# E40-05 · 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 5.80 秒）
- Picture 3 = f3.png（钉 9.40 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 5.80-second mark of the target video; Picture 3 (from Shot 3) aligns with the 9.40-second mark of the target video.
integrated_multimodal_description:
[Shot 1] close-up of Close framing over the felt-covered long table, the wheelchair pushed forward, one rough scarred hand slamming flat on the ink-stained tabletop beside a settling half-dried wine bowl, cinematic film still (camera: push in) <d>[Chinese] 我输了。输给『想守』这两个字。</d>
[Shot 2] At 00:05.800, the camera cuts to <Picture 2>: medium shot of Medium two-shot across the long felt table, willow fronds sweeping the window edge in the golden light, one lifts the remaining half bowl and drains it in one long swallow, cinematic film still (camera: static shot) <d>[Chinese] 我没赢你。</d>
[Shot 3] At 00:09.400, the camera cuts to <Picture 3>: wide shot of Wide symmetric framing down the felt-covered table, two seated figures facing each other, sunlit dust motes drifting through the window light shaft, neither looking away in the silent shop, cinematic film still (camera: static shot)
overall_soundscape: Soft fabric rustle, a dull hand slap on the wooden table, then the low gulp and swallow of wine draining from a coarse clay bowl.
non_diegetic_music: Quiet guqin plucks with a faintly somber, suspended air that holds through the silent locked gazes.