01 / Find
Faces are found
Each face gets a number on the photo. Click a number to leave that face out.
Free tool
Restore an old family photo, a soft scan or a small blurry portrait. The page finds every face, rebuilds it with an open AI model, sharpens the rest of the picture, and can add colour to a black and white photo or paint out scratches you point at. It runs in this tab, so your photo is never uploaded. No sign-up, no watermark.
Faces
100% is the rebuilt face. Lower it to blend back some of the original. It updates the picture at once.
The rest of the photo
Colour
This photo looks black and white, so the rebuilt faces are kept black and white too unless you turn colour on. Colour is a second download of 115 MB, once.
Scratches and marks
The page does not find scratches by itself. Paint over the ones you want gone, then press Restore the photo, or press Remove painted marks to see the fix first. The first time this downloads another 208 MB.
Settings are kept in this browser for next time, never the photo.
This runs in your browser. Your photos are never uploaded.
How it works
01 / Find
Each face gets a number on the photo. Click a number to leave that face out.
02 / Rebuild
Every face is turned upright, rebuilt, and blended back into the photo. Drag the line to compare.
03 / Finish
Clean the background, add colour to a black and white photo, then download the full size picture.
Guide
To restore an old photo online, you need something that repairs three different problems: soft or blurry faces, a dull or noisy picture, and physical damage such as scratches and tears. This photo restorer handles the first two on its own and the third with a brush you control. It runs on your computer inside the browser tab, so a family photo never goes to a server.
-restored.The face step works on each face separately. The page finds the eyes, nose and mouth corners, turns and scales the face to a fixed upright size, and gives it to RestoreFormer++, an open face restoration model. It returns a clean face, which the page matches to the colour cast of your photo and blends back through a soft oval, so there is no hard edge. Because the model rebuilds the face from what it has learned about faces, it can add detail that was never in the photo.
The clean-up step uses Real-ESRGAN, a small open model that removes noise and sharpens the whole picture. With Size set to 2x or 4x it also enlarges the picture, and the rebuilt faces are placed on top at that larger size so they stay crisp. Large photos are limited to about 16.7 million pixels in total.
The colour step uses DDColor, the same model as the colorize photo page. It guesses natural colours for a black and white photo. The guess is not a record of the real colours.
| Setting | What you get | Good for |
|---|---|---|
| 100% | The rebuilt face as the model made it | Very soft or tiny faces, where there is little to keep |
| 60% to 85% | The rebuilt face mixed with the original | Faces that look too smooth or not quite like the person |
| 0% | Your original faces | Checking what the model changed |
| Part | Size | When |
|---|---|---|
| AI engine (ONNX Runtime) | about 27 MB | Always, first visit |
| Face finder | 0.2 MB | Always |
| Face model (RestoreFormer++) | 74 MB | When you press Restore the photo with a face found |
| Sharpening model (Real-ESRGAN) | 5 MB | When Sharpen and clean the rest is on |
| Colour model (DDColor) | 115 MB | Only if you turn colour on |
| Scratch model (LaMa) | 208 MB | Only if you paint over scratches |
Each file is checked against its published checksum before it is used, then kept in your browser so it downloads once. Nothing about your photo is sent anywhere.
Questions
No. The AI models are downloaded to your browser and run on your computer. The photo never leaves it. Only the model files come from the internet.
YuNet finds the faces (MIT licence). RestoreFormer++ rebuilds them (Apache 2.0). Real-ESRGAN sharpens the rest (BSD 3-Clause). DDColor adds colour and LaMa fills painted marks, both Apache 2.0. The licence notes sit with the files on this site.
The model does not know the person. It rebuilds a face that fits the eyes, nose and mouth it can still see, using what it learned from many faces. With a very blurry source, several faces fit, and it picks a likely one. Lower Face strength to bring back some of the original, or leave that face out.
Only the ones you paint over. Press Paint over scratches, cover the marks and press Restore the photo. A model fills the painted area from what is around it. Thin scratches work best. A large tear across a face is hard, and the fill can look wrong.
Yes. Turn on Add colour to a black and white photo. The colours are a guess, so a dress or a car may not match the real one. Colour strength lets you tone it down.
Very small faces, faces turned away, and faces covered by sunglasses, a hat or a hand can be missed. Crop closer to the face or enlarge the photo first, then try again.
The page uses your graphics card through WebGPU when the browser supports it. When it does not, the models run on the processor, which is much slower, especially for faces and for the sharpening step. A recent Chrome or Edge on a computer with a graphics card gives the faster path. You can press Stop at any time.
Not unless you choose 2x or 4x. Photos above about 16.7 million pixels, or 4096 pixels on the long side, are scaled down before they are worked on, and the page says so.
Yes. There is no sign-up, no watermark and no limit on photos. The cost is the one-time model download.
It can make a faded or blurry portrait much easier to look at. Treat the result as a careful reconstruction, not as proof of what the person looked like. Keep the original scan next to it.