Face Swap

Routes your face swap request to one of five RunComfy models based on what you're actually trying to do. Single still with precise composition control goes to GPT Image 2 Edit, batch identity preservation to Nano Banana 2, audio-driven character animation to Wan 2-2 Animate, motion transfer to Kling Motion Control Pro. The skill itself is thin wrapper around runcomfy CLI invocations, but the routing logic saves you from reading five model cards. The consent section is blunt and necessary: you're responsible for rights and disclosure, the API will run whatever you feed it. Useful if you work with synthetic media regularly and want Claude to pick the right endpoint instead of always defaulting to the first thing that says "face swap."

skills.sh installs: 120.3K
GitHub stars: 11
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add agentspace-so/runcomfy-agent-skills --skill face-swap --agent claude-code

Installs into .claude/skills of the current project.

Files

Face Swap

Swap a face into a still or a video — RunComfy supports both via the runcomfy CLI. This skill routes across the available model API endpoints (community Wan 2-2 Animate, GPT Image 2 Edit, Nano Banana Edit, Flux Kontext, Kling Motion Control) by the user's actual intent.

runcomfy.com · Character-swap feature · CLI docs

Powered by the RunComfy CLI

# 1. Install (see runcomfy-cli skill for details)
npm i -g @runcomfy/cli      # or:  npx -y @runcomfy/cli --version

# 2. Sign in
runcomfy login              # or in CI: export RUNCOMFY_TOKEN=<token>

# 3. Swap
runcomfy run <vendor>/<model>/<endpoint> \
  --input '{"image_url": "...", "identity_url": "..."}' \
  --output-dir ./out

CLI deep dive: runcomfy-cli skill.