Find objects and outlines
Depth Anything Video
Generates depth maps from video using Video Depth Anything (CVPR 2025). Produces per-frame depth estimation with temporal consistency across frames. Supports 3 model sizes (Small, Base, Large), 5 colormaps including grayscale, side-by-side comparison with the original video, and raw depth export as .npz. Useful for 3D reconstruction, video effects, compositing, and scene understanding.
Opens the video studio with Depth Anything Video ready to use. You can look around as a guest. Running it takes the Pro plan or higher.
What Depth Anything Video makes, what it needs and what you get
What it makes
Find objects and outlines
Finds objects, depth, poses and outlines in a video.
What you need
- The video to work on
What you get
Masks, depth maps or outlines
- resolutions up to 1080p
About Depth Anything Video
Depth Anything Video finds objects, depth, poses and outlines in a video. It is made by Open Source.
To use it, you provide the video to work on. You get masks, depth maps or outlines. Options include resolutions up to 1080p.
A 5 s result costs about 2,000 credits. Longer or shorter results cost in proportion, about 400 credits per second. It is included from the Pro plan and up. You run it in the video studio, in your browser.
Best for
Typical uses for this kind of model.
- Cutting parts out of a picture
- Guiding other edits
- Compositing and 3D work
How to use Depth Anything Video
- 1
Add the video to work on
Upload your files, or pick them from your library. Nothing else is needed to start.
- 2
Check the settings
Pick the options you want. The cost updates as you choose, and is shown before you generate.
- 3
Generate your video
Masks, depth maps or outlines. Your result appears in the studio, ready to download.
Other models for this job
Same job: find objects and outlines. Compare before you choose.
SAM 3.1 builds comes with Object Multiplex, a shared-memory approach for joint multi-object tracking that delivers faster speeds with larger number of objects tracked.
SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.
Predict poses from videos.