跳到正文
TakoAPI
返回技能列表

depth-map-generation

由 eftalyurtseven 提供

Image & Video Generation
347下载量由 clawskills.sh 提供
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Generate depth maps from images using each::sense AI.

描述

该技能的功能

Generates depth maps from 2D images using the each::sense AI API. Outputs grayscale, normalized, or metric depth data from single images. Supports portraits, landscapes, products, and architectural scenes.

Extracts depth from a single image rather than requiring stereo camera setups or LiDAR hardware.

何时使用

  • Adding portrait mode blur to photos without a dual-lens camera
  • Creating parallax animations from still images for social media
  • Preparing product photos for 3D interactive e-commerce views
  • Generating metric depth data for placing AR objects in a room
  • Converting 2D photos to stereoscopic 3D for VR headsets

示例工作流

输入

User asks: Generate a depth map from this portrait photo for bokeh effect

智能体
  1. 1

    Receives the portrait image URL from the user

  2. 2

    Sends POST request to sense.eachlabs.run/chat with mode set to max

  3. 3

    Instructs the model to focus on accurate edge detection around subject and hair

  4. 4

    Receives grayscale depth map PNG in response

  5. 5

    Returns the depth map to the user ready for use in photo editing software

输出

Grayscale PNG depth map with white near-subject foreground and dark background, suitable for depth-of-field compositing

前置要求

  • EACHLABS_API_KEY environment variable
  • each::sense account with sufficient balance at eachlabs.ai

安装

clawhub install eftalyurtseven/depth-map-generation

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接