Links.

• Github -> https://github.com/Djdefrag/QualityScaler/releases/tag/1.1.0
• Itch -> https://jangystudio.itch.io/qualityscaler

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

Installation.

QualityScaler is completely portable; just download, unzip and execute the file .exe

Supported AI Backend.

• Nvidia Cuda [v10.2]
• CPU [works without GPU, but is very slow]

Features.

• Easy to use GUI
• Images and video upscale
• Drag&drop files [image/multiple images/video]
• Different upscale factors:
  • auto - automatic choose best upscale factor for the GPU used (to avoid running out of VRAM)
  • x1   - will mantain same resolution but will reconstruct the image (ideal for bigger images) 
  • x2   - upscale factor 2: 500x500px -> 1000x1000px
  • x4   - upscale factor 4: 500x500px -> 2000x2000px
• Cpu and Gpu [cuda] backend
• Compatible images - PNG, JPEG, BMP, WEBP, TIF  
• Compatible video  - MP4, WEBM, GIF, MKV, FLV, AVI, MOV 

Next steps.

1. Use both model for the upscale
2. Include audio for upscaled video
3. Support for other GPUs (AMD, Intel) with new backend