YourTools.
简体中文
Back to the catalog
Tools

Blur faces in photos

Find every face in your photos and cover it with pixels (mosaic), a blur or a black shape, to hide who is in a picture before you share it. Faces are found by a small model that runs in your browser.

Process locally

Files stay in this browser session. Closing or clearing releases them.

Choose files

JPG, PNG, WebP, BMP, TIFF, up to 20

Drop files here, or

Adjust settings

Optional: Cover faces with, Strength, Shape and more

Blur faces in photos

Run

Processes in this browser; cancel at any time

Choose files first

About this tool

Blur faces in photos automatically before you share them: every face that is found is covered with pixels (a mosaic), a blur or a black shape. It works with JPG, PNG, WebP, BMP and TIFF photos, and the photos are not uploaded.

Faces are found by YuNet, a small face detection model of about 230 KB that runs in your browser on ONNX Runtime. The first use downloads the detector and the runtime, a few MB in all, which the browser then keeps. Large photos are also searched in overlapping tiles, so small faces in group photos and crowds are found too. Up to 20 photos of up to 25 MB and 40 megapixels each, 80 MB in total, go in one run.

How to use it

  1. Choose or drop up to 20 JPG, PNG, WebP, BMP or TIFF photos.
  2. Pick what to “Cover faces with”: “Pixels (mosaic)”, “Blur” or “Black shape”, and the “Strength” from 1 (light) to 10 (heavy).
  3. Choose an “Oval” or “Rectangle” as the “Shape”, and the “Extra margin around each face (%)”, 20 by default, to cover a little more around each face, such as hair and ears.
  4. Select Run. The first run downloads the face detector; later runs start right away.
  5. Check every photo in the preview, then download them one by one or all together as a ZIP. The faces-report.json file lists how many faces were found in each photo.

Formats and limits

Input
JPG, PNG, WebP, BMP, TIFF, up to 20 files
Output
Same format as the input
Size limit
25 MB per file, 80 MB in total
Image size limit
40 megapixels per image
Settings
Cover faces with (Pixels, Blur, Black shape); Strength; Shape (Oval, Rectangle); Extra margin around each face
Privacy
Files stay in the current browser session. No file bytes are uploaded.
Price
Free, no sign-up

Common questions

Are my photos uploaded?

No. Only the face detector is downloaded from this site; the photos are read and covered in your browser and stay on your device.

Does it find every face?

It finds most faces that look towards the camera, including small ones in group photos, but it can miss faces that are very small, turned away, partly covered or in profile, and occasionally covers something that is not a face. Always check the results before you share them. To hide something it missed, crop it out, for example with “Crop images”.

Which cover is safest: mosaic, blur or black?

“Black shape” hides a face completely. A mosaic or blur keeps the photo looking natural, and the higher the strength, the less detail is left: a mosaic has 14 blocks across the face at strength 1 and only 4 at strength 10. When nobody may be recognised, use a high strength or the black shape.

What is in faces-report.json?

For each photo, its file name, the number of faces found, and the position and size in pixels of each covered area.

Does it change the format or quality of my photos?

Each photo keeps its format and file name, and only the covered areas change. JPG and WebP results are saved again at quality 0.92, and EXIF details such as location are not kept.