# E12-06 · 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 5.90 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 5.90-second mark of the target video.
integrated_multimodal_description:
[Shot 1] Wide shot: a resplendent bridal palanquin is lifted again, drums and gongs swell, and the procession moves toward the mountain gate beneath raking daylight, cinematic film still (camera: static shot) <d>[Chinese] 师姐——</d>
[Shot 2] At 00:05.900, the camera cuts to <Picture 2>: close-up of Close shot: behind the swaying curtain her lips part in a soundless whisper, while he strains once and is firmly pinned down, cinematic film still (camera: push in)
overall_soundscape: Palanquin creaks as it rises, drumbeats and gongs swell, footsteps on stone, muffled struggle.
non_diegetic_music: Low war drums with a sorrowful bamboo flute weaving through a slow southern melody.