What problem does it solve? Working with xAI's Grok media models requires knowing the correct endpoints, authentication headers, request fields, polling behavior, and pricing structure, which are easy to get wrong without a consolidated reference. ## Core Features & Use Cases - Image Generation and Editing: Covers text-to-image via POST /images/generations and single or multi-image editing via POST /images/edits with URL or base64 inputs. - Video Generation Modes: Documents text-to-video, image-to-video, and reference-image video using POST /videos/generations with async polling on GET /videos/{request_id}. - Prompting and Pricing Guidance: Provides Grok-specific prompt patterns, resolution constraints (480p/720p), per-image and per-second pricing, and failure-state handling. - Use Case: A developer building a product-placement clip can use reference-image video with placeholders like <IMAGE_1> to keep a character consistent while animating a short scene. ## Quick Start Use the grok-media skill to generate a 720p image-to-video clip from this product photo with a slow push-in camera move.
