DEDUPEDWho it is forA small shop owner or game modder with dozens of small images to enlarge at once.
The problemUpscaling images one by one takes too long.
The outcomeA folder of upscaled images, post-processed after the batch finishes.
What you need first
- A Vulkan-compatible GPU (most integrated GPUs do not work)
- Linux, macOS 12+ or Windows 10+
- Node.js (Volta recommended) only if you build from source
Steps
- On Windows, download upscayl-x.x.x-win.exe from the releases section and run it
- On Linux, download the AppImage, allow it to execute, and run it (RPM, DEB and Flatpak also exist)
- Turn on batch mode and choose your input folder
- Set the GPU ID if you have more than one GPU
- Let the batch finish completely before checking results, as the FAQ explains
Prompt for your agent
Install upscayl/upscayl on my <Windows or Linux> machine and batch upscale every image in <folder>. Do not interrupt the batch, then check that all outputs have the expected scale.
Caveat. This card is written from the upscayl/upscayl README, not from a test run by Deduped. Before you start, make sure you have a Vulkan-compatible GPU. Check the repo for newer instructions before you rely on these steps.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for upscayl/upscayl and "Batch upscale a whole folder of images on Windows or Linux"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer