face-swap
🎯Skillfrom prime-skills/runcomfy-agent-skills
Installation
npx vibeindex add prime-skills/runcomfy-agent-skills --skill face-swapnpx skills add prime-skills/runcomfy-agent-skills --skill face-swap~/.claude/skills/face-swap/SKILL.md
|A skill for swapping faces and characters in both video and still images via RunComfy CLI, routing across models like Wan 2-2 Animate, GPT Image 2 Edit, Nano Banana Edit, Flux Kontext, and Kling Motion Control based on whether the task involves video vs. stills, single vs. batch, or motion preservation.
Overview
This skill handles face and character swapping across both video and still images using the RunComfy CLI. It classifies user intent along several axes (video vs. still, motion-preserving vs. identity-preserving, single shot vs. batch, photoreal vs. stylized) and routes to the appropriate model. For video, it uses Wan 2-2 Animate for audio-driven character replacement and Kling Motion Control Pro for transferring motion from a source performance onto a new identity. For stills, it routes to GPT Image 2 Edit for multi-reference compositional swaps, Nano Banana Edit for batch identity-consistent swaps across multiple frames, and Flux Kontext Pro for single-image prose-described face edits.
Key Features
- Video character swap with audio: Wan 2-2 Animate replaces a character in a scene using a reference portrait + audio track for synchronized speaking
- Motion transfer onto a new identity: Kling 2-6 Motion Control Pro takes a source performance video and a target character image, producing the target performing the exact same motion
- Multi-reference still image swap: GPT Image 2 Edit accepts up to 10 reference images with explicit role assignment ("face from image 2 onto body in image 1") for precise compositional control
- Batch identity-consistent swaps: Nano Banana 2 Edit processes 1-20 images per call, maintaining the same identity across all frames for SKU galleries and narrative panels
- Prose-described face editing: Flux Kontext Pro edits a single image based on a text description of the new face, without requiring a reference image of the target identity
- Consent and ethics guidance: Includes built-in guidance on consent, rights verification, and disclosure requirements for synthetic media
Who is this for?
- Video producers and content creators who need to cast brand spokespersons into existing footage or swap characters across scenes
- E-commerce teams maintaining consistent product model identity across SKU photo galleries
- Creative professionals working on stylized character animation or cinematic identity transfers
Same repository
prime-skills/runcomfy-agent-skills(25 items)
SKILL.md
More from this repository10
A smart intent-routing skill for video editing on RunComfy that automatically selects the best model (Wan 2.7 Edit-Video, Kling 2.6 Pro Motion Control, or Lucy Edit Restyle) based on what the user wants to do, from general restyling and background swaps to precise motion transfer and outfit changes.
A smart intent-routing skill that animates still images on RunComfy by selecting the optimal model: HappyHorse 1.0 I2V for general portrait and product animation with native audio, Wan 2.7 for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal composition with image, video, and audio references.
A skill for generating images with Google Nano Banana 2, the flash-tier text-to-image model in the Gemini family on RunComfy, optimized for rapid iteration, batch ideation, in-image typography rendering, and optional web-grounded context with support for resolutions from 0.5K to 4K.
A smart intent-routing skill for image editing on RunComfy that selects the optimal model from Nano Banana Edit (batch up to 20 images), GPT Image 2 Edit (multilingual text rewrite, multi-ref composition), Flux Kontext Pro (single-shot precise local edit), or Z-Image Turbo Inpaint (mask-driven region edit) based on user intent.
A Claude Code skill that enables precise single-image editing using Black Forest Labs's Flux 1 Kontext Pro model through the RunComfy CLI, with built-in prompting patterns for high-fidelity local edits.
A skill for generating text-to-video with Wan 2.7, Wan-AI's flagship motion model on RunComfy, featuring multi-reference conditioning, audio-driven lip-sync via custom audio tracks, smooth transition physics, prompt expansion control, and up to 1080p output at 15 seconds duration.
A Claude Code skill for generating text-to-video clips with HappyHorse 1.0 via the RunComfy CLI. HappyHorse 1.0 is currently ranked #1 on the Artificial Analysis Video Arena, producing native 1080p video with in-pass synchronized audio and multi-shot character consistency.
A Claude Code skill for generating video with Kling 3.0 via the RunComfy CLI. Covers all six Kling 3.0 endpoints across three rendering tiers (Standard, Pro, 4K) and two modes (text-to-video, image-to-video), with native synchronized audio and multi-shot character consistency.
A Claude Code skill that generates custom OpenAI Codex Pets from a single reference image via the RunComfy CLI. It produces a Codex-compatible spritesheet (1536x1872, 8 columns x 9 rows) and pet.json manifest using GPT Image 2 and ImageMagick, without requiring Codex Pro or an OPENAI_API_KEY.
A Claude Code skill that acts as a smart router for AI video generation across the full RunComfy model catalog. Supports text-to-video, image-to-video, and video-extend modes with models including HappyHorse 1.0, Kling 3.0, Wan 2.7, Seedance, Veo 3.1, and more.