muapi Logomuapi Logo
muapi Logomuapi Logo

Depth Anything V2: Editor de vídeo de IA

Extract depth maps com Depth Anything V2. Turn any image or video into a per-frame structure signal for AI video motion transfer. Experimente grátis. Depth Anything V2 extracts a precise per-pixel depth map a partir de uma única imagem 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 e reassembled at the source resolution e frame rate, giving a temporally aligned depth sequence. This is commonly used as a motion e structure control signal for AI video generation models such as Seedance 2 e Seedance 2.5, where a driving video's depth map guides camera movement e scene geometry while the appearance is generated fresh. It is equally useful for 3D-aware compositing, relighting, background removal, e any pipeline that needs a stable geometric reference from ordinary RGB footage.

Carregar controles interativos

Extract depth maps com Depth Anything V2. Turn any image or video into a per-frame structure signal for AI video motion transfer. Experimente grátis.

📝

Visão geral

Sobre este modelo

Depth Anything V2 extracts a precise per-pixel depth map a partir de uma única imagem 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 e reassembled at the source resolution e frame rate, giving a temporally aligned depth sequence. This is commonly used as a motion e structure control signal for AI video generation models such as Seedance 2 e Seedance 2.5, where a driving video's depth map guides camera movement e scene geometry while the appearance is generated fresh. It is equally useful for 3D-aware compositing, relighting, background removal, e any pipeline that needs a stable geometric reference from ordinary RGB footage.

1Motion Transfer: Extract a depth video from a driving clip para controlar camera e 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 e Foreground Separation: Isolate subjects from backgrounds using relative depth instead of green-screen segmentation.
4Robotics e Spatial Analysis: Estimate relative scene geometry from a single camera for prototyping e research.
💰

Preço e valor

Análise de custos

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.aiNão disponível

Esta variante do modelo não está listada no Fal.ai.

ReplicateNão disponível

Esta variante do modelo não está listada no Replicate.

** Os preços dos concorrentes são estimados com base em arquiteturas de modelos e níveis de uso semelhantes.

⚙️

Detalhes técnicos

Esquema de configuração

URL do vídeostring

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

Valor padrãohttps://storage.googleapis.com/gtv-videos-bucket/sample/ForBiggerBlazes.mp4
URL da imagemstring

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

Valor padrãohttps://d3adwkbyhxyrtq.cloudfront.net/webassets/videomodels/seedream-5.0-edit.jpg
📖

Guia de implementação

Documentação do desenvolvedor

How to Use Depth Anything V2 API

  1. 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).
  2. Submit the request: Send a POST request to /api/v1/depth-anything com a publicly accessible URL.
  3. Poll or use a webhook: The task runs asynchronously; poll the returned request ID or supply a webhook_url to be notified on completion.
  4. Feed the output downstream: Use o 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"
  }'
  1. Retrieve output: Read the completed depth map URL (PNG for entrada de imagem, MP4 for video input) from the standard prediction result.
❓

Perguntas comuns

Perguntas frequentes

O que é Depth Anything V2?

It é um monocular depth estimation model that produces a grayscale depth map a partir de uma única imagem 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 e frame rate as the source. An entrada de imagem returns a single grayscale depth-map PNG.

O que é this used for com 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 com this API, then pass it into Seedance to guide camera movement e scene geometry while generating new appearance.

Is there a size or length limit?

The API accepts standard web-hosted image e 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 entrada de imagem is billed at a flat $0.05 per request.