# depth-map-generation

depth-map-generation is a Claude Code skill that generates depth maps from photos via each::sense AI. Triggered by a prompt with an image, it returns a grayscale map for parallax animation, bokeh or AR.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 229 installs · ★ 48 repo stars
- Author: eachlabs
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/eachlabs/skills/tree/HEAD/skills/depth-map-generation/SKILL.md
- Updated: 2026-10-07
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/depth-map-generation

## What it does

Takes an image URL, sends a request to the each::sense API and returns a depth map — white for foreground, black for distant areas. Handles portraits (with precise hair and face edges), landscapes (with foreground, midground and background separation), product shots and interiors.

Requires the `EACHLABS_API_KEY` for each::sense access. Output formats: 8-bit grayscale, inverse grayscale, normalized 0–1 values or metric distance estimation. No FFmpeg or Python dependencies — works via HTTP requests to a remote API.

Supports metric depth estimation for AR/VR apps and clear layer separation for parallax effects. For portraits, outputs data suitable for bokeh; for architectural shots, captures spatial relationships between objects.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill depth-map-generation -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/depth-map-generation/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/depth-map-generation/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill depth-map-generation -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/depth-map-generation/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill depth-map-generation -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/depth-map-generation/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install eachlabs/skills skills/depth-map-generation
```

2. **Manually: put the files in place**
- File: `.github/skills/depth-map-generation/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill depth-map-generation -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/eachlabs/skills --path skills/depth-map-generation
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/depth-map-generation/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill depth-map-generation -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/eachlabs/skills/tree/HEAD/skills/depth-map-generation/SKILL.md

## When to use it
- generate a depth map from a photo for a 3D effect
- extract depth data from a portrait for bokeh
- split a landscape into foreground, midground and background layers
- obtain metric scene depth for placing AR objects
- prepare a product depth map for interactive 3D viewing

## Example prompts
- Build a depth map from `photo.jpg`, white for foreground, black for background.
- Make a depth map for portrait `portrait.jpg` with precise hair and face edges for bokeh.
- Extract a depth map from `landscape.jpg`, separating foreground, midground mountains and distant background.

## Similar
- [lingbot-map-3d-reconstruction](https://affpapa.org/en/nevibecode/skills/lingbot-map-3d-reconstruction.md) — skill · 426 installs
- [stable-diffusion-image-generation](https://affpapa.org/en/nevibecode/skills/stable-diffusion-image-generation.md) — skill · 1200 installs
- [tao-train-foundation-stereo](https://affpapa.org/en/nevibecode/skills/tao-train-foundation-stereo.md) — skill · 1600 installs
- [add-mouse-driven-orbit](https://affpapa.org/en/nevibecode/skills/add-mouse-driven-orbit.md) — skill · 1500 installs
- [scenario-blender-2d-animation](https://affpapa.org/en/nevibecode/skills/scenario-blender-2d-animation.md) — skill · 589 installs
- [tao-train-fast-foundation-stereo](https://affpapa.org/en/nevibecode/skills/tao-train-fast-foundation-stereo.md) — skill · 1600 installs

From the same set: [eachlabs/skills](https://affpapa.org/en/nevibecode/by/eachlabs/skills.md) — 102 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
