# E44-05 · 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 5.80 秒）
- Picture 3 = f3.png（钉 10.50 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 5.80-second mark of the target video; Picture 3 (from Shot 3) aligns with the 10.50-second mark of the target video.
integrated_multimodal_description:
[Shot 1] Medium shot of the speaker beside the peeling black gate, with faded white lanterns and worn threshold in frame, dust motes drifting in warm light, cinematic film still (camera: static shot) <d>[Chinese] 我守。守到有人来接。</d> <d>[Chinese] 师娘，等我回来，还吃您蒸的包子。</d>
[Shot 2] At 00:05.800, the camera cuts to <Picture 2>: Wide shot of the courtyard with twin plum trees and stacked firewood, as one kneels low and the other watches quietly, cinematic film still (camera: static shot) <d>[Chinese] 好。我在家等你回来。</d>
[Shot 3] At 00:10.500, the camera cuts to <Picture 3>: extreme wide shot of Extreme- of the empty street and mourning hall, the lone figure standing still, wind catching her skirt, dappled locust shade on worn cobbles, cinematic film still (camera: static shot)
overall_soundscape: Footsteps fade into wind through locust leaves, with the soft creak of old lanterns.
non_diegetic_music: Sparse guzheng and low dizi, solemn and tender.