# E20-07 · 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 9.30 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 5.00-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] extreme wide shot of Extreme-wide establishing shot over the battle-worn wall top: the lone young defender lifts the sword and steps into the jagged crenellation gap, dust shafts and smoke swirling, cinematic film still (camera: static shot)
[Shot 2] At 00:05.000, the camera cuts to <Picture 2>: medium shot of Medium tracking shot following the defender as he shoves the siege ladder off the parapet, then seizes a round stone and smashes the next ladder as it rises, cinematic film still <d>[Chinese] 来一个，砸一个。</d>
[Shot 3] At 00:09.300, the camera cuts to <Picture 3>: Wide shot looking along the arrow-studded wooden pillar and scorched black banner: the stone pile is gone, he grips a broken spear, alone on the wall with wind tearing the flag, cinematic film still (camera: tilt up)
overall_soundscape: Harsh wind, crackling banner cloth, wood striking stone, and the heavy thud of a falling siege ladder.
non_diegetic_music: Low, grim strings with sparse war drums building a lonely resolve beneath the battle din.