Desktop AI Engine

Deep Learning Hardware-Level Features

Upscayl does not guess pixels. It reconstructs textures using trained AI on your GPU — explore the workflow and the technical core behind our open source image engine.

Simple 4-Step Workflow

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.

Drag and drop or select images instantly
Batch Upscayl toggle for folder processing
Double Upscayl option for tougher sources

Desktop workspace screenshot highlighting the four-step import and upscale workflow

Before and After Comparison

Preview results with a built-in slider before you save. Watch a low resolution source transform into a sharp upscale, from 300×168 to 1200×672 in this example, with model control on the left panel.

Interactive compare slider in the preview pane
General Photo and specialty model dropdown
Resolution target shown before you run

Interactive before-and-after preview pane with draggable comparison divider

Local GPU Processing

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.

Real-time progress with clear status messages
100% offline after models are installed
No uploads and no cloud queue delays

Progress overlay while Vulkan-accelerated enhancement runs entirely offline

Under the Hood

Neural Core & Pipeline

Specialized models, native GPU paths, and production-grade batch tooling — all running locally on your machine.

Advanced Model Architecture

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.

Real-ESRGANRemacriUltraSharpDigital_Art

Vulkan API Local Acceleration

No remote latency or subscription queues. Upscayl utilizes the local Vulkan API to communicate directly with your AMD, Nvidia, or Intel GPU, maximizing throughput securely.

100% OfflineHardware NativeNo Cloud Fees

Enterprise-Grade Batch Export

Perfect for texture packs, archival scanning, or comic workflows. Point at any directory, select your scale factor, and let the background queue process hundreds of files concurrently.

Folder InputAuto-NamingQueue Parallelism

Flexible Output Layouts

Export into high-fidelity wrappers without intermediate compression loss. Save and compare using PNG, JPG, or modern WebP depending on your requirements.

Lossless PNGWebP ReadyCustom Scale Factor