#1010th of 10 in Image and video

upscayl

Desktop image upscaler using Real-ESRGAN models over Vulkan

Stars
50.5k
License
AGPL-3.0
Last commit
Mar 2026
Last release
Dec 2024
Language
TypeScript
Stars, last 29 weeks+6,959
24 Mar 2026: 43,587 stars31 Mar 2026: 43,798 stars7 Apr 2026: 43,943 stars14 Apr 2026: 44,118 stars21 Apr 2026: 44,270 stars28 Apr 2026: 44,490 stars5 May 2026: 44,640 stars12 May 2026: 44,812 stars19 May 2026: 44,997 stars26 May 2026: 45,172 stars2 Jun 2026: 45,378 stars9 Jun 2026: 45,589 stars16 Jun 2026: 45,786 stars23 Jun 2026: 46,025 stars30 Jun 2026: 46,232 stars7 Jul 2026: 46,478 stars14 Jul 2026: 46,894 stars21 Jul 2026: 47,176 stars28 Jul 2026: 47,382 stars4 Aug 2026: 47,530 stars11 Aug 2026: 47,766 stars18 Aug 2026: 48,385 stars25 Aug 2026: 48,573 stars1 Sept 2026: 48,767 stars8 Sept 2026: 48,957 stars15 Sept 2026: 49,168 stars22 Sept 2026: 49,714 stars29 Sept 2026: 49,939 stars6 Oct 2026: 50,139 stars13 Oct 2026: 50,546 stars

43,587 on 24 Mar 202650,546 on 13 Oct 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

Upscayl is an Electron desktop app that enlarges low-resolution images with Real-ESRGAN-based models run through an NCNN Vulkan backend. It supports batch upscaling, GPU selection by ID, and custom models converted from other formats. Installers cover Windows 10+, macOS 12+ and Linux (AppImage, Flatpak, Snap, deb, rpm).

Who it is for: Users who want to upscale photos locally on a desktop with a Vulkan GPU

Strengths

  • Native installers for Windows, macOS and Linux, including Flatpak, Snap, AUR and Homebrew
  • Batch upscaling and selectable GPU ID in the GUI
  • Custom models can be added; a separate repo of extra models and a conversion guide exist
  • Separate upscayl-ncnn CLI backend is open source under AGPLv3

Weaknesses

  • Requires a Vulkan-compatible GPU; many integrated GPUs do not work
  • Cannot de-blur or fix focus; it only enhances low-resolution or pixelated images
  • Last tagged release is 2024-12-25, though commits continue into 2026
  • Image upscaling only; no video or generation features described

What it needs

  • GPU required
  • Needs Vulkan-compatible GPU, upscayl-ncnn backend
  • Models: Real-ESRGAN, NCNN, custom converted models, HFA2k, Remacri

Also in Image and video

See all 10
Also in Image and video
RankProjectScore
1ComfyUINode-graph engine for diffusion image, video, audio and 3D models137.4k starsGPL-3.075 out of 100
2MoneyPrinterTurboTurns a topic into a short video with script, footage, voiceover and subtitles130.6k starsMIT75 out of 100
3InvokeAICanvas-first web UI for Stable Diffusion and Flux image generation28.6k starsApache-2.061 out of 100
#4AI ToolkitFine-tuning suite for image, video and audio diffusion models, with GUI and CLI12.3k starsMIT53 out of 100
#5biniouGradio web UI for local text, image, audio, video and 3D generation1.2k starsGPL-3.050 out of 100