# E11-04 · H3 提示词

首帧 = **f1.png**。图片按 Picture 序号挂载：

- Picture 1 = f1.png（**首帧**，钉 0.00 秒）
- Picture 2 = f2.png（钉 4.00 秒）
- Picture 3 = f3.png（钉 9.40 秒）

---

How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 2) aligns with the 4.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 9.40-second mark of the target video.
integrated_multimodal_description:
[Shot 1] wide shot of Wide framing: the aged recluse releases a cold sneer, sweeping his sleeve as he withdraws backward into the pale drifting fog beside the dark cave mouth and wet stones, cinematic film still (camera: static shot) <d>[Chinese] 好，我答应你。先治伤，别的事往后放。</d>
[Shot 2] At 00:04.000, the camera cuts to <Picture 2>: wide shot of Wide tracking shot: the gaunt youth staggers toward the misty reed beds carrying the pale-robed companion on his back, stepping unevenly out of the marsh haze into the open water fog, cinematic film still <d>[Chinese] 师父就在外面。师姐，撑住。</d>
[Shot 3] At 00:09.400, the camera cuts to <Picture 3>: medium shot of the scene described, cinematic film still (camera: static shot)
overall_soundscape: Cold sneer and a sharp rustle of sleeves in the damp marsh air, then heavy staggered footsteps and breath over wet ground.
non_diegetic_music: Low, sparse erhu drone with a faint pulsing guqin, tense and resigned, fading as the pair vanish into the mist.