What problem does it solve? Building video generation into an application requires handling asynchronous task creation, status polling, and result retrieval, which is error-prone to implement from scratch. This Skill provides ready-to-use patterns for generating videos from text prompts or images with the z-ai-web-dev-sdk. ## Core Features & Use Cases - Text-to-Video and Image-to-Video: Create videos from text descriptions, a single starting image, or start/end keyframe pairs with configurable resolution, frame rate, duration, and quality mode. - Asynchronous Task Management: Create generation tasks, poll task status with fixed intervals or exponential backoff, and extract the resulting video URL from multiple possible response fields. - CLI and SDK Workflows: Use the z-ai CLI for quick one-off generation with automatic polling, or the SDK for batch generation, queue management, Express.js endpoints, and WebSocket status updates. - Use Case: A developer building a social media tool can submit a prompt like "A sunset over the ocean", poll the returned task ID until it succeeds, and serve the generated MP4 URL to end users. ## Quick Start Use the video generation skill to create a five-second 1080p video from the prompt "A cat playing with a ball" and poll until the video URL is ready.
