# E37-07 · 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 5.60 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 5.60-second mark of the target video.
integrated_multimodal_description:
[Shot 1] extreme wide shot of Extreme-wide static shot over the empty market street: warm spring sun on grey-tiled roofs, dappled locust shade on worn cobbles, the mourning hall with peeling black doors and faded white lanterns, dust motes drifting in light shafts, cinematic film still <d>[Chinese] 化封那一下，把我弹出渊口了。</d>
[Shot 2] At 00:05.600, the camera cuts to <Picture 2>: close-up of Close push-in on the coarse-palmed hand with bloodied tiger mouth, a greying sideburn catching daylight, the shallow breath answered by a slow head lift, twin plum blossoms blurring beyond the worn cobbles, cinematic film still (camera: push in) <d>[Chinese] 那你这三年，在哪儿过的？</d> <d>[Chinese] 荒山。养了两年，才养回一口气。</d>
overall_soundscape: Sparrows scatter and a dry wind rustles locust leaves over the empty street, then a soft scrape of cloth as she lifts her head.
non_diegetic_music: Low, yearning guqin line with sparse bamboo flute, rising faintly as the head lift lands.