Cool_Tools/upscayl
1
0
Fork 0
mirror of https://github.com/upscayl/upscayl.git synced 2024-11-23 23:21:05 +01:00
Code Releases Wiki Activity
🆙 Upscayl - Free and Open Source AI Image Upscaler for Linux, MacOS and Windows built with Linux-First philosophy.
106 Commits 14 Branches 34 Tags 645 MiB
TypeScript 89.9%
JavaScript 3.4%
CSS 3.2%
Python 2.8%
Shell 0.7%
09f41b5598
Go to file
Nayam Amarshe 09f41b5598 Added sharpening info
2022-09-11 17:04:36 +05:30
build Fixed mac icon 2022-08-27 15:29:46 +05:30
main Added sharpening info 2022-09-11 17:04:36 +05:30
models/future-use Fixed path bugs and errors 2022-09-07 08:01:28 +05:30
renderer Added sharpening info 2022-09-11 17:04:36 +05:30
resources fixed sharpen errors 2022-09-11 13:00:50 +05:30
scripts next and electron template 2022-08-15 10:23:14 +05:30
sharpened Added sharpening info 2022-09-11 17:04:36 +05:30
.gitignore next and electron template 2022-08-15 10:23:14 +05:30
LICENSE Create LICENSE 2022-08-24 10:18:39 +05:30
next.config.js temporary fix (messy) 2022-08-22 14:01:16 +05:30
package.json Added batch mode option 2022-09-08 12:22:00 +05:30
postcss.config.js next and electron template 2022-08-15 10:23:14 +05:30
README.md Update README.md 2022-08-29 13:29:47 +05:30
Real-ESRGAN_LICENSE.txt Add files via upload 2022-08-24 16:23:22 +05:30
tailwind.config.js Added sharp 2022-08-18 15:23:23 +05:30
to_upscale.jpeg Added upscaling functionality 2022-08-16 07:47:27 +05:30
upscayl.mp4 Added mp4 2022-08-24 10:25:15 +05:30
yarn.lock Added batch mode option 2022-09-08 12:22:00 +05:30

README.md

New Project (33)
v1.3 will come around 12 September

Upscayl 🆙

Free and Open Source AI Image Upscaler

https://user-images.githubusercontent.com/25067102/186332548-0d53f02f-d159-4804-8b0e-887d96651fdb.mp4

Upscayl is a cross-platform application built with the Linux-first philosophy. This means that we prioritize Linux builds over others but that doesn't mean we'll break things for other OSes :)

NOTE: Upscayl does not work without a GPU, sorry. You'll need a Vulkan compatible GPU to upscale images. CPU or iGPU won't work.

Installation 👨‍💻

Linux 🐧👑

  1. Go to releases section

  2. Download the .AppImage file.

  3. Right Click AppImage -> Go to Permissions tab -> Check allow file to execute and then double click the file to run Upscayl.

You can also download the flatpak version and double click the flatpak file to install via Store but wait for the full release, we'll be pushing it to Flathub for easy access.

MacOS 🍎

  1. Go to releases section

  2. Download the .dmg file.

  3. Double click dmg, drag Upscayl icon into Applications folder.

  4. Open Terminal and enter this command: chmod +x /Applications/Upscayl.app/Contents/Resources/bin/upscayl. Press Enter, profit.

Windows 🐌

  1. Go to releases section

  2. Download the .exe file.

  3. Double click exe file, wait for installation, profit.

Comparisons:

Medium Resolution Images (300-400 pixels wide):

image image

Low Resolution Images (150 pixels wide):

image image

Super Low Resolution Images (75 pixels wide):

UPSCALED TWICE

image

Roadmap 🤫

  • Allow video upscaling📼
  • 2x, 3x upscaling modes
  • More models
  • Make the whole world use FOSS

Development 🛠

git clone https://github.com/TGS963/upscayl
cd upscayl

# INSTALL DEPENDENCIES
npm install

# RUN THE DEVELOPMENT SERVER LOCALLY
npm run start

# PACKAGE THE APP
npm run dist

# PUBLISH THE APP, MAKE SURE TO ADD GH_TOKEN= IN SHELL
npm run publish-app

FAQ 🤓

  • How does Upscayl work?
    • Upscayl uses AI models to enhance your images by guessing what the details could be. It uses Real-ESRGAN (and more in the future) model to achieve this.
  • Is there a CLI available?
    • The CLI tool is called real-esrgan-ncnn-vulkan and it's available on the Real-ESRGAN repository.
  • Do I need a GPU for this to work?
    • Yes, unfortunately. NCNN Vulkan requires a Vulkan compatible GPU. Upscayl won't work on iGPU or CPU.
  • How can I contribute?
    • You can donate more NCNN compatible models or fix code by submitting PRs :)
  • You are not fully open source!!😡
    • We are, we're using completely free and open source tech. We do ship a binary but that's because not including it would kill the entire purpose of the project. If you want to deal with all those PyTorch, NCNN, and Python errors, you're more than welcome to compile your own binary using the code provided by Real-ESRGAN. The binary is pre-compiled for convenience, if you do not trust it, then you can compile your own since everything is free and open source here :)

Upscayl uses Real-ESRGAN-ncnn-vulkan binaries to upscale images. More models and algorithms will come soon.

Credits ❤

Copyright © 2022 - Upscayl
By Nayam Amarshe and TGS963
Made with 🖱 & ⌨