# E10-03 · 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 2.50 秒）
- Picture 3 = f3.png（钉 6.10 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 2.50-second mark of the target video; Picture 3 (from Shot 3) aligns with the 6.10-second mark of the target video.
integrated_multimodal_description:
[Shot 1] Close-up of a young man's face, thin and scarred, with greying temples; a stiff, forced smile freezes into blank shock, pale misty marsh light diffusing around him, cinematic film still (camera: static shot)
[Shot 2] At 00:02.500, the camera cuts to <Picture 2>: Medium shot, a woman in vivid red stands against the dim cave mouth, misty pale daylight behind her; she speaks coldly while a jade-key stone is half-lit between them, cinematic film still (camera: push in) <d>[Chinese] 魔渊的钥匙，落在你一个凡人手里？</d>
[Shot 3] At 00:06.100, the camera cuts to <Picture 3>: Close-up of coarse calloused hands cradling a round-jade stone near the mossy stele base; a soft weary voice admits he never knew its meaning, grey-green haze filling the dark cave, cinematic film still (camera: static shot) <d>[Chinese] 我不知道它是什么。我娘留下的。</d>
overall_soundscape: Soft cave drips, reed rustle in damp wind, and the faint scrape of a stone being shifted by hand.
non_diegetic_music: Low, hesitant guzheng phrase with sparse strings, unresolved and fragile.