How this Agent works
Designs high-density automotive brand film storyboards through escalating speed, mechanical detail, and environmental reaction.

Skill · v1.1.0
Video creation Skill
Builds high-density automotive brand films from speed escalation, mechanical close-ups, and environmental reaction
Designs high-density automotive brand film storyboards through escalating speed, mechanical detail, and environmental reaction.
An automotive brand or creator needs a short, high-impact TVC emphasizing performance, design language, and driving emotion, with generated visual keyframes.
canvas_read 读取 revision、现有车辆素材、镜头和场景。
建立车辆连续性锁:车身比例、前脸、灯组、轮毂、漆色、内饰、左右舵与品牌标识;不存在的细节不得随意补造。
设计“静止蓄能—机械唤醒—第一次加速—环境压缩—能力峰值—安静定格”的速度曲线,让快慢对比制造爽感。
组合低机位掠过、轮胎与材质特写、驾驶者反应、长焦压缩和环境反馈;保持道路方向、光源、车身朝向与运动模糊一致。
需要车辆英雄帧、内饰或道路关键帧时调用 generate_image;使用 generation_status 确认真实完成。
获得明确批准后,以 canvas_apply_operations 写入最小镜头批次;revision 冲突则重新读取。
The Agent returns its execution process, real Yiluna Tool results, and a final summary; until a generation job finishes, a waiting state is never packaged as a deliverable.
Currently delivers: Planning document, Keyframe images.The final video file is not included yet.
Illustrative still — not an actual run output