OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Image & Video AI

Qualityscaler

QualityScaler is a Windows application that uses AI to enhance, upscale and de-noise photographs and videos. It supports local processing and includes tools for resizing, interpolation and video upscaling.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Qualityscaler — OpenViST project profile in Image & Video AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use QualityScaler when you need AI-assisted image or video enhancement on a Windows PC and can meet its memory and GPU requirements.

Who it is for

  • Windows users enhancing or enlarging photos and video footage.
  • People looking to reduce image noise or compression artifacts.
  • Developers who want to inspect or build the Python application from its MIT-licensed repository.

Documented uses

  • Upscale images in supported formats such as JPG, PNG, WebP and HEIC.
  • Upscale video in formats including MP4, MKV, AVI and MOV.
  • Resize media before upscaling or blend the original with the enhanced output using interpolation.
  • Stop and resume video upscaling.
Before you choose

Requirements & limits

The application is documented for Windows 10 and Windows 11, with at least 8 GB RAM and a DirectX 12-compatible GPU with at least 4 GB VRAM. The README says processing does not require an internet connection. The public repository lists an MIT license.

  • Hardware requirements include a DirectX 12-compatible GPU with at least 4 GB VRAM.
  • Automatic image tiling is documented as a way to avoid GPU VRAM limitations.
  • The README lists supported image and video formats, plus video stop-and-resume and output-resolution controls.
  • Building from source requires Python, VS Code, downloaded AI models, ffmpeg.exe and installing the listed Python dependencies.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare QualityScaler from source in VSCode

Set up the project and its listed dependencies, AI models, and ffmpeg executable, then start the Python application from VSCode.

Before you start

  • Windows 10 or Windows 11
  • At least 8 GB RAM
  • A DirectX 12-compatible GPU with at least 4 GB VRAM
  • Python installed
  • VSCode installed

Steps

  1. Download the project ZIP from the GitHub repository and extract it.

  2. Extract the AI model files into the project’s /AI-onnx folder and extract ffmpeg.exe into /Assets.

  3. Open the project directory in VSCode and select QualityScaler.py in the sidebar; install the Python extension if VSCode prompts for it.

  4. In the VSCode Terminal, run the command below, then close and reopen VSCode to refresh dependencies.

    Documented command
    pip install -r requirements.txt

  5. Select the Play button in the upper-right corner of VSCode.

Expected outcome

The documented setup culminates in launching `QualityScaler.py` from VSCode.

Guide limitations

  • The README lists Windows 10/11, 8 GB or more of RAM, and a DirectX 12-compatible GPU with at least 4 GB VRAM as minimum requirements.
  • The documented steps cover setup and launch, but do not explain the application’s image or video processing controls.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
Djdefrag/QualityScaler · Official homepage title · retained in its source language
How we review sourcesSuggest a correction