AutoUpscale

Universal app for scaling images

AutoUpscale is a universal app for scaling images. It can be used as a command line tool, a web GUI, or a console application.

Supported algorithms

• Classical Algorithms ^{(Up-scaling and downscaling)}:
  • Bicubic (Better than bilinear, less blur, more detail, higher contrast)
  • Bilinear (Second-simplest algorithm, most common and most blurry)
  • Nearest neighbor (Simplest algorithm, duplicates or keeps only the nearest pixel)
  • Area (Averages pixels into smaller ones) ^{(Only down-scaling)}
  • Lanczos (Better than bicubic, less blur, higher contrast)
• AI-based Algorithms ^{(Only up-scaling)}:
  • A2N
  • AWSRN-BAM
  • CARN
  • CARN-BAM
  • DRLN (recommended)
  • DRLN-BAM (recommended)
  • EDSR
  • EDSR-base
  • ESPCN
  • FSRCNN (normal and small)
  • HAN
  • LapSRN
  • MDSR
  • MDSR-BAM
  • MSRN
  • MSRN-BAM
  • PAN
  • PAN-BAM
  • RCAN-BAM,
  • RealESRGAN (improved ESRGAN) (recommended)
  • Anime4K (recommended)
  • HSDBTRE (hybrid of DRLN and RealESRGAN AIs) (recommended)
• Edge Detection Algorithms ^{(Only up-scaling)}:
  • hqx (edge detection algorithm, simple, not so great)
  • NEDI (New Edge-Directed Interpolation, can be better than hqx, but probably won't)
  • Super xBR (edge detection algorithm, based on xBR, more angles but more blur)
  • xBRZ (edge detection algorithm, based on xBR, better at preserving small details)
• Smart Algorithms ^{(Only up-scaling)}:
  • FSR (FidelityFX Super Resolution 1.1, made by AMD)
  • CAS (Contrast Adaptive Sharpening, made by AMD)

Installation:

1. Make sure you have installed on your system:
   • Python 3.12
   • Node.js (16.0.0 or newer)
2. Clone this repository
3. Run the included install.bat script

Usage:

• Command line tool:
  • Run the included run_console.bat script
  • Run the python script manually: python src/standalone.py
    • You can also pass arguments to the script. Add --help to see the list of available arguments
• Web GUI (currently lacks some functionality):
  • Run the included run_webui.bat script

Examples:

Example - Wiki Shell:

Scaled down image (40px):

Results of up-scaling the image (40px -> 160px):

Original	Nearest Neighbour	Bilinear	Bicubic

Lanczos	EDSR (CV2)	ESPCN (CV2)	FSRCNN (CV2)

FSRCNN-small (CV2)	LapSRN (CV2)	A2N (SI)	AWSRN-BAM (SI)

CARN (SI)	CARN-BAM (SI)	DRLN (SI)	DRLN-BAM (SI)

EDSR (SI)	EDSR-base (SI)	HAN (SI)	MDSR (SI)

MDSR-BAM (SI)	MSRN (SI)	MSRN-BAM (SI)	PAN (SI)

PAN-BAM (SI)	RCAN-BAM (SI)	RealESRGAN	Anime4K

HSDBTRE	hqx	NEDI (m = 4)	Super xBR

xBRZ	FSR	CAS (sharpness = 0.5)

Supported file formats:

Tested working:

• Write:

  • PNG (Widely used, popular, lossless format)
  • QOI (A bit worse compression then PNG, but a lot lot faster to save and load)
  • WEBP (Comparable, lossless and lossy compression, to JPEG XL (a bit worse on average), but with better overall support)
  • JPEG XL (New advanced compression format, better lossless compression compared to PNG and better lossy compared to JPEG)
    ^{(see this plugin for Windows Support)}
  • Benchmark result (size, lower is better):
    • QOI: 790 448 B
    • PNG: 675 397 B
    • WEBP: 444 538 B
    • JPEG XL: 450 085 B

• Read:

  • PNG (.png)
  • JPEG (.jpg, .jpeg)

Should work:

• Read:

  APNG (.apng, .png2) BLP (.blp, .blp2, .tex) BMP (.bmp, .rle) CUR (.cur) DCX (.dcx) DDS (.dds, .dds2) DIB (.dib, .dib2) EMF (.emf) EPS (.eps, .eps2, .epsf, .epsi) FITS (.fits) FLC (.flc) FLI (.fli) FPX (.fpx) FTEX (.ftex) GBR (.gbr) GD (.gd) GIF (.gif, .giff) ICNS (.icns, .icon) ICO (.ico, .cur) IM (.im, .im2) IMT (.imt) IPTC (.iptc) JPEG (.jpg, .jpeg, .jpe) JPEG 2000 (.jp2, .j2k, .jpf, .jpx, .jpm, .j2c, .j2r, .jpx)

  MCIDAS (.mcidas) MIC (.mic) MPO (.mpo) MSP (.msp, .msp2) NAA (.naa) PCD (.pcd) PCX (.pcx, .pcx2) PFM (.pfm, .pfm2) PIXAR (.pixar) PNG (.png, .pns) PPM (.ppm, .ppm2) PSD (.psd) QOI (.qoi) SGI (.sgi, .rgb, .bw) SPIDER (.spi, .spider2) SUN (.sun) TGA (.tga, .targa) TIFF (.tif, .tiff, .tiff2) WAL (.wal) WMF (.wmf) WebP (.webp, .webp2) XBM (.xbm, .xbm2) XPM (.xpm)

Roadmap:

• Add Performance / Benchmarks section to the README
• Add support for WEBP2 format (both reading and writing)
• Add support for AVIF format (both reading and writing)
• Optimize the code, adn remove unnecessary parts and duplicates
• Rewrite and update the WebUI
• Add support for Waifu2x and Supir AIs via Docker
• Fix and improve standalone console application experience

Credits:

• WebUI, Scaling App and HSDBTRE AI hybrid created by Mikołaj Pokora
• API backend and xBRZ wheel by Piotr Przetacki
• Anime4K implementation by TianZer (TianZerL)
• RealESRGAN implementation by ai-forever
• NEDI implementation by Ley (Kirstihly)
• hqx implementation by whoatemybutter
• xBRZ implementation by ioistired
• Super xBR implementation originally created by Matt Schwartz (n0spaces) corrected by Mikołaj Pokora
• FSR and CAS are implemented using FidelityFX-CLI by GPUOpen-Effects and AMD ^{(licence in "src/FidelityFX-CLI-v1.0.3")}
• Area, Bicubic, Bilinear, Lanchos and Nearest neighbor algorithms are implemented using OpenCV
• EDSR, ESPCN, FSRCNN, FSRCNN-small, LapSRN AI algorithms are also implemented using OpenCV
• Nearest neighbor, Bilinear, Bicubic and Lanchos algorithms are also implemented using Pillow library
• A2N, AWSRN-BAM, CARN, CARN-BAM, DRLN, DRLN-BAM, EDSR, EDSR-base, HAN, MDSR, ...gasssp...
• MDSR-BAM, MSRN, MSRN-BAM, PAN, PAN-BAM, RCAN-BAM AI algorithms are implemented using super-image by eugenesiow (Eugene Siow) and Freed Wu
• QOI file format support library by kodonnell
• JPEG XL PIL plugin by Isotr0py

• Download icon: Install icons created by NajmunNahar - Flaticon

• Web GUI icon: Interface icons created by Freepik - Flaticon

• Console icon: Console icon by Icons8