# eachlabs-face-swap

A skill that walks your agent through face swaps on images and video using the EachLabs Predictions API. Handy when one face has to land in someone else's shot.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 322 installs · ★ 44
- 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/eachlabs-face-swap/SKILL.md
- Updated: 2026-10-07
- HTML: https://affpapa.org/en/nevibecode/skills/eachlabs-face-swap

## What it does

The skill covers the EachLabs Predictions API. Your agent picks a model, posts to `https://api.eachlabs.ai/v1/prediction`, then pulls the finished image or video. Image swaps run on `aifaceswap-face-swap`, `each-faceswap-v1` or `face-swap-new`; video swaps use `faceswap-video`. A prompt-based route through `gpt-image-v1-5-edit` is described too.

The flow has four steps. First the agent calls `GET https://api.eachlabs.ai/v1/model?slug=<slug>` to confirm the model exists and read its `request_schema`. Then it creates a prediction, polls `GET https://api.eachlabs.ai/v1/prediction/{id}` until the status reads `success` or `failed`, and takes the output URL. Requests carry an `X-API-Key` header, so set `EACHLABS_API_KEY` first — the key comes from eachlabs.ai.

Source images decide the outcome. A clear frontal portrait with even lighting swaps cleanly; a heavily occluded face in the target frame will not. Matching the light between the two shots helps.

## Install

### Claude Code (native platform)

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

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill eachlabs-face-swap -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill eachlabs-face-swap -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install eachlabs/skills eachlabs-face-swap
```

2. **Manually: put the files in place**
- File: `.github/skills/eachlabs-face-swap/SKILL.md`

### Gemini CLI

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

2. **Platform CLI**
```bash
gemini skills install https://github.com/eachlabs/skills --path skills/eachlabs-face-swap
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill eachlabs-face-swap -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/eachlabs-face-swap/SKILL.md

## When to use it
- swap a face between two photos by URL
- carry a face from a still into a video
- check a model's request schema before spending a call
- pick between image and video swap models
- replace a face with a text prompt instead of a dedicated model

## Example prompts
- Swap the face in `target-photo.jpg` with the one from `source-face.jpg`
- Run a face swap on `target-video.mp4` using `source-face.jpg`
- Check the `each-faceswap-v1` schema and start the swap

## Similar
- [skill-creator](https://affpapa.org/en/nevibecode/skills/skill-creator.md) — skill · 414180 installs
- [writing-for-agents](https://affpapa.org/en/nevibecode/skills/writing-for-agents.md) — skill · 466719 installs
- [media-use](https://affpapa.org/en/nevibecode/skills/media-use.md) — skill · 1100000 installs
- [mcp-builder](https://affpapa.org/en/nevibecode/skills/mcp-builder.md) — skill · 130949 installs
- [subagent-driven-development](https://affpapa.org/en/nevibecode/skills/subagent-driven-development.md) — skill · 237746 installs
- [orchestration](https://affpapa.org/en/nevibecode/skills/orchestration.md) — skill · 350300 installs

From the same set: [eachlabs/skills](https://affpapa.org/en/nevibecode/by/eachlabs/skills.md) — 36 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