What makes WaveSpeedAI Face Swapper notable?

1.1K downloads. Trust evidence available

How should WaveSpeedAI Face Swapper be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

WaveSpeedAI Face Swapper

Swap faces in images and videos using WaveSpeed AI. Supports image face swap and video face swap with multi-face targeting, with automatic lighting and skin tone adaptation. Only for media the user has the right to edit and faces whose owners have consented; refuse impersonation, deception, or sexual content. Use when the user wants to replace a face in an image or video with another face. Skill: WaveSpeedAI Face Swapper Owner: wavespeed Summary: Swap faces in images and videos using WaveSpeed AI. Supports image face swap and video face swap with multi-face targeting, with automatic lighting and skin tone adaptation. Only for media the user has the right to edit and faces whose owners have consented; refuse impersonation, deception, or sexual content. Use when the user wants to replace a face in an ima

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

2.0.1

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 2.0.1release · observed Sep 5, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17epnq4kcsv1261rq3e9gvwcx8dth5q:wavespeed-face-swapper

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-face-swapper/snapshot"

Documentation

CLAWHUB

42,425 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: wavespeed-face-swapper
description: Swap faces in images and videos using WaveSpeed AI. Supports image face swap and video face swap with multi-face targeting, with automatic lighting and skin tone adaptation. Only for media the user has the right to edit and faces whose owners have consented; refuse impersonation, deception, or sexual content. Use when the user wants to replace a face in an image or video with another face.
metadata:
  author: wavespeedai
  version: "2.0"
---

# WaveSpeedAI Face Swapper

Swap faces in images and videos using WaveSpeed AI, with automatic lighting and skin tone adaptation. Supports targeting specific faces when multiple people are present.

**Read [Responsible use](#responsible-use) before running anything.** Face swapping edits a real person's likeness; this skill is for consented, lawful, non-deceptive edits only.

## Setup

Install the open-source CLI once and sign in; the CLI stores the key, so never ask the user to paste an API key into the chat:

```bash
npm install -g @wavespeed/cli
wavespeed login          # opens https://wavespeed.ai/accesskey and stores the key
wavespeed status         # confirms you are signed in
```

For CI or one-off shells, `WAVESPEED_API_KEY` in the environment also works.

Prefer MCP tools over shell commands? The same platform is exposed by [`@wavespeed/mcp`](https://github.com/WaveSpeedAI/mcp-server) (`npx -y @wavespeed/mcp`; tools `search_models`, `get_model_schema`, `get_price`, `upload_file`, `run_model`, `get_prediction`). It shares the CLI's stored login. Every example below maps one-to-one onto `run_model` with the same model id and input fields.

## Quick Start

### Image Face Swap

```bash
# Upload local images to get URLs
OUTPUT_URL=$(wavespeed run wavespeed-ai/image-face-swap \
  -i image=@./target-photo.png \
  -i face_image=@./reference-face.png \
  --json | jq -r '.outputs[0]')
```

### Video Face Swap

```bash
# Upload local files to get URLs
OUTPUT_URL=$(wavespeed run wavespeed-ai/video-face-swap \
  -i video=@./video.mp4 \
  -i face_image=@./reference-face.png \
  --json | jq -r '.outputs[0]')
```

Existing URLs work as-is:

```bash
OUTPUT_URL=$(wavespeed run wavespeed-ai/image-face-swap \
  -i image="https://example.com/target-photo.jpg" \
  -i face_image="https://example.com/reference-face.jpg" \
  --json | jq -r '.outputs[0]')
```

## API Endpoints

### Image Face Swap

**Model ID:** `wavespeed-ai/image-face-swap`

Replace a face in an image with a reference face.

#### Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `image` | string | Yes | -- | URL of the image containing the face to replace |
| `face_image` | string | Yes | -- | URL of the reference face image to swap in |
| `target_index` | integer | No | `0` | Which face to replace (0 = largest face, 1-10 for others) |
| `output_format` | string | No | `jpeg` | Output format. One of: `jpeg`, `png`, `webp` |

#### Exampl

_meta.json

{
  "ownerId": "kn733k72mbe41a710dd1kfpg2s8257bs",
  "slug": "wavespeed-face-swapper",
  "version": "2.0.1",
  "publishedAt": 1788625830655
}

skill-card.md

## Description:

Swap faces in images and videos using WaveSpeed AI with multi-face targeting, automatic lighting and skin tone adaptation, and consent-focused refusal guidance.

This skill is ready for commercial/non-commercial use.

## Publisher:

[wavespeed](https://clawhub.ai/user/wavespeed)

### License/Terms of Use:

MIT-0

## Use Case:

External users and developers use this skill to perform consented, lawful image or video face swaps through WaveSpeed AI while refusing impersonation, deception, sexual content, and other prohibited likeness edits.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Selected media is processed by WaveSpeed and a WaveSpeed login may be stored locally.

Mitigation: Use only consented, lawful, non-deceptive media and rely on local login or environment credentials without sharing keys in chat.

Risk: Global npm installs can add ordinary third-party package and local privilege risk.

Mitigation: Avoid running npm commands as administrator and prefer pinned or reviewed package versions where feasible.

Risk: Face swapping can create misleading likeness edits if consent, rights, or disclosure are unclear.

Mitigation: Confirm consent, media rights, non-deceptive purpose, no sexual or intimate content, no minors, and recommend labeling shared outputs as AI-edited.

## Reference(s):

- [ClawHub Skill Page](https://clawhub.ai/wavespeed/skills/wavespeed-face-swapper)
- [WaveSpeed MCP Server](https://github.com/WaveSpeedAI/mcp-server)

## Skill Output:

**Output Type(s):** [Shell commands, Configuration instructions, Guidance]

**Output Format:** [Markdown with inline bash code blocks]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Produces WaveSpeed output URLs or downloaded media files when commands are executed.]

## Skill Version(s):

2.0.1 (source: server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular