# E09-04 · 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 5.70 秒）
- Picture 3 = f3.png（钉 9.30 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 5.70-second mark of the target video; Picture 3 (from Shot 3) aligns with the 9.30-second mark of the target video.
integrated_multimodal_description:
[Shot 1] wide shot of Wide static shot of fog-drowned reed beds: sword energy erupts from a grey-clad youth by wet stones, hurling an emaciated elder and two cultivators into the grass, cinematic film still <d>[Chinese] 阿砚！</d>
[Shot 2] At 00:05.700, the camera cuts to <Picture 2>: close-up of Push-in close shot: sword energy gone, a grey-clad youth kneels gasping on his sword before the dark cave mouth, the mossy ancient stele beyond, as a pale-robed woman cries out, cinematic film still (camera: push in) <d>[Chinese] 又白了……</d>
[Shot 3] At 00:09.300, the camera cuts to <Picture 3>: extreme close-up of Extreme-close tilt-up: a pale-robed woman's hand steadies a grey-clad youth's shoulder and presses his temple, revealing more white hair among black strands, damp cave wall with dripping stalactites behind, cinematic film still (camera: tilt up) <d>[Chinese] 白发换三个修士，值了。</d>
overall_soundscape: A muffled thunderclap of sword energy rips through wet fog, followed by heavy thuds as bodies hit the grass, ragged breathing, and a woman's urgent cry.
non_diegetic_music: Low droning strings swell into a sharp percussive hit, then fall to a fragile woodwind phrase.