What problem does it solve? Choosing the wrong image-to-video model wastes generation credits and produces weak results; this Skill classifies user intent and routes each animation request to the right RunComfy model with the correct parameters. ## Core Features & Use Cases - Intent-based model routing: Selects HappyHorse 1.0 I2V for portrait/product animation with native audio, Wan 2.7 with audio_url for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal image + reference video + reference audio composition. - Documented schemas and prompting patterns: Each route includes parameter tables, CLI invocation examples, and prompting tips so output quality improves without trial-and-error iterations. - Use Case: A marketer needs the same spokesperson image lip-synced to voiceovers in three languages; the Skill routes to Wan 2.7, reuses the prompt with a locked seed, and swaps audio_url per language. ## Quick Start Ask the agent to animate a still image into a video on RunComfy, describing the motion you want and providing the image URL.
