Upscayl does not guess pixels. It reconstructs textures using trained AI on your GPU. Explore the desktop app workflow and the technical core behind our open source image engine.
Drop in a PNG, JPG, JPEG, or WebP file and follow the guided sidebar. Pick a model, set your output folder, and upscale with one click. Batch mode lets you queue entire folders without leaving the app.
Preview results with a built-in slider before you save. Watch a low resolution source transform into a sharp upscale, from 300x168 to 1200x672 in this example, with model control on the left panel.
Everything runs on your hardware with Vulkan acceleration. The processing overlay keeps you informed while AI reconstruction happens offline, with a stop button if you need to cancel mid-run.
Switch between various deep neural networks designed for specialized tasks. Whether you are scaling low-poly game assets or old family photographs, Upscayl fits the mathematical model dynamically.
No remote latency or subscription queues. Upscayl utilizes the local Vulkan API to communicate directly with your computer's AMD, Nvidia, or Intel GPU, maximizing processing throughput securely.
Perfect for full texture packs, archival scanning, or comic book workflows. Point the application to any directory folder, select your preferred scale factor, and let the background queue process hundreds of files concurrently.
Export directly into high-fidelity image wrappers without worrying about intermediate compression loss. Save and compare results using PNG, JPG, or modern WebP layouts depending on your network requirements.