

Credits.

BSRGAN - https://github.com/cszn/BSRGAN | https://arxiv.org/abs/2103.14006

RealSR_JPEG - https://github.com/jixiaozhong/RealSR | https://arxiv.org/pdf/2005.01996.pdf

How is made.

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

• [ ] AI -> Pytorch-directml
• [ ] GUI -> Tkinter / Tkdnd / Sv_ttk
• [ ] Image/video -> OpenCV / Moviepy
• [ ] Packaging -> Pyinstaller
• [ ] Miscellaneous -> Pywin32 / Win32mica / Image_slicer

Installation.

1. download the QualityScaler release .zip
2. unzip using 7zip or similar
3. execute QualityScaler.exe in the directory

Requirements

• [ ] Windows 11 / Windows 10
• [ ] RAM >= 8Gb
• [ ] Directx12 compatible GPU:
  • [ ] any AMD >= Radeon HD 7000 series
  • [ ] any Intel HD Integrated >= 4th-gen core
  • [ ] any NVIDIA >= GTX 600 series
• [ ] CPU [works without GPU, but is very slow]

Features.

• [x] Easy to use GUI
• [x] Image/list of images upscale
• [x] Video upscale
• [x] Drag&drop files [image/multiple images/video]
• [x] Automatic image tiling and merging to avoid gpu VRAM limitation
• [x] Different upscale factors:
  • [x] x2 - 500x500px -> 1000x1000px
  • [x] x3 - 500x500px -> 1500x1500px
  • [x] x4 - 500x500px -> 2000x2000px
• [x] Cpu and Gpu backend
• [x] Compatible images - png, jpeg, bmp, webp, tif
• [x] Compatible video - mp4, wemb, gif, mkv, flv, avi, mov, qt

Next steps.

• [x] Support for Nvidia RTX 3k and 2k with cuda 11
• [x] New Fused model (that combines the best of both models)
• [x] New GUI with Windows 11 style
• [ ] Include audio for upscaled video
• [x] Switch to Pytorch-directml to support all Directx12 compatible gpu (AMD, Intel, Nvidia)
• [ ] Update libraries
  • [ ] Python 3.10 (expecting ~10% more performance)
  • [ ] Python 3.11 (expecting ~30% more performance, now in beta)

Known bugs.

• [ ] Windows10 - the app starts with white colored navbar instead of dark
• [ ] Upscaling multiple images doesn't free GPU Vram, so the it is very likely that the process will fail when the gpu memory fills up
• [ ] Filenames with non-latin symbols (for example kangy, cyrillic etc.) not supported - [Temp solution] rename files like "image" or "video"

Some Example.

• BSRGAN examples

• Fused model examples