# E20-01 · 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 5.00 秒）
- Picture 3 = f3.png（钉 9.90 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 5.00-second mark of the target video; Picture 3 (from Shot 3) aligns with the 9.90-second mark of the target video.
integrated_multimodal_description:
[Shot 1] wide shot of A wide static view of the broken crenellations and scorched black banner; a lone arrow quivers in the arrow-studded wooden pillar beside the jagged gap, dust shafts slanting in bright daylight, cinematic film still (camera: static shot)
[Shot 2] At 00:05.000, the camera cuts to <Picture 2>: medium shot of A medium push-in framing a haggard grey-haired youth in a dusty tunic, a fresh tear in his shoulder cloth, striding forward past the heap of broken spears and round stones as the ladder thuds against the embrasure, cinematic film still (camera: push in) <d>[Chinese] 沈砚？你来这里做什么！</d>
[Shot 3] At 00:09.900, the camera cuts to <Picture 3>: wide shot of A wide tracking shot along the cracked stone deck toward the dog-tooth gap, an old swordsman in a bloodied dark robe kicking the ladder away then cleaving the second one; the scorched banner ripples overhead, cinematic film still
overall_soundscape: Clattering arrow, thudding ladders, snapping wood, and scuffling boots on cracked stone.
non_diegetic_music: N/A