What problem does it solve? Creating video content traditionally requires filming, editing software, and significant production time. This Skill lets you generate videos directly from text prompts, images, or reference media using state-of-the-art AI models like Google Veo, Seedance 2.0, HappyHorse, and Wan, all through a single CLI. ## Core Features & Use Cases - Text-to-Video & Image-to-Video: Generate clips from prompts or animate still images with models like Veo 3.1, Seedance 2.0, and Wan 2.5, with optional synchronized audio. - Avatars, Lipsync & Editing: Create talking-head videos with OmniHuman, apply lipsync with Fabric or PixVerse, and edit videos using natural language with HappyHorse Edit. - Utilities: Upscale video quality with Topaz, add foley sound effects with HunyuanVideo, and merge clips with transitions. - Use Case: A marketer needs a 10-second product teaser with sound. They run Seedance 2.0 with a text prompt and audio generation enabled, then merge it with an existing clip using the media merger. ## Quick Start Ask the AI to generate a video of a drone shot flying over a forest using the Veo model via the belt CLI.
