Promptcelerator
简体中文

固定机位双人中近景中的咖啡馆对话

精准的调度与明确命名的角色,让口语场景中的两张脸始终保持一致。

提示词与视频作者タナベ | AI動画 × マーケティング@tanabe_fragm查看原帖 ↗

提示词

A fixed, locked-off medium two-shot in a bright café at midday, horizontal 16:9 cinematic framing. Two young Japanese women in their early twenties sit facing each other across a small wooden table. The camera is at table height beside the table, so both women are seen in three-quarter view from the waist up — Misaki on the left of frame, Yui on the right — with their faces large and clearly lit. A large window runs along the background; soft natural daylight falls on their faces from the side, not from behind. Two iced lattes sit on the table between them. Photorealistic, natural skin texture, gentle background blur.

Misaki (left): 22, cheerful and talkative, black chin-length bob, white knit sweater, expressive hand gestures.
Yui (right): 23, gentle and easygoing, long brown hair, beige cardigan, laughs easily.

The camera does not move or cut. Exactly four lines of dialogue, in natural Tokyo-standard Japanese, in this order. While one speaks, the other listens with her mouth closed, reacting only with nods and smiles.

0–4s: Misaki leans forward toward Yui, eyes bright, excited:「ねえ聞いて! 昨日ね、駅前のパン屋さん、やっと行けたの」
4–7s: Yui's eyes widen, surprised, quick:「え、まって、あの毎朝並んでるとこ?」
7–11s: Misaki nods hard, hands miming something crispy, delighted:「そうそう! メロンパン、ぱりっぱりで…もう最高だった」
11–15s: Yui bursts out laughing and speaks through the laugh, playfully envious:「ずるい! 今度ぜったい一緒に行こうね」

Precise lip sync: lips fully close on ま, ぱ, め, ば sounds; mouth shapes follow each vowel. No extra lines, no ad-libs, no narration. Audio is only the two voices and soft café ambience — no background music. No subtitles, no on-screen text. Single continuous horizontal shot, same framing from start to end.
模型
Kling 4
分类
对白与访谈式人物
画幅
16:9 · 1920×1080
时长
0:15
声音
原生音频
发布时间
2026年10月16日

这个镜头用到的技巧