# 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 10.00 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 10.00-second mark of the target video.

integrated_multimodal_description:
[Shot 1] Cinematic, live-action, muted earth-tone palette. A static shot in medium framing holds: the old man eats silently, pushes a small dish of pickles toward the youth, the oil lamp flame swaying in a draft.
[Shot 2] At 00:05.000, the camera cuts to a close-up with a slow push in: the youth's gaze rises to the wall where a faded embroidered cloth hangs, a plum blossom stitched at the corner, the push in drawing attention to the embroidery.
[Shot 3] At 00:10.000, the camera cuts to a static shot in medium framing in flashback: a mute young woman in period clothing sits by lamplight, an embroidery needle between her fingers, her lips sealed, her expression gentle.

overall_soundscape: A small dish clinks across the table, the oil lamp wick hisses, and the silence of memory pressing in.

non_diegetic_music: A single sparse piano note at a slow tempo, fading before the flashback begins.
