pixelate.run

Turn an image into pixel art

Open a photo or a drawing and it is redrawn as pixel art straight away. Set how big the pixels are and how many colours it may use, then save it full size, or at one pixel per block for sprites and icons. The image never leaves your device.

Drop or paste an image herePress Ctrl+V (⌘V on a Mac), or click to choose a file.

Hokusai’s “Great Wave off Kanagawa”, redrawn in 16 colours. Point at it to see the print it was made from.

How it works

  1. Open an imageChoose a file, drop it anywhere on the page, or paste it from the clipboard.
  2. Set the pixels and the paletteDrag the pixel size slider, and keep all colours or pick a palette of 64, 32, 16 or 8. The picture is redrawn as you go.
  3. Save itDownload it at the size of the original, or switch on “Save at one pixel per block” for the small version that a game engine or a sprite editor scales up.

Questions

What size should the pixels be?
For a sprite or an icon, aim for 16 to 64 blocks along the short side; the count is shown next to the slider. For a poster that still reads as the original photo, 80 to 120.
How are the colours chosen?
From the picture itself. Its colours are split into as many groups as you ask for, each time along the channel in which they differ most, and every block takes the average of its group. Nothing is matched against a fixed set, so skies and skin keep their character.
Does it look for faces and private text, like the other pages?
Not unless you ask. From this page nothing is searched and no recognition model is downloaded. “Look for private details” in the panel starts the search if you want it.
Is my image uploaded?
No. Text recognition, the privacy model, face detection and code scanning all run inside this page. Its security policy only lets it talk to pixelate.run itself, and once the models are cached it works with the network switched off. If you choose fast cloud recognition instead of the on-device model, the text read from the image, and only that, is sent to pixelate.run, checked by an AI model on Cloudflare and not kept.
Can a pixelated number be recovered?
Not from an image made here. An ordinary mosaic or blur can sometimes be reversed by matching it against known fonts. Before text is pixelated or blurred, this tool shuffles the blocks at random, which leaves nothing to match. A solid block removes the pixels outright.
What about the location stored in my photo?
The saved image is drawn from scratch, so GPS position, camera model and every other piece of metadata stay behind.
Will it work on my phone?
Yes, in current versions of Safari, Chrome, Firefox and Edge. The first image takes a few seconds longer while the recognition models download (about 11 MB); after that they load from your device.
Why does it download a large model on a computer?
To tell a name, a nickname or an address from ordinary words, it uses OpenAI Privacy Filter, an open model of about 917 MB that runs in the page like everything else. It downloads once, in the background while the patterns give a first answer, and then stays on your device. Phones and tablets use the patterns alone.

More ways in