Djdefrag/QualityScaler

QualityScaler - image/video AI upscaler app

What it solves

QualityScaler is a Windows application designed to improve the visual quality of photographs and videos. It addresses the problem of low-resolution or noisy images and videos by using AI to upscale (increase resolution) and de-noise them.

How it works

The app is built with Python and uses AI models (such as BSRGAN, Real-ESRGAN, and IRCNN) via the ONNX Runtime and PyTorch. It leverages DirectX12 compatible GPUs (AMD, Intel, and Nvidia) to perform the processing. To prevent GPU VRAM limitations, it employs automatic image tiling.

Who it’s for

It is intended for Windows users who want a simple, privacy-focused tool to enhance their media files locally on their own PC without requiring an internet connection.

Highlights

  • Multi-GPU Support: Supports multiple GPUs, including combinations of integrated and dedicated graphics.
  • Broad Format Support: Compatible with a wide range of image (jpg, png, tif, bmp, webp, heic) and video (mp4, webm, mkv, flv, gif, avi, mov, mpg, qt, 3gp) formats.
  • Local Processing: Everything runs locally for privacy, requiring no internet connection.
  • Video Controls: Includes features like stop-and-resume for video upscaling and hardware-accelerated encoding.
  • Interpolation: Allows users to blend the original file with the upscaled version.

Related

  • Project
    taylorwilsdon/google_workspace_mcp

    Google Workspace MCP Server is an open‑source Python service that exposes 120+ Google Workspace actions (Gmail, Drive, Docs, Calendar, etc.) through the Model‑Client‑Protocol, enabling LLM assistants like Claude or ChatGPT to read and write Workspace data. It supports multi‑user OAuth 2.1, three tool‑tiers, stateless container deployment, and a full CLI, while keeping all traffic limited to Google’s APIs and offering MIT‑licensed, self‑hostable code.

  • Project
    SkyworkAI/Skywork-R1V

    Skywork-R1V is an open-source multimodal reasoning model that uses reinforcement learning and visual chain-of-thought to achieve state-of-the-art performance in complex visual logic, math, and physics tasks.

  • Project
    llm-as-a-verifier/llm-as-a-verifier

    llm-as-a-verifier is a Python framework that turns LLMs into fine‑grained, probabilistic verifiers for AI agent outputs. It scores candidate trajectories, selects the best‑of‑N via an efficient Probabilistic Pivot Tournament, tracks progress step‑by‑step, and supports multimodal (image) inputs. The library achieves state‑of‑the‑art results on several agentic benchmarks and includes scripts for reproducible evaluation, a cache‑optimised token usage tracker, and a Claude Code plugin (TurboAgent) for seamless integration.

  • Project
    breezedeus/Pix2Text

    An open-source Python toolkit that converts images and PDFs into Markdown by recognizing layouts, tables, text, and mathematical formulas.