Photo Censor
Automatically find and blur, pixelate, or black out faces in a photo, or draw the regions yourself — adjustable strength and detection sensitivity. Runs entirely in your browser; your photo is never uploaded.
Input
Finds faces automatically — best for clear, front-facing photos.
Higher catches more angled or partially-visible faces, at the cost of more false positives.
Result
Upload a photo, choose auto-detect or draw manually, and press Censor faces. Detection and redaction both run in your browser — your photo is never uploaded.
Guides
Photo Censor finds faces in a photo automatically and blurs, pixelates, or blacks them out, or lets you draw the regions yourself when auto-detection misses. Detection and redaction both happen on-device with a small machine-learning model; your photo is never uploaded anywhere.
How to use it
- Drop or browse for a photo.
- Pick a detection method — Auto-detect faces, or Draw manually to drag your own boxes over the photo (useful when a face is angled, partly hidden, small, or not a face at all).
- Pick an effect — Pixelate for a blocky, obviously-redacted look, Blur for a softer effect, or Black bar to fully black out the region.
- For Pixelate or Blur, adjust the strength to control how heavy the effect is (Black bar is a flat fill, so there's no strength to tune).
- In auto mode, if it misses a face, raise detection sensitivity and press Censor faces again; lower it if it's flagging things that aren't faces.
- Press the censor button, then download the result.
Why on-device detection?
Face detection runs with a small (~230KB) on-device model, entirely in your browser — the photo itself is never sent anywhere. Re-running with a different strength or effect after censoring is instant, since only the redraw changes; only adjusting the detection sensitivity re-scans the photo.
Pixelate, Blur, or Black bar — which should I pick?
Pixelate makes it unambiguous at a glance that a face has been redacted — the usual choice for screenshots, social posts, or anything meant for a general audience. Blur reads a little softer and less "censored," which some people prefer for casual photos. Black bar is the most absolute — no trace of the original pixels remains, which is the safer pick when the photo might be re-processed or zoomed into later.
What does detection sensitivity actually change?
It's the confidence threshold the model uses to decide something is a face. Raise it to catch more faces — angled profiles, partially obscured ones, faces further from the camera — at the cost of occasionally flagging something that isn't a face. Lower it to keep only the model's most confident matches. It has no effect in manual mode, since you're drawing the regions yourself.
Does it need an internet connection?
Only briefly, to load the small on-device detection model the first time you use the tool. After that, detection and redaction both run locally — nothing about the photo itself leaves your browser.