# Create Consented Face Swaps with RunComfy

Choosing a face-swap model for each image or video workflow can be difficult. This skill routes consented requests to suitable RunComfy endpoints and CLI commands.

## Install

```bash
npx skillstore add agentspace-so/face-swap
```

## Metadata

- Status: approved
- Slug: agentspace-so-face-swap
- Skillstore revision: r2
- Version status: missing
- Tree hash: 9983b6d6a3bb3468318713cb3c27c8449a1f7da43a4cf5ef93442ab7fc1e03b9
- Author: agentspace-so
- GitHub username: agentspace-so
- License: MIT
- Repository: https://github.com/agentspace-so/runcomfy-agent-skills/tree/main/face-swap/
- Ref: 181fdefcafd96b041926e61c4b2e306ca7e7820e
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: confirmation\_required
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: external\_commands, network, filesystem
- Quality score: 38
- Quality tier: warning
- Public page: https://skillstore.pages.dev/skills/agentspace-so-face-swap
- Manifest: https://skillstore.pages.dev/api/skills/agentspace-so-face-swap/manifest

## Capabilities

- Classifies requests by still image, video, motion preservation, identity preservation, batch size, and visual style.
- Routes work across Wan 2-2 Animate, Kling Motion Control, GPT Image 2 Edit, Nano Banana Edit, and Flux Kontext.
- Builds RunComfy CLI invocations for audio-driven animation, motion transfer, multi-reference editing, batch editing, and local face changes.
- Explains required inputs, model limits, output handling, and common CLI exit codes.
- Provides consent, disclosure, package installation, token storage, endpoint, and generated-file guidance.

## Use Cases

- Prepare campaign portraits: Brand designers can place a consenting spokesperson into approved scenes while preserving pose, clothing, lighting, and background.
- Transfer character motion: Video editors can apply an approved performance to a target character while preserving the source movement.
- Create consistent image sets: Creative developers can apply one approved identity across multiple product images or narrative frames.

## Prompt Templates

### Choose a route

```
I have [still image or video] and consent from every depicted person. Choose the best RunComfy route and explain the required inputs.
```

### Edit one portrait

```
Use the approved face in [identity image] to replace the face in [scene image]. Preserve pose, clothing, hair, lighting, and background.
```

### Process a consistent batch

```
Apply the approved identity in [reference image] across [scene images]. Keep aspect ratio and resolution consistent, and change no other scene elements.
```

### Plan motion-preserving video

```
Use [performance video] and [approved character image] for motion transfer. Select the model, validate inputs, run the job, and summarize disclosure needs.
```

## Limitations

- Requires the RunComfy CLI, an authenticated account, network access, and supported hosted model endpoints.
- Sends asset URLs and identity media to external services, subject to their privacy and retention terms.
- Does not technically enforce consent, identity rights, platform disclosure, or harmful-content restrictions.
- Generated results may change unintended details or produce inconsistent identity, lighting, motion, and facial features.

## Best Practices

- Confirm identity rights, source rights, and platform disclosure requirements before processing media.
- Use clear, well-lit references and state exactly which visual details must remain unchanged.
- Review every result for identity accuracy, unintended edits, privacy exposure, and required synthetic-media labels.

## Anti Patterns

- Do not create impersonation, defamatory, sexual, fraudulent, or nonconsensual media involving real people.
- Do not place secrets, local paths, or private media URLs into prompts or public asset links.
- Do not assume a successful model response proves consent, factuality, or platform compliance.

## Security Audit

- Audited at: 2026-07-23T08:47:15.913\+00:00
- Summary: Most static findings are false positives caused by Markdown formatting, documentation links, placeholder URLs, and model-selection prose. Confirmed risks include third-party command execution, external processing of biometric media, unsafe shell quoting, and advisory-only consent controls.

## Stats

- Views: 40
- Downloads: 8
- Favorites: 0
- Popularity score: 0