Header Logo

Docs

Start

Header Logo

Start

Header Logo

Docs

Start

All Models

WaveSpeed logo

Depth Anything Video

Depth Anything Video estimates pixel-level depth from footage and returns a grayscale depth video, using temporal context to keep spatial information consistent through motion.

Video editing

Based on verified input duration.

OfferingPrice (USD)
Usage rate$0.005 / input second
  • Based on the video input; billing steps apply in this order:
  • Round input duration up to a whole second.
  • Cap billed duration at 600 seconds.
  • Bill at least 3 seconds.
  • Round the total charge up to the next $0.01.

Depth Anything Video

Depth Anything Video produces a grayscale video containing depth estimates for each pixel of source footage. It follows the spatial arrangement of moving subjects and background geometry, creating a depth pass for further production work.

Clip-wide depth normalization and context from neighboring frames help maintain continuity as the action progresses. This supports consistent depth values through subject movement and camera motion, while retaining scene details such as silhouettes and narrow objects. The model works with live-action and rendered footage in indoor or outdoor settings.

What it's good for

In post-production, the depth video can control distance-based fog or help separate scene layers for compositing. Focus effects can use the same spatial information to distinguish foreground subjects from their surroundings.

Motion designers can use depth-driven displacement for transitions. For generative video workflows, the pass provides structural guidance based on the reference clip's motion and camera path, supporting visual reinterpretations of existing footage.

Model ID

wavespeed-ai/depth-anything-video

Output Type

Video

Pricing

$0.005 / input second

Provider

WaveSpeed

Hosting

Passthru

Depth Anything Video

Depth Anything Video produces a grayscale video containing depth estimates for each pixel of source footage. It follows the spatial arrangement of moving subjects and background geometry, creating a depth pass for further production work.

Clip-wide depth normalization and context from neighboring frames help maintain continuity as the action progresses. This supports consistent depth values through subject movement and camera motion, while retaining scene details such as silhouettes and narrow objects. The model works with live-action and rendered footage in indoor or outdoor settings.

What it's good for

In post-production, the depth video can control distance-based fog or help separate scene layers for compositing. Focus effects can use the same spatial information to distinguish foreground subjects from their surroundings.

Motion designers can use depth-driven displacement for transitions. For generative video workflows, the pass provides structural guidance based on the reference clip's motion and camera path, supporting visual reinterpretations of existing footage.