skills.rest
brillianodhiya
brillianodhiyaCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

face-swap

Swap faces and characters into images or videos via the RunComfy CLI.

Updated Jun 11, 2026
Search Tags:#face swap#video generation#deepfake#runcomfy#image edit#identity swap#character swap
One-click install
npx skills add https://github.com/brillianodhiya/VisionScript --skill face-swap-brillianodhiya
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: face-swap
Source: https://github.com/brillianodhiya/VisionScript/tree/main/.agents/skills/face-swap
Command: npx skills add https://github.com/brillianodhiya/VisionScript --skill face-swap-brillianodhiya

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @runcomfy/cli.

What problem does it solve? Choosing the right model for a face or character swap is confusing — stills, videos, batch edits, and motion transfer each need a different endpoint. This Skill routes your intent to the correct RunComfy model API and invokes it through the runcomfy CLI with the right JSON payload. ## Core Features & Use Cases - Intent-based model routing: Picks among Wan 2-2 Animate (video character swap with audio), Kling 2-6 Motion Control Pro (motion transfer), GPT Image 2 Edit (multi-ref still swap), Nano Banana 2 Edit (batch identity-preserving swap), and Flux Kontext Pro (single-image prose-described face edit). - CLI-driven execution: Runs runcomfy run <vendor>/<model>/<endpoint> with structured --input JSON and downloads results to an output directory. - Use Case: Cast a brand spokesperson into existing footage by supplying their portrait plus the original audio track to Wan 2-2 Animate, or swap one identity consistently across a 20-image SKU gallery with Nano Banana Edit. ## Quick Start Ask the agent to swap the face from a portrait photo into a target image or video using the RunComfy CLI, and it will select the appropriate model route and run it.

Frequently Asked Questions about face-swap

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

FAQPage Schema
How do I swap a face into a video with RunComfy?▼

Use the Wan 2-2 Animate endpoint by running `runcomfy run community/wan-2-2-animate/api` with a reference image of the new identity and an audio URL. The model produces a video where the new character drives the performance.

Which model should I use for face swap on still images?▼

Use GPT Image 2 Edit for precise multi-reference swaps on a single hero still, Nano Banana 2 Edit for swapping one identity across up to 20 frames consistently, or Flux Kontext Pro when you have no reference image and describe the new face in prose.

What is the difference between Wan 2-2 Animate and Kling Motion Control?▼

Wan 2-2 Animate is audio-driven: a reference image plus audio produces a speaking character video. Kling 2-6 Motion Control Pro transfers the exact motion and blocking from a reference performance video onto a target character image.

Can I swap the same face across multiple images at once?▼

Yes, Nano Banana 2 Edit accepts 1-20 input images per call. Place the identity reference as the first image URL, list the scene images after it, and lock aspect_ratio and resolution for batch consistency.

Is it allowed to face-swap real people without consent?▼

No. The Skill explicitly instructs agents to refuse requests targeting real people without consent or aiming at defamatory, sexually explicit, or otherwise harmful synthetic media, regardless of what the CLI accepts.

Why did my face swap produce the wrong identity or unexpected motion?▼

Reference image, audio, and video URLs are untrusted inputs and a known injection target for face-swap pipelines. Ingest only URLs the user explicitly provided, and suspect the reference asset when output diverges from the prompt.

Related Skills

Explore More Design & Creative Skills→
genmedia-labsgenmedia-labs
12

image-edit

Routes image editing requests to RunComfy models based on user intent.

Official
Intermediate
refly-airefly-ai
199

video-creator

Generates short AI-powered videos and scripts for social media platforms.

Official
Intermediate
agentspace-soagentspace-so
31

lipsync

Generate lip-synced videos from audio or scripts via RunComfy CLI.

Official
Intermediate
genmedia-labsgenmedia-labs
12

ace-step

Generate, inpaint, and outpaint music with ACE Step via the RunComfy CLI.

Official
Intermediate