Enlarge Image Without Losing Quality
A normal resize makes a small image bigger and blurrier. This enlarges it with a super-resolution model that reconstructs edges and texture — on your device, free, nothing uploaded.
Upscale
Cleans JPEG artefacts and noise while keeping detail — the right default.
About the model
Real-ESRGAN "general x4v3" (SRVGGNetCompact, BSD-3-Clause), 4.9 MB, fp32. Runs in a Web Worker with ONNX Runtime on your CPU, in 256-pixel tiles; the 2× option runs the 4× model and box-filters the result down, which is sharper than a native 2× would be. The three styles are the official weights blended with the "denoise" weights at 0, 0.5 and 1. Each style is cached on your device after its first download.
What this tool does
It runs Real-ESRGAN — a compact super-resolution neural network released under the BSD-3 licence — on your device, in a Web Worker with ONNX Runtime, to enlarge the image 2× with reconstructed edges and texture and compression artefacts removed. The 4.9 MB model downloads from this site once and is cached; the photo never leaves your browser. There is no queue, no credits and no watermark because no server does any work.
Why ordinary enlarging looks bad
Photoshop's bicubic, Lanczos in the resizer, your phone's pinch-zoom — they all interpolate between the pixels that exist, so an enlargement is always softer than the original, and sharpening afterwards just adds halos. A super-resolution network does something different: it has seen millions of pairs of small and large images and predicts what the missing detail most plausibly looks like. The result has real-looking edges and texture at 2× or 4×, which is why it is the tool for printing a small web image, using a thumbnail on a slide, or bringing an old 640-px photo up to a modern screen.
What to expect
Excellent on edges, fabric, foliage, architecture, product shots and logos; good on faces at 2× (4× can look waxy on skin); it will not invent legible text. For "make this photo bigger for print", upscale 2× or 4× here, then resize to the exact pixel dimensions the printer wants.
Limits and honesty
- Super-resolution invents detail. It cannot make unreadable text readable or recover a face that was never captured.
- Inputs are capped at 2.1 MP for 2× and 1.05 MP for 4×; larger images are reduced first and the page says so.
- It is CPU-bound: about 15–40 s for a 1 MP image at 2× on a laptop, longer on a phone, with a progress counter and a cancel button.
The full tool with every option lives at Upscale Image.
Frequently asked questions
Is my photo uploaded?
No. The page is static and has no upload endpoint; your browser does the work on your own device and the result is saved straight back to your disk. The site's Content-Security-Policy only allows it to talk to its own origin, so it cannot send your file anywhere even by accident. Load the page, disconnect from the internet, and it still works.
Is it really "without losing quality"?
Honest answer: enlargement always invents pixels. The difference is that this invents plausible detail instead of blur, so the result looks like a sharper photo rather than a zoomed one. For most uses that is exactly what people mean by the phrase.
How big can I go?
2× or 4× in one pass. Input is capped at 2.1 MP for 2× and 1.05 MP for 4× (roughly 1920×1080 / 1024×1024); larger images are reduced first because they do not need upscaling. For more than 4×, upscale, then run the result again.
Which model is it?
Real-ESRGAN "general x4v3" (Tencent ARC, BSD-3-Clause) converted to ONNX by us from the official weights, running with ONNX Runtime compiled to WebAssembly. The three styles are the official base/denoise weight blends.
Is it free? Any limits or watermark?
Free, no account, no watermark, no daily quota. Because nothing runs on our servers there is nothing to meter. The only limits are your device's memory — anything up to roughly 50 megapixels is fine on a modern phone or laptop.
Does it work on my phone?
Yes on recent phones; the model download is 4.9 MB and processing takes 30–90 s for a 1 MP image. Keep the tab in the foreground.