What problem does it solve? AI video models cap each generation at a few seconds, so creators cannot produce longer clips or multi-shot narratives from a single seed video without visible breaks in motion, lighting, or subject identity. ## Core Features & Use Cases - Video continuation: Routes to Google Veo 3-1's extend-video and fast/extend-video endpoints through the runcomfy CLI, continuing a source clip with consistent motion, lighting, and identity. - Quality/cost routing: Picks full Extend for final delivery or Fast Extend for cheaper iteration drafts. - Shot-by-shot chaining: Feeds each extend output into the next call to build longer narratives, with prompting patterns for camera anchoring and single-beat extends. - Use Case: Take an 8-second Veo clip of a character and extend it to 16 seconds with a prompt like "camera continues pushing in; the character turns toward the window", then chain further beats into a short story. ## Quick Start Ask the agent to extend your video by providing the source video URL and a short prompt describing what should happen next, for example: extend this clip so the camera slowly dollies out while the character walks away.
