# E02-03 · 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 9.50 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 9.50-second mark of the target video.
integrated_multimodal_description:
[Shot 1] Extreme wide shot of the misty corner, black gate lanterns glowing; the scarred youth staggers upright against the wall, a neighbor lifting the small bundle from his arms, cinematic film still (camera: static shot)
[Shot 2] At 00:05.000, the camera cuts to <Picture 2>: Medium shot, push in near the black gate; the old carpenter bursts out, gripping the scarred youth's arm, lantern light on weathered hands while the street stays silent, cinematic film still <d>[Chinese] 阿砚！这手怎么了！</d>
[Shot 3] At 00:09.500, the camera cuts to <Picture 3>: close-up of Close shot, push in; blood drips from the youth's wrist to the worn cobbles as he glances toward the old locust tree, the black mist gone, words swallowed, cinematic film still
overall_soundscape: Staggering footsteps scrape the cobbles, the mourning hall lantern creaks overhead, and a single drop of blood lands on the worn stone.
non_diegetic_music: A sparse low guqin and dizi line, muted and uneasy under the pale moonlight and drifting mist.