ai21.net
语言

节拍同步的实拍混剪展示片

演示视频

节拍同步的实拍混剪展示片 — 1节拍同步的实拍混剪展示片 — 2节拍同步的实拍混剪展示片 — 3

提示词

<inputs>
Ask me for: the product name and a one-line promise, 3 to 5 UI moments to show, one accent color, 10 to 20 real vertical clips I own, and a royalty-free song with a clear drop (e.g. Mixkit, free for commercial use).
</inputs>

<direction>
High-end minimal. One idea per shot, lots of empty space, one accent color, one clean sans (Geist or Inter) with tight tracking. Masked type reveals, match cuts, one smooth camera language. Real footage only, never placeholder cards. No full stops in on-screen text.
Banned: shockwave rings, particle bursts, RGB split, camera shake, lens flares, neon glows, grid floors, flashing backgrounds, bouncy easing.
</direction>

<structure>
10 bars at 120 BPM, 2 seconds each.
Bar 1: the hook lands word by word on the beats.
Bar 2: one hook word morphs into the product UI. A cursor types and clicks.
The drop: a circle opens out of the button into a dark scene.
Then one move per bar: a wall of real clips with a scan line and 3 winners, the key output as big type, a 3D carousel of real videos with floor reflections and a motion-blurred whip onto one hero clip, the hero in a phone next to a panel that flips into results, big stats on push cuts, a 3-word ticker, a logo reveal, a fade to black.
</structure>

<build>
1. One HTML file at 1920x1080. Every style is computed from time inside 
http://
window.seek(t): no CSS animations, no timers, no state between frames.
2. Real video: extract clips to 30fps JPEG sequences with ffmpeg and swap img sources per frame. seek awaits the image decodes.
3. Analyze the song with numpy: tempo, beat grid, energy per bar, the drop. Calibrate the grid to the real kick hits. Every cut sits on a downbeat, every UI hit on a beat.
4. Render with Playwright: 3 subframes per frame at t minus, at, and plus 1/240s, then blend with ffmpeg tmix for real motion blur at 60fps.
5. Place each sound effect so its measured peak, not its file start, lands on the event. Keep the effects quiet under the music. Loudnorm to -14 LUFS.
6. Probe 20 or more frames before the full render. Fix anything cluttered, overlapping or hard to read.
</build>

<gotchas>
Never set opacity or filter on a preserve-3d element, because it flattens and both faces show. Fade its wrapper instead. Measure element positions at runtime for match cuts. Only use music and sound effects whose license allows commercial use.
</gotchas>

<start>
Ask me for the inputs, then show me a storyboard with every timing on the beat grid before you write any code.
</start>

中文译文

<inputs>
向我询问:产品名称和一句话承诺、要展示的 3 到 5 个 UI 时刻、一种强调色、10 到 20 段我自己的真实竖屏素材,以及一首有明显 drop 的免版税歌曲(例如 Mixkit,商用免费)。
</inputs>

<direction>
高端极简。每个镜头只讲一个想法,大量留白,一种强调色,一款干净的无衬线字体(Geist 或 Inter),字距收紧。遮罩式文字显现、匹配剪辑、统一流畅的镜头语言。只用真实素材,绝不用占位卡片。画面文字不加句号。
禁用:冲击波光环、粒子爆发、RGB 分离、镜头抖动、镜头光晕、霓虹辉光、网格地板、闪烁背景、弹跳缓动。
</direction>

<structure>
120 BPM 下 10 个小节,每小节 2 秒。
第 1 小节:钩子逐词落在节拍上。
第 2 小节:一个钩子词变形为产品 UI。光标输入并点击。
drop:一个圆从按钮中向外展开,进入暗色场景。
之后每小节一个动作:一面真实片段之墙,带一条扫描线和 3 个胜出片段;关键输出以大号字体呈现;真实视频的 3D 旋转木马,带地面反射,并以运动模糊的甩镜落到一个主视觉片段上;主视觉出现在手机里,旁边是一块翻转为结果的面板;大号统计数据配合推镜切换;一个 3 词跑马灯;一次 logo 揭示;以及淡出至黑。
</structure>

<build>
1. 一个 1920x1080 的 HTML 文件。所有样式都在 
http://
window.seek(t) 内部根据时间计算:没有 CSS 动画,没有计时器,帧与帧之间不保留状态。
2. 真实视频:用 ffmpeg 把片段提取为 30fps 的 JPEG 序列,逐帧切换 img 的 src。seek 会等待图像解码完成。
3. 用 numpy 分析歌曲:速度、节拍网格、每小节能量、drop。把网格校准到真实的底鼓击打上。每次剪切都落在强拍上,每个 UI 动效都落在拍子上。
4. 用 Playwright 渲染:每帧取 t 减、t、t 加 1/240 秒处的 3 个子帧,再用 ffmpeg tmix 混合,得到 60fps 的真实运动模糊。
5. 放置每个音效时,让它实测的峰值(而不是文件开头)落在事件上。让音效在音乐之下保持安静。用 Loudnorm 标准化到 -14 LUFS。
6. 完整渲染前先探查 20 帧或更多帧。修复任何杂乱、重叠或难以阅读的地方。
</build>

<gotchas>
绝不要在 preserve-3d 元素上设置 opacity 或 filter,因为这会将其压平,导致两面都显示。改为淡化它的外层容器。为匹配剪辑在运行时测量元素位置。只使用许可证允许商用的音乐和音效。
</gotchas>

<start>
先向我询问这些输入,然后在写任何代码之前,给我看一份每个时间点都落在节拍网格上的分镜。
</start>

溯源

原作者
twoclipping
发布日期
2026-09-23(由推文 ID 反解)
原始出处
查看原帖 ↗
收录来源
yihui-dev/awesome-opus5-5-videos · twoclipping-000267 · MIT
yihui-dev/awesome-opus5-5-videos · raphaelaubryy-687877 · MIT
zhuyansen/awesome-opus-5.5-video · 2102554209166000267 · 未声明许可
本条由 3 个来源合并去重得来