Перейти к содержимому
TakoAPI
Назад к навыкам

depth-map-generation

от eftalyurtseven

Image & Video Generation
347Число загрузок по данным clawskills.sh
0Просмотры
0 лайковВойдите, чтобы поставить лайк навыку
—Ещё нет оценок
Ваша оценка

Кратко

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

Описание

Что делает этот навык

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.

Когда его использовать

  • 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

Пример сценария

ВВОД

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

АГЕНТ
  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

ВЫВОД

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

Требования

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

Установка

clawhub install eftalyurtseven/depth-map-generation

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки