Depth Anything V2: AI Video Editor

Extract depth maps with Depth Anything V2. Turn any image or video into a per-frame structure signal for AI video motion transfer. Try free.

📝

Tổng quan

Về mô hình này

Depth Anything V2 extracts a precise per-pixel depth map from a single image or every frame of a video, producing a grayscale map where brightness encodes relative distance from the camera. For video input, frames are processed in batches on GPU and reassembled at the source resolution and frame rate, giving a temporally aligned depth sequence. This is commonly used as a motion and structure control signal for AI video generation models such as Seedance 2 and Seedance 2.5, where a driving video's depth map guides camera movement and scene geometry while the appearance is generated fresh. It is equally useful for 3D-aware compositing, relighting, background removal, and any pipeline that needs a stable geometric reference from ordinary RGB footage.

1Motion Transfer: Extract a depth video from a driving clip to control camera and scene motion in Seedance 2/2.5 video generation.

23D-Aware Compositing: Use per-pixel depth to composite, relight, or apply depth-of-field effects on ordinary footage.

3Background and Foreground Separation: Isolate subjects from backgrounds using relative depth instead of green-screen segmentation.

4Robotics and Spatial Analysis: Estimate relative scene geometry from a single camera for prototyping and research.

💰

Giá cả & Giá trị

Phân tích chi phí

nhà cung cấp	Chi phí	Ghi chú
muapiapp	$0.04/sec of video, or $0.05 flat per image	Pay per second of input video processed, or a flat rate for single-image depth maps, with no subscription.
Fal.ai	Không khả dụng	This model variant is not listed on Fal.ai.
Replicate	Không khả dụng	This model variant is not listed on Replicate.

muapiapp$0.04/sec of video, or $0.05 flat per image

Pay per second of input video processed, or a flat rate for single-image depth maps, with no subscription.

Fal.aiKhông khả dụng

This model variant is not listed on Fal.ai.

ReplicateKhông khả dụng

This model variant is not listed on Replicate.

** Giá của đối thủ cạnh tranh được ước tính dựa trên kiến trúc mô hình và cấp độ sử dụng tương tự.

⚙️

Chi tiết kỹ thuật

Lược đồ cấu hình

tham số	Loại	Mô tả	Mặc định
Video URL	string	The URL of the driving video to extract a per-frame depth map from. Provide exactly one of video_url or image_url.	`https://storage.googleapis.com/gtv-videos-bucket/sample/ForBiggerBlazes.mp4`
Hình ảnh URL	string	The URL of a single image to generate a depth map from. Provide exactly one of video_url or image_url.	`https://d3adwkbyhxyrtq.cloudfront.net/webassets/videomodels/seedream-5.0-edit.jpg`

Video URLstring

The URL of the driving video to extract a per-frame depth map from. Provide exactly one of video_url or image_url.

Giá trị mặc địnhhttps://storage.googleapis.com/gtv-videos-bucket/sample/ForBiggerBlazes.mp4

Hình ảnh URLstring

The URL of a single image to generate a depth map from. Provide exactly one of video_url or image_url.

Giá trị mặc địnhhttps://d3adwkbyhxyrtq.cloudfront.net/webassets/videomodels/seedream-5.0-edit.jpg

📖

Hướng dẫn thực hiện

Tài liệu dành cho nhà phát triển

How to Use Depth Anything V2 API

Choose your input: Provide exactly one of video_url (a driving video for per-frame depth extraction) or image_url (a single frame for a one-off depth map).
Submit the request: Send a POST request to /api/v1/depth-anything with a publicly accessible URL.
Poll or use a webhook: The task runs asynchronously; poll the returned request ID or supply a webhook_url to be notified on completion.
Feed the output downstream: Use the returned depth map/video as the motion or structure control input for a video generation model such as Seedance 2 or 2.5, or for any depth-aware compositing pipeline.

curl -X POST "https://api.muapi.ai/api/v1/depth-anything" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video_url": "https://example.com/driving-video.mp4"
  }'

Retrieve output: Read the completed depth map URL (PNG for image input, MP4 for video input) from the standard prediction result.

❓

Câu hỏi thường gặp

Thường xuyên hỏi

What is Depth Anything V2?

It is a monocular depth estimation model that produces a grayscale depth map from a single image or every frame of a video, where pixel brightness represents relative distance from the camera.

Should I provide video_url or image_url?

Provide exactly one. Use video_url to extract a per-frame depth video (e.g. for motion-transfer control signals), or image_url for a single-frame depth map.

What output format do I get back?

A video input returns a grayscale depth-map video at the same resolution and frame rate as the source. An image input returns a single grayscale depth-map PNG.

What is this used for with Seedance 2 or 2.5?

Seedance's motion-transfer workflows accept a depth video as a structure/motion control signal. Extract the depth map from a driving video with this API, then pass it into Seedance to guide camera movement and scene geometry while generating new appearance.

Is there a size or length limit?

The API accepts standard web-hosted image and video files. Very long videos increase processing time since every frame is run through the depth model; keep driving videos to the length you actually need for the downstream generation.

How is pricing calculated?

Video input is billed at $0.04 per second of input video. A single image input is billed at a flat $0.05 per request.