# E16-04 · 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 5.80 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.
integrated_multimodal_description:
[Shot 1] Wide shot, rainy night: the young man staggers, the red-clad woman steadies him, the blind old man's fingertips resting on the cracked teapot, rain streaking the dark windowpanes, cinematic film still (camera: push in) <d>[Chinese] 公主的儿子，怎么会在义庄长大？</d>
[Shot 2] At 00:05.800, the camera cuts to <Picture 2>: Medium shot under the weathered ink-slab plaque, the red-clad figure's cold bright eyes meeting the blind old man's clouded gaze, steam curling from the clay teapot, cinematic film still (camera: static shot) <d>[Chinese] 有人怕她回去，怕她手里的玉。</d>
overall_soundscape: Rain patters on the carved lattice, a body sways, a hand steadies it, and a chipped celadon cup scrapes faintly as it turns.
non_diegetic_music: Low, sparse guqin notes with a tense, unresolved drone under the rainy night.