- Change FLOAT_LIST → FLOATS to match Yvann node output type - Add example_workflows/audio_reactive_mask_video.json with full wiring: audio sep model → analysis → remap → transform → video combine - Includes foreground/background image loading, mask extraction, and audio weights graph preview 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>