seedance

What problem does it solve? Creating AI-generated video with synchronized audio typically requires navigating multiple model APIs and complex parameter setups. This Skill provides direct CLI access to ByteDance Seedance 2.0 models for text-to-video, image-to-video, and reference-to-video generation through a single command interface. ## Core Features & Use Cases - Text-to-Video (T2V): Generate videos from text prompts with optional synchronized audio, configurable duration (4-10 seconds), aspect ratios, and 480p/720p resolution. - Image-to-Video (I2V): Animate still images into videos, with support for start and end frame transitions. - Reference-to-Video (R2V): Use reference images, videos, or audio files with @Image1, @Video1, and @Audio1 placeholders to guide generation. - Quality and Fast Modes: Choose between higher-quality output (~$0.30/sec at 720p) or faster, cheaper generation (~$0.24/sec at 720p). - Use Case: A content creator needs a 10-second clip of a jazz band performing in a club with ambient audio for social media. They run a single belt command with the prompt, enable audio generation, and receive a 720p video ready to publish. ## Quick Start Ask the AI to generate a video of ocean waves crashing on rocks during a storm with synchronized audio using the Seedance 2 T2V model.