Generates cinematic AI videos and animations using Google's Veo 3.1 model directly through Claude Code.
This skill integrates Google's Veo 3.1 video generation capabilities into the Claude Code environment, enabling developers and creators to produce high-quality video content from text prompts or static images. It features a specialized prompt engineering framework that prioritizes cinematography and camera movement, while offering advanced controls for synchronized audio, multi-shot timestamp prompting, and character consistency. Whether you need a simple animation or a complex cinematic sequence, this skill automates the API interaction and provides the structural guidance needed for professional-grade AI video production.
주요 기능
01Advanced multi-shot sequences via timestamp-based prompting
020 GitHub stars
03Text-to-video and image-to-video generation using Google Veo 3.1
04Synchronized audio generation with specific SFX and dialogue directions
05Support for character consistency using up to three reference images
06Cinematography-first prompt formula for professional camera control
사용 사례
01Animating static character designs into consistent video sequences for storytelling
02Creating cinematic marketing clips and product shots with precise camera movements
03Generating social-media ready video content with built-in sound effects and ambient audio
