Turn photos into 3D motion. Cinematic parallax. Export-ready.
From flat photo to 3D motion video.
Cinematic camera moves, real 3D model exports, and zero uploads — the depth model runs in your browser.
Cinematic 3D motion
Four camera presets — dolly in, sway, orbit, and pull out — turn a photo into a parallax clip in 16:9, 1:1, or 9:16. Preview the move live, then export watermark-free 720p MP4/WebM free; 1080p is Pro.
100% on-device and private
Depth estimation, mesh building, brush edits, and video rendering all run in your browser through WebGPU with automatic WASM fallback. Photos and video frames never leave your device.
Real 3D files, not just a clip
Export the same depth as a textured relief mesh or a vertex-colored point cloud: GLB, OBJ, STL, PLY, and USDZ for AR Quick Look, Blender, and game engines, plus the grayscale depth map as PNG.
Free 518px depth, Pro 700px
Every plan gets Depth Anything V2 with watermark-free video and all 3D formats. Pro raises depth maps from 518px to 700px, adds a manual depth brush, and unlocks 1080p/16 Mbps motion exports.
Add a photo, orbit, export.
- 01
Add a photo
Drag and drop, paste, or browse. Portraits, products, food, architecture — anything with layered depth works best.
- 02
Depth is estimated
Depth Anything V2 runs locally through WebGPU or WASM in seconds. The first run caches the model (~27–50 MB).
- 03
Orbit, animate, export
Drag to orbit and tune the depth, then play a cinematic move and export MP4/WebM — or download GLB, OBJ, STL, PLY, USDZ, and the depth PNG. Pro adds 700px depth, 1080p video, and the depth brush.
About Depth 3D
A free browser tool that turns a single photo into an interactive 3D object you can orbit, tune, and export. It is built for people who want a picture to feel more alive — a product shot for a store listing, a portrait, a plate of food, a building facade — or who need a starting 3D file for a design project without paying for cloud photo-to-3D services or waiting in their render queues.
Two representations come out of the same depth estimate: a textured relief mesh under studio-style lighting, and a vertex-colored point cloud that lays the scene's depth layers bare.
How it works
Depth Anything V2 Small, a state-of-the-art monocular depth network (Apache-2.0 licensed), runs in your browser through Transformers.js — on WebGPU where available, WebAssembly everywhere else. It maps every pixel to a relative scene distance, which the tool then turns into geometry: a subdivided plane displaced along the depth field and skinned with your original photo, or a point cloud sampled from the same field. Exports use the standard three.js exporters: GLB with the texture embedded, OBJ packaged as a ZIP with the MTL material and texture PNG, and USDZ that opens directly in AR Quick Look on iPhone and iPad.
Making a 3D motion video
The same depth field that builds the mesh also drives a virtual camera, so you can render a cinematic parallax clip without any other app. Open the 3D Motion panel and pick a camera preset — dolly pushes toward the subject, sway slides side to side, orbit circles the scene, and pull out retreats while widening the view. Press Play to preview the move before exporting, then set a duration from 3 to 10 seconds, and turn on the ping-pong loop for clips that reverse seamlessly on social posts.
Three aspect ratios cover every placement: 16:9 for YouTube and desktop, 1:1 for feeds, and 9:16 for Reels, Shorts, and TikTok. Free accounts render watermark-free 720p (1280×720, 720×720, 720×1280) at 8 Mbps; Pro renders 1080p at 16 Mbps. Rendering is frame-by-frame on-device capture at 30 fps, so every playback is pixel-identical; the file is MP4 where the browser supports H.264 encoding (Safari, recent Chrome) and WebM elsewhere.
Pro users can also brush depth over areas the model under-separated — raising a foreground subject makes it travel more strongly through the frame, while lowering a flat backdrop keeps it calm. The brush changes only the depth used for geometry and motion, never the original photo, and the restore tool paints the model's estimate back.
Honest 2.5D — what it is and isn't
A single photograph contains no information about surfaces the camera never saw, so the tool reconstructs front-facing geometry only — in the spirit of the classic Facebook 3D photos rather than a full generative image-to-3D model like TripoSR or Meshy, which run on data-center GPUs and have no browser-capable quantized weights today. The back of an object stays flat. What you get instead is speed and privacy: depth in a couple of seconds, entirely on your own hardware, with standard 3D files as the output.
Getting better reconstructions
Photos with clear depth separation work best: a subject well in front of its background, layered foreground and scenery, a building seen at a slight angle. Depth strength controls how far the geometry protrudes toward the camera; smoothing softens the depth field before displacement, which helps on noisy scans; mesh detail trades vertex count for fidelity, while point size adapts the cloud. The grayscale depth map can be downloaded separately for use in other pipelines.
Limits & requirements
The model downloads once (~50 MB on WebGPU, ~27 MB on WebAssembly) and is cached by the browser; each photo afterwards processes in a few seconds. Chrome, Edge, and other Chromium browsers get the WebGPU path; Safari and Firefox run on WASM with identical output. Very flat subjects — document scans, perfectly frontal walls — have little depth to reveal. Mesh exports carry your photo as an embedded texture in GLB; the OBJ export is a ZIP containing the MTL material and texture PNG.
Privacy
Photos are decoded, depth-estimated, and rebuilt into 3D entirely inside your browser's memory. Nothing is uploaded, queued, or stored on a server, and there is no watermark or usage limit. Once the model is cached, the tool keeps working offline.