# E01-04 · 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 5.00 秒）
- Picture 3 = f3.png（钉 9.00 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 5.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 9.00-second mark of the target video.
integrated_multimodal_description:
[Shot 1] Extreme wide shot of a crowd by a chasm as an old storyteller presses a jade token onto the edge and silence settles over spring daylight, cinematic film still (camera: static shot) <d>[Chinese] 剑仙把半块玉佩往渊口一按，天地才静下来。</d>
[Shot 2] At 00:05.000, the camera cuts to <Picture 2>: close-up of Close shot of an old storyteller with a worn tea bowl as he vows that someone still lives and keeps watch at the chasm mouth, cinematic film still (camera: push in) <d>[Chinese] 也有人赌咒，说他还活着，守在渊口。</d>
[Shot 3] At 00:09.000, the camera cuts to <Picture 3>: Wide shot outside the crowd as a gray-clad young man carrying firewood pauses mid-step in the bright spring sunshine, cinematic film still (camera: tracking shot)
overall_soundscape: Spring wind through leaves, muffled crowd murmur, the dull clink of the jade token meeting stone, the creak of a tea bowl setting down, and the soft rustle of a firewood bundle shifting as footsteps stop.
non_diegetic_music: A sparse, low dizi melody that hushes at the jade touch, then thins to a lone, distant note as the gray-clad youth pauses.