muapi Logomuapi Logo
muapi Logomuapi Logo

Depth Anything V2: AI 视频编辑器

使用 Depth Anything V2 提取深度图。将任意图像或视频转换为逐帧结构信号，用于 AI 视频动作迁移。免费试用。 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. 对于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 是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 是generated fresh. It 是equally useful for 3D-aware compositing, relighting, background removal, and any pipeline that needs a stable geometric reference from ordinary RGB footage.

交互式模型控制

使用 Depth Anything V2 提取深度图。将任意图像或视频转换为逐帧结构信号，用于 AI 视频动作迁移。免费试用。

📝

概览

关于此模型

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. 对于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 是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 是generated fresh. It 是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: 使用 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.
💰

价格与价值

成本分析

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

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

Fal.ai暂不可用

This model variant 是not listed on Fal.ai.

Replicate暂不可用

This model variant 是not listed on Replicate.

** 竞品价格根据相似模型架构和使用层级估算。

⚙️

技术详情

配置参数

视频 URLstring

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

默认值https://storage.googleapis.com/gtv-videos-bucket/sample/ForBiggerBlazes.mp4
图像 URLstring

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

默认值https://d3adwkbyhxyrtq.cloudfront.net/webassets/videomodels/seedream-5.0-edit.jpg
📖

实施指南

开发者文档

使用方法 Depth Anything V2 API

  1. 选择输入: 请仅提供以下其中一项： video_url（用于逐帧提取深度的视频），或image_url（用于生成单帧深度图的图像）。
  2. 提交请求: Send a POST request to /api/v1/depth-anything 并提供可公开访问的 URL。
  3. 轮询或使用 webhook: 任务将异步运行；请轮询返回的 request ID，或提供 webhook_url 以在任务完成时接收通知。
  4. 将输出用于后续处理: 使用 the returned depth map/video as the motion or structure control 输入for a video generation model such as Seedance 2 or 2.5, 也可用于任何支持深度信息的合成流程。
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. 获取输出: 从标准预测结果中读取已完成的深度图 URL（图像输入返回 PNG，视频输入返回 MP4）。
❓

常见问题

常见问答

What 是Depth Anything V2?

It 是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. 使用 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 输出format do I get back?

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

What 是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?

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

如何计算价格？

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