Free AI Image Upscaler
This tool enlarges an image 2x or 4x and reconstructs detail while it does it. It is free and unlimited, and the model runs in your browser, so the photo never leaves your device. It is the right tool for a small photo you need bigger: an old avatar, a product shot, a scan. It is not magic, it cannot invent a face that was never in the pixels, but it beats plain resizing by a wide margin.
The first run loads the AI model into your browser and stashes it away like an acorn. One-time setup: every later visit starts instantly, even offline.
How to use it
Drop in your image
Smaller inputs work best. Something in the 200 to 800 pixel range is the sweet spot, because 4x on an already-large photo produces a gigantic image that your browser has to hold in memory.
Pick 2x or 4x
4x runs the model once at four times scale. 2x runs the same model and scales the result back down, which is often cleaner than a dedicated 2x model on photos.
We tile, run, and stitch
The image is cut into overlapping tiles and each one goes through the model separately, which is what lets this work on large images inside a browser's memory budget. We feed the model extra context around each tile and then throw that margin away, so the seams between tiles are invisible rather than blurred over.
How this runs without a server
Every other tool in this category works the same way: you upload your image, a GPU in a data centre somewhere runs the model, and the result comes back. That architecture is why they all have credits, watermarks and sign-up walls. Someone has to pay for that GPU, and it is metered by the second.
This page does it differently. When you drop in an image, your browser loads the AI model itself and runs it locally. If your browser supports WebGPU, the model runs on your own graphics hardware, which is typically five to sixty times faster than the CPU fallback. If it does not, we fall back to WebAssembly, which is slower but works everywhere.
Two things follow from that, and they are the entire reason this site exists. First, your photo never goes anywhere: it is read into a canvas in your tab and stays in your device's memory until you close it. There is no upload endpoint on this domain to send it to. Second, our cost per image is zero, so the free tier is not a loss-leader with a trapdoor in it. It is just what the thing costs to run, which is nothing.
The model file is cached by your browser after the first download. That is the one wait you have to sit through, and it only happens once per browser. After that the tool works with your network disconnected, which is a decent way to prove to yourself that nothing is being sent.
Checking that for yourself
You do not have to take our word for it, and you should not. Open your browser's developer tools, go to the Network tab, and use the tool. You will see the model coming down. You will not see your image going up, because it never does. Then turn your wifi off: once the model is loaded, the tool keeps working with no network at all, which is not something we could fake. We walk you through both checks here.
Your photo stays on your device.
Not "deleted after 24 hours". Not "encrypted in transit". Never sent. Here is how we prove it.
Frequently asked questions
How is this free when other upscalers charge per image?
Because we are not paying for the GPU, your device is. Server-side upscalers have a real cost per image and have to charge for it. Once the model is downloaded to your browser, our cost for your hundredth image is the same as for your first: zero.
Why is it slow on my machine?
Upscaling is genuinely the heaviest of the five tools here. It runs the model once per tile, and a 4x pass on a large image can be hundreds of tiles. If your browser supports WebGPU it is dramatically faster than the WASM fallback. Chrome and Edge have it on by default; Safari and Firefox are further behind.
What size image can I upscale?
We cap the input based on what your device reports it can handle, and warn you before you hit it. The hard ceiling is your browser's memory: the WASM runtime tops out around 2 GB, and a 4x upscale of a 4000px photo is a 16000px result that no browser will hold happily.
Will it fix a blurry or out-of-focus photo?
Not really, and be suspicious of any tool that says it will. This kind of model is trained to reverse downscaling and compression, so it is excellent on small, JPEG-mangled images. Motion blur and missed focus are a different problem that needs a different kind of model entirely, and no amount of upscaling recovers them.