3D Photo Maker: what it does
A 3D photo moves like a tiny camera is gliding past the scene: the person or product in front shifts against the background, so a flat picture suddenly has depth. This maker estimates how far away every part of your photo is with Depth Anything V2 Small, an open-source AI model (Apache-2.0) that runs in your browser, then redraws the photo from a moving point of view on your graphics card. Near things cover what is behind them instead of smearing over it. Pick a motion (circle, side to side, up and down or a slow zoom), set how deep the effect is and which part of the picture stays still, look around with your mouse, finger or by tilting your phone, and save a 4, 8 or 12 second video loop to post as a Reel, a TikTok, a Story or a moving product photo. The AI downloads once (27 MB) and is saved in your browser, so your photo is never uploaded.
How to use it
- Drop a photo into the box, paste it with Ctrl+V, or tap to choose one from your phone.
- The first time, allow the one-time AI download. It is saved in your browser for next time.
- Wait while the AI measures depth on your device. The photo then starts moving in 3D: move your mouse or finger over it to look around.
- Choose a motion, the depth and the still point, pick a length, and click Download video.
Tips
- Photos with a clear subject in front of a farther background (a person outdoors, a product on a table, a street, a landscape with a tree in front) give the strongest 3D effect.
- Keep Depth moderate for people: too much and faces start to bend at the edges. Landscapes and products can take more.
- Set the still point to Front to keep the subject steady while the background moves, which looks like a camera orbiting it. Background does the opposite.
- Circle is the classic 3D photo look; Zoom suits Stories and Reels, where a slow push-in feels natural.
- The video is recorded in real time, so keep the tab open and visible until it is saved. An 8 second loop takes 8 seconds.
- Hair, glass, fences and thin branches are the hardest for any depth AI. If they wobble, lower the depth.
Frequently asked questions
How do I make a 3D photo?
Add a photo and allow the one-time AI download. The AI measures depth on your device (about 10 seconds on our 4-core test PC), and the photo starts moving in 3D. Choose a motion and depth, then click Download video.
Is my photo uploaded?
No. The AI model is downloaded to your browser and runs on your device, and the video is recorded in your browser too. After the first run you can switch on airplane mode and make more 3D photos.
What video format do I get?
MP4 (H.264) in Chrome, Edge and Safari, which posts to Instagram, TikTok, Facebook and YouTube Shorts directly. Browsers that can only record WebM, such as Firefox, save a WebM file. The video is 1080 pixels on its long side, in your photo’s shape.
Can I post it as a Facebook 3D photo?
Facebook’s own 3D photo feature works from its app. This tool makes a normal video of the effect, which you can post anywhere videos are allowed, including Facebook, Instagram Reels and TikTok.
Why do edges stretch a little?
A single photo has no information about what is hidden behind the subject, so when the view moves, the tool has to fill those gaps from nearby pixels. Lower depth keeps the gaps small and the result clean.
Does it work on phones?
Yes, in recent Chrome and Safari. The AI uses a smaller size on phones to stay quick, and you can tilt the phone to look around the picture.