qduaty / qualityscaler Goto Github PK

This project forked from djdefrag/qualityscaler

QualityScaler - image/video AI upscaler app

License: MIT License

Python 98.37% HTML 1.63%

qualityscaler's Introduction

Changes in this fork

Replaced the slow and memory hungry GUI list for more images than 100 with a button to Explorer, TODO generalize for Linux
Added progress percentage, current file name and ETA for images upscaling
Implemented skipping of existing output images

The server can be launched with UPSCALE button when no images are selected and listens on port 12345

Implemented a maximum output image size of 4096 in any dimension to optimize cases when accidentally a big image is being scaled
Randomized the input images order to make visual inspection easier
Any downloaded onnx models are now detected and used, but must be in subdirectories IRCNN/SRVGGNetCompact/RRDB
Added support for 1-channel (monochromatic) models such as FSRCNN
generalized scale factor detection from model name: now they can also start from eg. 4x and any number is accepted

QualityScaler - image/video AI upscaler app

Qualityscaler is a Windows app powered by AI to enhance, upscale and de-noise photographs and videos.

https://github.com/Djdefrag/RealScaler / RealScaler - image/video AI upscaler (Real-ESRGAN)
https://github.com/Djdefrag/FluidFrames.RIFE / FluidFrames.RIFE - video AI frame generation

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

Prerequisites.

Python installed on your pc, you can download it from here (https://www.python.org/downloads/release/python-3119/)
VSCode installed on your pc, you can download it from here (https://code.visualstudio.com/)

Getting started.

First of all, you need to download the project on your PC (Green button Code > Download ZIP)
Extract the project directory from the .zip
Now you need to download the AI models (github won't let me upload them directly because they are too big)
In "AI-onnx" folder, there is the link to download the AI models, download the .zip and extract the files in AI-onnx directory
Open the project with VSCode (just Drag&Drop the project directory on VSCode)
Click on QualityScaler.py from left bar (VSCode will ask you to install some plugins, go ahead)
Now, you need to install dependencies. In VSCode there is the "Terminal" panel, click there and execute the command "pip install -r requirements"
Close VSCode and re-open it (this will refresh all the dependecies installed)
Just click on the "Play button" in the upper right corner of VSCode
Now the app should work