This skill provides an automated interface to Google's Flow AI, bypassing manual UI hurdles to generate high-quality videos and images. It allows for programmatic control over text-to-video, text-to-image, and advanced editing features like video extension and camera manipulation.
Use this skill when you need to generate cinematic videos with Veo 3.1, create high-fidelity images with Imagen, or perform precise video edits such as upscaling, adding/removing objects, or controlling camera motion (dolly, orbit, etc.).
flow) and Python SDK (FlowClient) providing a wide array of commands for generation, editing, and batch processing.Designed for any agent capable of running a Python environment and managing browser sessions (via Playwright/CDP) to interact with Google's labs environment.
This skill has not been reviewed by our automated audit pipeline yet.