# E14-02 · 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）

---

For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.
integrated_multimodal_description:
[Shot 1] Extreme close-up on the boy's weathered face and cracked lips beside the dark wet cobbles, heavy shadows swallowing the empty black-market street, cinematic film still (camera: static shot) <d>[Chinese] 哭声……在地下。</d>
overall_soundscape: Muffled sobbing echoes from below as rough cloth rustles and worn straw sandals scrape each wooden ladder rung.
non_diegetic_music: Low, tense ambient drones with sparse plucked strings under a hollow reverb.