skills.rest
prime-skills
prime-skillsOFFICIAL
Explore all skills by this author →
GitHub

face-swap

Replaces faces or characters in images and videos via RunComfy APIs.

31|9|Updated Apr 30, 2026
Search Tags:#image editing#face swap#video editing#identity preservation#runcomfy#motion transfer#character replacement
One-click install
npx skills add https://github.com/prime-skills/runcomfy-agent-skills --skill face-swap-prime-skills
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: face-swap
Source: https://github.com/prime-skills/runcomfy-agent-skills/tree/main/face-swap
Command: npx skills add https://github.com/prime-skills/runcomfy-agent-skills --skill face-swap-prime-skills

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the complexity of replacing a face or character in still images and video by selecting an appropriate RunComfy model and managing the generation workflow.

Core Features & Use Cases

  • Video Character Swapping: Replace a character using audio-driven animation or transfer motion from a source performance to a target identity.
  • Still Image Face Editing: Perform precise single-image swaps, batch identity-preserving edits, or high-fidelity face changes with or without a reference portrait.
  • Intent-Based Routing: Choose between Wan Animate, Kling Motion Control, GPT Image Edit, Nano Banana Edit, and Flux Kontext based on the requested media type, motion needs, references, and fidelity requirements.
  • Consent and Safety Guidance: Encourages rights verification, synthetic-media disclosure, and refusal of non-consensual, defamatory, sexually explicit, or otherwise harmful face-swap requests.
  • Use Case: Create a campaign hero image with a spokesperson's face, produce consistent identity variants across a product gallery, or transfer a performance onto a stylized character.

Quick Start

Ask the face-swap skill to replace the face in your provided image or video using the supplied identity reference and save the generated result locally.

Frequently Asked Questions about face-swap

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I replace a face in a video while preserving the target identity?▼

You can perform identity-preserving face swaps in videos by using RunComfy model APIs to transfer motion from a source performance onto a target character through models like Wan Animate or Kling Motion Control.

Can I do a batch face swap across multiple still images?▼

Yes, you can perform batch identity-preserving image swaps to create consistent identity variants across a product gallery, utilizing models like GPT Image Edit, Nano Banana Edit, or Flux Kontext for high-fidelity results.

Do I need the RunComfy CLI to perform image and video face swaps?▼

Yes, replacing faces requires the RunComfy CLI, valid media URLs, authenticated access, and consent for both the source asset and substituted identity.

What are the limitations and safety requirements for swapping faces?▼

Face swapping requires rights verification and synthetic-media disclosure, and will refuse non-consensual, defamatory, sexually explicit, or otherwise harmful requests to ensure safe character replacement.

Which model is best for audio-driven character animation?▼

Wan Animate is the recommended model for audio-driven character animation, while Kling Motion Control, GPT Image Edit, Nano Banana Edit, and Flux Kontext are routed based on specific media type, motion needs, and fidelity requirements.

Related Skills

Explore More Design & Creative Skills→
prime-skillsprime-skills
31

video-edit

Route video editing requests to RunComfy models and execute transformations.

Official
Advanced
Rosetears520Rosetears520
2

frontend-dev

Build cinematic marketing frontend pages with locally generated media assets.

Community
Advanced
AceDataCloudAceDataCloud
13

wan-video

Generate AI videos from text, images, or reference videos via the /wan/videos API.

Official
Intermediate
eachlabseachlabs
28

eachlabs-face-swap

Swap faces in images and videos via the EachLabs API.

Official
Intermediate