Blur faces in photos automatically
The AI finds the faces in your photos and puts a box around each one. Check and correct the boxes, then make new pictures with the faces hidden by a mosaic, a blur or a solid color. Your photos are processed only on this device.
- Free
- No upload
- No sign-up
- Works offline
How to use
Press "Choose files" and pick your photos (up to 20). The AI puts a box around each face it finds.
Check the boxes. Drag over the photo to add a box around a face that has none, and remove the boxes you do not need. You can also choose how to hide them (mosaic, blur or solid color).
Press "Hide the faces". Check in the preview that they are hidden, then press "Save" to save the new pictures.
Questions
Are my photos sent anywhere?
No. The AI that finds the faces runs on your device too. The first time, the parts of the AI (about 14 MB) are loaded from the TEMOTO site, but nothing is sent out after you choose a photo.
Does the AI find every face?
No. It can miss very small faces, faces seen from the side, and faces partly covered by a hat, a mask or a hand. It can also put a box around something that is not a face. Check every photo as a whole before you save, and add boxes where they are missing.
Can the hidden parts be brought back later?
They cannot be restored as they were: every pixel of those parts is written again, and nothing is laid over the original. But small text and numbers under a mosaic or blur can sometimes be guessed back. To hide text or numbers, use a solid color.
Which is better: mosaic, blur or solid color?
For faces, a mosaic or a blur works (the mosaic starts at "Large"). To hide text or numbers too, such as name tags, use a solid color: small text under a mosaic or blur can sometimes be read back.
Does the location or other hidden information stay?
No. The new pictures have no location, date or device information. They have no orientation information either: the picture itself is saved upright.
What are the saved files called?
They get plain names such as "face-blur-1.jpg". Several pictures are saved together in "images-face-blur.zip". The original file names often include the date a photo was taken.
Can I use it on a phone?
Yes. You can draw and move the boxes with your finger. It needs WebAssembly SIMD, so use a recent version of Chrome, Edge or Firefox, or Safari 16.4 or later. Inside apps such as LINE, saving may not work. If so, open the page again in Safari or Chrome.
Limits
- The AI can miss faces (very small faces, faces seen from the side, faces partly covered by a hat or a mask). It can also put a box around something that is not a face. Check every photo before you save.
- Small text and numbers under a mosaic or blur can sometimes be read back. Hide text and numbers with a solid color. Reflections (in windows or glasses) or the background can also show where a photo was taken or who is in it.
- Each time, up to 20 photos can be used. Moving pictures (GIF, moving WebP or PNG) become a still picture of their first frame.
- One file can be up to 50 MB, and a picture up to 50 megapixels. HEIC (the photo format of iPhones) works only in browsers that can open it (mainly Safari).
- The first time, the parts of the AI (about 14 MB) are loaded. After that, the parts kept on this device are usually used.
- We cannot protect against things in your own environment, such as browser extensions.