face-swap

Official

Swap faces in images and videos fast.

Authorruncomfy-com
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Face-swap helps you substitute one identity’s face into still images or videos by routing to the right RunComfy model endpoints based on whether the input is a photo or a video and whether you need motion preservation.

Core Features & Use Cases

  • Video character + face swap with motion from audio: Uses Wan 2-2 Animate to drive a new identity from a reference portrait plus an audio track.
  • Motion-preserving identity swap: Uses Kling 2-6 Motion Control Pro to transfer a reference performance video onto a target character image.
  • Still-image face swap with strong fidelity controls: Uses Nano Banana 2 Edit for batch identity-consistent swaps, GPT Image 2 Edit for precise multi-reference compositional swaps, and Flux Kontext Pro for single-image, high-fidelity edits via a declarative instruction.

Quick Start

Use the face-swap skill to swap a face into a video by providing a target identity image and an audio track as inputs to runcomfy.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: face-swap
Download link: https://github.com/runcomfy-com/skills/archive/main.zip#face-swap

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.