# E18-05 · 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 4.30 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 4.30-second mark of the target video.
integrated_multimodal_description:
[Shot 1] extreme wide shot of Extreme- under pale blue moonlight over charred house frames and collapsed gable walls, the blackened burning village with a tilted mud idol, three disciples lunge as a red-clad figure spins her sword to force them back, cinematic film still (camera: static shot) <d>[Chinese] 凡骨也敢挡剑宗？</d>
[Shot 2] At 00:04.300, the camera cuts to <Picture 2>: close-up of Close shot pushing in on the sallow middle-aged elder, high brow and protruding cheekbones, cold sneer on his short-bearded face as he scoffs at a mortal guts daring to block the sword sect, cinematic film still (camera: push in) <d>[Chinese] 都住手！</d>
overall_soundscape: Clashing swords, footsteps scraping ash, a thud against the half-burned door plank, and the whistle of a descending flying sword.
non_diegetic_music: Cold, desolate guqin theme with faint ember glow and sudden tense stabs as the white-robed figure lands.