taste
替 angelcore 風格的音樂影片定美學方向、調色和對拍剪輯流程
中文翻譯
---
name: taste
description: 給音樂影片和短影音剪輯用的創意方向層，專攻 angelcore / cloud-trance / hyperpop 這一系：有一套命名風格的美學詞彙、情緒＋色彩＋光線系統、對拍剪輯語法，還有一條把 ECC 各個影片 skill 串起來的流程，從 b-roll 生成一路到發布。當影片要看起來是有意為之、而不只是堪用時就用：音樂影片、fancam、以情緒板為底的 reels，或是想幫 AI 生成的 b-roll 找一個一致的視覺方向。
origin: ECC
---
# Taste
大部分 AI 影片的建議只講到*怎麼 render 畫面*。這個 skill 是它上面那一層：
**畫面該長什麼樣、用什麼順序、切在什麼節奏上，成品才會是一個有意圖的整體，而不是一堆生成結果的堆疊。**
它收錄的是一種特定的品味：**angelcore / cloud-trance / hyperpop** 這一系
（Bladee「Silver Surfer」時期的空靈 trance，混上厚重的 angelcore），
是從一批收藏的 Reels，加上逛過約 70 個條目的視覺風格庫提煉出來的。
它刻意有立場。品味是一種觀點，不是菜單。
> 配套檔案 `references/genre-taxonomy.md` 放了完整的命名風格目錄。
> 這個檔案是可以直接動手的那一層：情緒、語法、流程，還有一份對拍的鏡頭計畫。
## 何時啟用
- 製作**音樂影片**、歌詞影片、fancam 或 visualizer。
- 做短影音的**剪輯 / reel**，而且重點是*感覺*，不是資訊。
- 驅動 **AI b-roll 生成**（fal.ai、Veo、Kling 等），prompt 需要一個一致的方向，而不是各自為政的氛圍。
- 在任何 render 之前，組一份**情緒板**或挑視覺風格。
- 使用者說「taste」、「讓它感覺像 X」、「給它一個方向」、「angelcore」、
「cloud trance」、「hyperpop edit」、「Bladee」、「dreamcore」，或是點名某個收藏的參考。
- 目前的剪輯堪用，但看起來平、很通用、像 AI 垃圾，或是風格前後不一致。
這個 skill 站在 `video-editing`（機制面）和 `remotion-video-creation`（渲染器）**之上**。
*怎麼做*用那兩個，*做什麼、為什麼*用這個。
## 核心主張
1. **Taste 是最後一層，但必須最先決定。** `video-editing` 說得沒錯，
品味是最後的人工把關。陷阱在於：如果到最後才決定品味，前面每一次生成、每一刀都是在猜。
在第一個 prompt 之前就選好方向，再讓它去約束所有東西。
2. **一致性勝過新鮮感。** 一個外觀貫穿 30 個鏡頭，贏過 30 種外觀。
一個命名風格（見下）就是一種約束，白送你一致性。
3. **對著歌剪，不要對著素材剪。** 音樂影片的時間軸就是波形。
每一個硬切都要落在拍點或 transient 上。畫格的計算在流程那一節。
4. **選擇性地生成，狠狠地剪。** AI 能做出不存在的 b-roll，
但做不出品味。你還是得丟掉 80%。
## 美學詞彙（提煉版）
參考素材庫涵蓋大量*有命名*的視覺風格，完整清單在
`references/genre-taxonomy.md`。有用的做法不是背 70 個名字，而是看出
**一個風格名稱就是一整套 prompt 加調色的預設。** 你選了一個，
它的色盤、質感、打光和主題就整組繼承過來。
風格會聚成幾個家族。挑一個**主**家族，最多再加**一個**點綴：
| 家族 | 屬於這個家族的風格 | 給人的感覺 |
|--------|-------------|----------|
| **Ethereal / divine** | spiritualism、glacial folk、beacons、zen core、fairy tale | 失重、神聖、發光、柔 |
| **Hyperpop / Y2K-cyber** | cyberdelia、acid house、acid nora、neo aggressano、new liquid | 亮面、鉻金屬、霓虹、kawaii-cyber |
| **Dark / occult** | dark academia、smoke nostalgia、communist core、abstract tech | 高反差、不祥、顆粒感 |
| **Retro / print** | retro surfers、art deco、adventure pulp、classic advertising、magazine collage、bumper stickers | 平面、圖像化、半色調、懷舊 |
| **Organic / textural** | microbiology core、weaving patterns、fruitage retro、cozy blanket、pacific punk wave | 觸感、微距、編織、濕潤 |
| **Systemic / data** | numbers、mazes、code web、heatmap、pixel、8-bit | 網格、生成式、示意圖 |
**以目前這個專案來說**，主家族是 **Ethereal / divine**，點綴是 **Hyperpop / Y2K-cyber**，
也就是神聖的光和結晶般的綻放，間或點上鉻金屬和霓虹。這個組合
*就是* angelcore × cloud-trance 的 brief。
## 情緒系統：angelcore × cloud-trance
直接從最強的幾支參考 reels 提煉出來。這是具體的調色方案。
### 色盤
- **基底：** 近乎全黑的虛空（#05060a）和骨白（#f4f1ea）。大多數畫面不是這個就是那個。
- **神聖點綴：** 熔金 / 餘燼橘（#ffb24d → #ff7a18），是黑暗裡*唯一的暖光*。
- **結晶點綴：** 虹彩的紫→青→洋紅 bokeh（#8a6bff、#4fc3ff、#ff6ad5），
是 hyperpop 的綻放，用在明亮的畫面。
- **危險點綴（要節制）：** 單色畫面上一點發光的紅（#ff2a2a），
只留給一兩個震撼切點。
- **Hyperpop 主體：** 糖果粉頭髮 / 鉻金屬 / 亮白，襯著藍天。
規則：**每個鏡頭只有一個點綴色。** 金色待在暗的畫面，虹彩待在亮的畫面，
同一個鏡頭絕對不要兩個都出現。
### 光線與質感
- 黑暗被單一暖光源刺穿（餘燼綻放、神聖光束）。高反差、深黑。
- 結晶 / 亮片 bokeh、鏡頭光暈、bloom、漏光，要*天堂感*，不要髒。
- 暗的畫面加底片顆粒和輕微色差，亮的畫面保持乾淨的亮面。
- 在留白處放微距細節：一個主角物件置中在黑底上（鑰匙、眼睛、齒輪、花瓣、水）。
- 主題：有翼的人影、雲、光環、天使、結晶結構、糖果賽博肖像。
### 運動
- 緩慢、漂浮、失重的鏡頭（漂移、慢推、慢繞），這才是 *cloud* trance。
- 只有在 drop 才爆發速度。其他時候一切都在呼吸。
- 粒子往上飄（餘燼、灰塵、亮片），往上的運動等於升天。
## 剪輯語法（提煉版）
從參考剪輯裡歸納出反覆出現、定義這個風格的手法：
1. **鎖拍的硬切。** verse / drop 不用溶接。切在 kick 上。眼睛要能
感覺到 BPM。
2. **黑底微距主角插入。** 單一銳利的物件置中在黑色留白裡，
撐 1 到 2 拍就切。把這些做成節奏蒙太奇，就是 cloud-trance 的招牌。
3. **Bloom / 爆炸揭示。** 白色或餘燼色的 bloom 在 transient 上把畫面炸白，
然後解析成下一個鏡頭。就是「神聖閃光」轉場。
4. **單色畫面中的彩色跳出。** 一段用黑白，然後某個單一彩色元素
（紅眼睛、金色火焰、粉紅頭髮）在強拍上衝出來。
5. **進 drop 的變速。** 在 drop 前最後一小節把素材從慢拉到快，
在第一拍硬切到正常速度。
6. **字幕關鍵字強調（只用在口說 / 歌詞段落）。** 全大寫，
一兩個字用點綴色標出，跟人聲同步。用在歌詞影片，不要用在純 visualizer。
7. **Reaction PiP（只用在解說 / 剪輯評論）。** 在 b-roll 上疊一個
畫中畫的說話人頭。不在音樂影片本身的範圍內，會寫進來是因為素材庫大量使用它。
**不准做的事：** 在有節奏的段落用 crossfade 轉場；一個鏡頭超過一個點綴色；
一個鏡頭撐過它的樂句；畫面上出現看得清楚的 UI 外框（要裁掉）；
同一條時間軸混用不同長寬比。
## 流程：混用 ECC 的影片 skill
這個 skill 是指揮。每個 ECC skill 是一件樂器。不要跳層。
```
0. TASTE (this skill) decide genre + mood + grammar BEFORE anything renders
1. STRUCTURE (video-editing) map the song: timestamps for intro/verse/drop/bridge/outro
2. GENERATE (fal-ai-media) make b-roll per genre prompt-presets; throw away 80%
3. CUT (video-editing/FFmpeg) beat-cut + reframe to 9:16; assemble selects on the grid
4. COMPOSE (remotion-video-creation) overlays, blooms, lyric text, beat-synced sequencing
5. MOTION (motion-* skills) easing curves, light-leak/particle motion, transition timing
6. AUDIO (fal-ai-media) transition risers/impacts to sell the cuts (track itself is in Ableton)
7. POLISH grade to the palette above, final pacing pass, export
8. DISTRIBUTE (content-engine) platform-native versions + caption/cover
```
| 步驟 | 要載入的 ECC skill | 在這裡做什麼 |
|------|-------------------|-------------------|
| 結構與剪輯 | `video-editing` | FFmpeg 剪 / 串接 / 重新構圖、EDL、場景 / 靜音偵測 |
| 生成 b-roll | `fal-ai-media` | 依風格預設使用圖像 / 影片模型 |
| 合成與疊加 | `remotion-video-creation` | 對拍的 `<Sequence>`、文字、bloom、遮罩 |
| 動態時序 | `motion-foundations`、`motion-patterns`、`motion-advanced` | easing、彈簧、光 / 粒子運動 |
| 伺服器端影片 | `videodb` | 智慧重新構圖，素材很大時做索引 |
| 發布 | `content-engine` | 各平台的版本、封面、字幕 |
| 配音 / 歌詞旁白 | `video-editing`（ElevenLabs 那節） | 只有需要口說層時才用 |
## 拍點計算（把剪點鎖在歌上）
目前這首是 **138 BPM、B minor**。常數：
- `seconds_per_beat = 60 / 138 = 0.43478s`
- `frames_per_beat = fps × 0.43478` → **24fps: 10.43**、**30fps: 13.04**、**60fps: 26.09**
- `1 bar (4 beats) = 1.7391s` → 30fps：**52.17 frames**
- `8-bar phrase = 13.913s` → 這首歌的 loop 長度
在 Remotion 裡，把每個 `from={}` 都吸附到拍點：
```ts
const FPS = 30;
const BPM = 138;
const beat = (n: number) => Math.round(n * (60 / BPM) * FPS); // beat(n) → frame
// cut on beats 0,4,8,... : <Sequence from={beat(0)} durationInFrames={beat(4)}> ...
```
## 對拍的鏡頭計畫（這支音樂影片）
歌曲編排（出自專案自己的筆記）是
**Intro → Verse → Drop → Bridge → Drop → Outro（約 2:05）**。把品味對應到每個段落：
| 段落 | 風格 / 情緒傾向 | 語法 | 鏡頭點子 |
|---------|-----------------|---------|------------|
| **Intro** | Ethereal/divine，近乎全黑 | 慢推、不切 | 虛空裡的餘燼綻放；一道金色光束；灰塵上升 |
| **Verse** | Dark + 黑底微距主角 | 每 2 拍硬切 | 鑰匙、眼睛、齒輪、水滴、花瓣，節奏式微距蒙太奇 |
| **Drop** | Hyperpop 綻放 + 結晶 | 變速進入、在第一拍切、快 | 糖果粉人影、鉻金屬、虹彩 bokeh、有翼升天 |
| **Bridge** | Spiritualism，失重 | 一個長的定格鏡頭、彩色跳出 | 雲 + 光環；單一紅色點綴衝出一次 |
| **Drop 2** | 同 Drop，加強 | 在 transient 上加神聖閃光 bloom | 翅膀張開、亮片爆開、漏光拉到最滿 |
| **Outro** | Glacial folk，冷靜 | 慢慢淡出到黑 | 結晶結構消融；餘燼熄滅 |
## fal.ai Prompt 預設（依情緒）
搭配 `fal-ai-media` 使用。每個預設都是把風格套到專案色盤上。所有 prompt 都附加
`9:16, vertical, cinematic, film grain, volumetric light, no text, no watermark`。
- **Divine void：** "a single molten-gold ember bloom rising in an infinite near-black void,
deep shadow, one warm light source, weightless dust particles, holy, high contrast"
- **Macro hero：** "extreme macro of an antique brass key / a human eye / interlocking gears,
centered on pure black negative space, razor-sharp detail, single rim light"
- **Crystalline bloom：** "iridescent violet-cyan-magenta crystalline bokeh, glittering light
refraction, dreamy lens flares, heavenly glow, soft focus, hyperpop angelcore"
- **Candy-cyber portrait：** "candy-pink-haired figure, glossy chrome accents, bright blue sky,
Y2K hyperpop, clean gloss, saturated, kawaii-cyber"
- **Winged ascension：** "a winged figure ascending into clouds, halo of light, bone-white and
gold, volumetric god-rays, ethereal, religious iconography, soft"
- **Cold outro：** "pale crystalline ice structure slowly dissolving, glacial folk, cold blue
and bone white, minimal, calm, fading to black"
每個預設生成 6 到 10 張，留 2 到 3 張。要有動態的話，用 image-to-video 模型
讓靜態圖動起來，或直接生成短片段；鏡頭運動照 Motion 的規則保持緩慢。
## FFmpeg 配方（剪輯 + 重新構圖）
```bash
# Reframe any landscape/raw clip to 9:16 (center crop)
ffmpeg -i in.mp4 -vf "crop=ih*9/16:ih,scale=1080:1920" v.mp4
# Beat-cut a clip to exactly N beats at 138 BPM (e.g. 2 beats = 0.8696s)
ffmpeg -i in.mp4 -t 0.8696 -c copy beat2.mp4
# Concatenate beat-selects into the verse montage
for f in selects/*.mp4; do echo "file '$f'"; done > concat.txt
ffmpeg -f concat -safe 0 -i concat.txt -c copy verse.mp4
# Strip UI chrome / status bar from a screen-recorded reference (crop top+bottom)
ffmpeg -i reel.mp4 -vf "crop=iw:ih-300:0:150" clean.mp4
```
## Remotion 合成骨架（對拍）
```tsx
import { AbsoluteFill, Sequence, Video, Img, useCurrentFrame, interpolate } from "remotion";
const FPS = 30, BPM = 138;
const beat = (n: number) => Math.round(n * (60 / BPM) * FPS);
const Bloom: React.FC = () => {
const f = useCurrentFrame();
const o = interpolate(f, [0, 3, 12], [0, 1, 0], { extrapolateRight: "clamp" }); // divine flash on a transient
return <AbsoluteFill style={{ background: "radial-gradient(#fff,#ffb24d)", opacity: o, mixBlendMode: "screen" }} />;
};
export const AngelcoreMV: React.FC = () => (
<AbsoluteFill style={{ background: "#05060a" }}>
{/* Verse: macro hero-on-black, hard cut every 2 beats */}
<Sequence from={beat(0)} durationInFrames={beat(2)}><Video src="/selects/key.mp4" /></Sequence>
<Sequence from={beat(2)} durationInFrames={beat(2)}><Video src="/selects/eye.mp4" /></Sequence>
<Sequence from={beat(4)} durationInFrames={beat(2)}><Video src="/selects/gear.mp4" /></Sequence>
{/* Drop: crystalline bloom + flash on the one */}
<Sequence from={beat(8)} durationInFrames={beat(16)}><Video src="/selects/crystalline.mp4" /></Sequence>
<Sequence from={beat(8)} durationInFrames={beat(1)}><Bloom /></Sequence>
</AbsoluteFill>
);
```
Render：`npx remotion render src/index.ts AngelcoreMV out.mp4`。專案設定、音軌綁定和 render 參數
請看 `remotion-video-creation`。
## 關鍵原則
1. **在第一次生成之前先決定風格。** 挑一個主家族加一個點綴。
2. **每個鏡頭只有一個點綴色。** 金色在暗處，虹彩在亮處，紅色只出現一次。
3. **每一個硬切都落在拍點上。** 用拍點計算，有節奏的段落不要轉場。
4. **黑底微距主角是招牌動作。** 把它練到熟，verse 就靠它撐。
5. **生成 10 張，留 2 張。** 一致性來自淘汰，不是來自 prompt 寫得更用力。
6. **裁掉外框。** 最終畫面不准有狀態列、字幕或 UI。
7. **品味先決定，最後才評斷。** 先定方向，然後在每一刀上捍衛它。
## 相關 Skills
- `video-editing`：這個 skill 所站在上面的機制流程（FFmpeg、重新構圖、EDL、收尾）
- `remotion-video-creation`：可程式化的對拍合成與渲染
- `fal-ai-media`：生成 b-roll、轉場音效和 riser
- `motion-foundations`、`motion-patterns`、`motion-advanced`：easing 和動態時序
- `videodb`：大量素材用的伺服器端智慧重新構圖和索引
- `content-engine`：各平台原生的發布、封面、字幕
- `frontend-design-direction`：同樣的「先決定方向」紀律，只是用在 UI英文原文
---
name: taste
description: Creative-direction layer for music videos and short-form edits in the angelcore / cloud-trance / hyperpop family — a named-genre aesthetic vocabulary, mood + color + light system, beat-synced editing grammar, and a pipeline chaining ECC's video skills from b-roll generation to distribution. Use when a video must feel intentional rather than merely functional — music videos, fancams, moodboard-driven reels, or giving AI-generated b-roll a coherent visual direction.
origin: ECC
---
# Taste
Most AI video advice stops at *how to render frames*. This skill is the layer above
that: **what the frames should look like, in what order, cut to what rhythm, so the
result reads as one intentional thing instead of a pile of generations.**
It encodes a specific taste — the **angelcore / cloud-trance / hyperpop** family
(Bladee "Silver Surfer"-era ethereal trance crossed with heavy angelcore) — distilled
from a corpus of saved Reels and a tour through a ~70-entry visual-genre library. It
is opinionated on purpose. Taste is a point of view, not a menu.
> The companion file `references/genre-taxonomy.md` holds the full named-genre catalog.
> This file is the actionable layer: mood, grammar, pipeline, and a beat-mapped shot plan.
## When to Activate
- Building a **music video**, lyric video, fancam, or visualizer.
- Making a short-form **edit / reel** where the *feel* matters more than the information.
- Driving **AI b-roll generation** (fal.ai, Veo, Kling, etc.) and the prompts need a
coherent direction instead of one-off vibes.
- Assembling a **moodboard** or choosing a visual genre before any rendering.
- The user says "taste", "make it feel like X", "give it a direction", "angelcore",
"cloud trance", "hyperpop edit", "Bladee", "dreamcore", or names a saved reference.
- The current edit works but reads as flat, generic, AI-slop, or stylistically incoherent.
This skill sits **on top of** `video-editing` (the mechanics) and `remotion-video-creation`
(the renderer). Use those for *how*. Use this for *what and why*.
## Core Thesis
1. **Taste is the last layer, and it must be decided first.** `video-editing` correctly
says taste is the final human pass. The trap: if you only decide taste at the end, every
generation and cut upstream was a guess. Pick the direction *before* the first prompt,
then let it constrain everything.
2. **Coherence beats novelty.** One look executed across 30 shots beats 30 looks. A named
genre (below) is a constraint that buys coherence for free.
3. **Cut to the song, not to the footage.** In a music video the timeline is the waveform.
Every hard cut lands on a beat or a transient. Frame math is in the pipeline section.
4. **Generate selectively, edit ruthlessly.** AI makes b-roll that does not exist; it does
not make taste. You still throw away 80%.
## The Aesthetic Vocabulary (distilled)
The reference corpus tours a large library of *named* visual genres. The full list lives in
`references/genre-taxonomy.md`. The useful move is not memorizing 70 names — it is seeing
that **a genre name is a complete prompt-and-grade preset.** When you pick one, you inherit
its palette, texture, lighting, and subject matter as a unit.
The genres cluster into families. Pick a **primary** family and at most **one accent**:
| Family | Genres in it | Reads as |
|--------|-------------|----------|
| **Ethereal / divine** | spiritualism, glacial folk, beacons, zen core, fairy tale | weightless, holy, glowing, soft |
| **Hyperpop / Y2K-cyber** | cyberdelia, acid house, acid nora, neo aggressano, new liquid | glossy, chrome, neon, kawaii-cyber |
| **Dark / occult** | dark academia, smoke nostalgia, communist core, abstract tech | high-contrast, ominous, grain |
| **Retro / print** | retro surfers, art deco, adventure pulp, classic advertising, magazine collage, bumper stickers | flat, graphic, halftone, nostalgic |
| **Organic / textural** | microbiology core, weaving patterns, fruitage retro, cozy blanket, pacific punk wave | tactile, macro, woven, wet |
| **Systemic / data** | numbers, mazes, code web, heatmap, pixel, 8-bit | gridded, generative, schematic |
**For the current project**, the primary is **Ethereal / divine** with a **Hyperpop / Y2K-cyber**
accent — i.e. holy light and crystalline bloom, punctuated by chrome and neon. That pairing
*is* the angelcore × cloud-trance brief.
## The Mood System — angelcore × cloud-trance
Distilled directly from the strongest reference reels. This is the concrete grade.
### Palette
- **Base:** near-black void (#05060a) and bone white (#f4f1ea). Most frames are one or the other.
- **Divine accent:** molten gold / ember orange (#ffb24d → #ff7a18) — the *one warm light* in the dark.
- **Crystalline accent:** iridescent violet→cyan→magenta bokeh (#8a6bff, #4fc3ff, #ff6ad5) — the
hyperpop bloom, used in bright frames.
- **Danger accent (sparingly):** a single glowing red (#ff2a2a) on monochrome — for one or two
shock cuts only.
- **Hyperpop subject:** candy pink hair / chrome / glossy white against blue sky.
Rule: **one accent per shot.** Gold lives in dark frames; iridescence lives in light frames;
never both in one shot.
### Light & texture
- Darkness pierced by a single warm source (ember bloom, divine shaft). High contrast, deep blacks.
- Crystalline / glitter bokeh, lens flares, bloom, light leaks — *heavenly*, not dirty.
- Film grain + subtle chromatic aberration on the dark frames; clean gloss on the bright frames.
- Macro detail on negative space: a hero object centered on black (key, eye, gear, petal, water).
- Subjects: winged figures, clouds, halos, angels, crystalline structures, candy-cyber portraits.
### Motion
- Slow, floating, weightless camera (drift, slow push, slow orbit) — *cloud* trance.
- Bursts of speed only at the drop. Otherwise everything breathes.
- Particles rising (embers, dust, glitter) — upward motion = ascension.
## The Editing Grammar (distilled)
From the reference edits, the techniques that recur and define the style:
1. **Beat-locked hard cuts.** No dissolves in the verse/drop. Cut on the kick. The eye should
feel the BPM.
2. **Hero-on-black macro inserts.** A single sharp object centered in black negative space,
held for 1–2 beats, then cut. Rhythmic montage of these = the cloud-trance signature.
3. **Bloom / explosion reveal.** A white or ember bloom that blows out the frame on a transient,
then resolves into the next shot. The "divine flash" transition.
4. **Color-pop on monochrome.** Run a passage in B&W, then a single colored element (red eye,
gold flame, pink hair) punches through on the downbeat.
5. **Speed-ramp into the drop.** Ramp footage from slow to fast across the last bar before the
drop, hard-cut to tempo on the one.
6. **Caption keyword highlight (for talking-head / lyric sections only).** All-caps, one or two
words highlighted in the accent color, synced to the vocal. Use for lyric video, not for the
pure visualizer.
7. **Reaction PiP (for explainer/edit-commentary only).** Picture-in-picture talking head over
b-roll. Out of scope for the music video itself; documented because the corpus uses it heavily.
**Do-nots:** crossfade transitions in tempo sections; more than one accent color per shot; a
shot held past its musical phrase; readable on-screen UI chrome (crop it out); mixed aspect
ratios in one timeline.
## The Pipeline — mixing the ECC video skills
This skill is the conductor. Each ECC skill is an instrument. Do not skip layers.
```
0. TASTE (this skill) decide genre + mood + grammar BEFORE anything renders
1. STRUCTURE (video-editing) map the song: timestamps for intro/verse/drop/bridge/outro
2. GENERATE (fal-ai-media) make b-roll per genre prompt-presets; throw away 80%
3. CUT (video-editing/FFmpeg) beat-cut + reframe to 9:16; assemble selects on the grid
4. COMPOSE (remotion-video-creation) overlays, blooms, lyric text, beat-synced sequencing
5. MOTION (motion-* skills) easing curves, light-leak/particle motion, transition timing
6. AUDIO (fal-ai-media) transition risers/impacts to sell the cuts (track itself is in Ableton)
7. POLISH grade to the palette above, final pacing pass, export
8. DISTRIBUTE (content-engine) platform-native versions + caption/cover
```
| Step | ECC skill to load | What it does here |
|------|-------------------|-------------------|
| Structure & cut | `video-editing` | FFmpeg cut/concat/reframe, EDL, scene/silence detection |
| Generate b-roll | `fal-ai-media` | image/video models per genre preset |
| Compose & overlay | `remotion-video-creation` | beat-synced `<Sequence>`s, text, blooms, masks |
| Motion timing | `motion-foundations`, `motion-patterns`, `motion-advanced` | easing, springs, light/particle motion |
| Server-side video | `videodb` | smart reframe, indexing if footage is large |
| Distribution | `content-engine` | per-platform cuts, covers, captions |
| Voice/lyric VO | `video-editing` (ElevenLabs section) | only if a spoken layer is needed |
## Beat Math (lock cuts to the song)
The current track is **138 BPM, B minor**. Constants:
- `seconds_per_beat = 60 / 138 = 0.43478s`
- `frames_per_beat = fps × 0.43478` → **24fps: 10.43**, **30fps: 13.04**, **60fps: 26.09**
- `1 bar (4 beats) = 1.7391s` → 30fps: **52.17 frames**
- `8-bar phrase = 13.913s` → the loop length from the track
In Remotion, snap every `from={}` to a beat:
```ts
const FPS = 30;
const BPM = 138;
const beat = (n: number) => Math.round(n * (60 / BPM) * FPS); // beat(n) → frame
// cut on beats 0,4,8,... : <Sequence from={beat(0)} durationInFrames={beat(4)}> ...
```
## Beat-Mapped Shot Plan (this music video)
The song arrangement (from the project's own notes) is
**Intro → Verse → Drop → Bridge → Drop → Outro (~2:05)**. Map taste to each section:
| Section | Genre/mood lean | Grammar | Shot ideas |
|---------|-----------------|---------|------------|
| **Intro** | Ethereal/divine, near-black | slow push, no cuts | ember bloom in the void; a single shaft of gold; dust rising |
| **Verse** | Dark + macro hero-on-black | hard cuts every 2 beats | key, eye, gear, water drop, petal — rhythmic macro montage |
| **Drop** | Hyperpop bloom + crystalline | speed-ramp in, cut on the one, fast | candy-pink figure, chrome, iridescent bokeh, winged ascension |
| **Bridge** | Spiritualism, weightless | one long held shot, color-pop | clouds + halo; single red accent punches once |
| **Drop 2** | as Drop, intensify | add divine-flash blooms on transients | wings open, glitter burst, light leaks maxed |
| **Outro** | Glacial folk, cold calm | slow fade to black | crystalline structure dissolving; ember dies out |
## fal.ai Prompt Presets (per mood)
Use with `fal-ai-media`. Each preset is the genre rendered to the project palette. Append
`9:16, vertical, cinematic, film grain, volumetric light, no text, no watermark` to all.
- **Divine void:** "a single molten-gold ember bloom rising in an infinite near-black void,
deep shadow, one warm light source, weightless dust particles, holy, high contrast"
- **Macro hero:** "extreme macro of an antique brass key / a human eye / interlocking gears,
centered on pure black negative space, razor-sharp detail, single rim light"
- **Crystalline bloom:** "iridescent violet-cyan-magenta crystalline bokeh, glittering light
refraction, dreamy lens flares, heavenly glow, soft focus, hyperpop angelcore"
- **Candy-cyber portrait:** "candy-pink-haired figure, glossy chrome accents, bright blue sky,
Y2K hyperpop, clean gloss, saturated, kawaii-cyber"
- **Winged ascension:** "a winged figure ascending into clouds, halo of light, bone-white and
gold, volumetric god-rays, ethereal, religious iconography, soft"
- **Cold outro:** "pale crystalline ice structure slowly dissolving, glacial folk, cold blue
and bone white, minimal, calm, fading to black"
Generate 6–10 per preset, keep 2–3. For motion, animate stills with an image-to-video model
or generate short clips directly; keep camera moves slow per the Motion rules.
## FFmpeg Recipes (cut + reframe)
```bash
# Reframe any landscape/raw clip to 9:16 (center crop)
ffmpeg -i in.mp4 -vf "crop=ih*9/16:ih,scale=1080:1920" v.mp4
# Beat-cut a clip to exactly N beats at 138 BPM (e.g. 2 beats = 0.8696s)
ffmpeg -i in.mp4 -t 0.8696 -c copy beat2.mp4
# Concatenate beat-selects into the verse montage
for f in selects/*.mp4; do echo "file '$f'"; done > concat.txt
ffmpeg -f concat -safe 0 -i concat.txt -c copy verse.mp4
# Strip UI chrome / status bar from a screen-recorded reference (crop top+bottom)
ffmpeg -i reel.mp4 -vf "crop=iw:ih-300:0:150" clean.mp4
```
## Remotion Composition Skeleton (beat-synced)
```tsx
import { AbsoluteFill, Sequence, Video, Img, useCurrentFrame, interpolate } from "remotion";
const FPS = 30, BPM = 138;
const beat = (n: number) => Math.round(n * (60 / BPM) * FPS);
const Bloom: React.FC = () => {
const f = useCurrentFrame();
const o = interpolate(f, [0, 3, 12], [0, 1, 0], { extrapolateRight: "clamp" }); // divine flash on a transient
return <AbsoluteFill style={{ background: "radial-gradient(#fff,#ffb24d)", opacity: o, mixBlendMode: "screen" }} />;
};
export const AngelcoreMV: React.FC = () => (
<AbsoluteFill style={{ background: "#05060a" }}>
{/* Verse: macro hero-on-black, hard cut every 2 beats */}
<Sequence from={beat(0)} durationInFrames={beat(2)}><Video src="/selects/key.mp4" /></Sequence>
<Sequence from={beat(2)} durationInFrames={beat(2)}><Video src="/selects/eye.mp4" /></Sequence>
<Sequence from={beat(4)} durationInFrames={beat(2)}><Video src="/selects/gear.mp4" /></Sequence>
{/* Drop: crystalline bloom + flash on the one */}
<Sequence from={beat(8)} durationInFrames={beat(16)}><Video src="/selects/crystalline.mp4" /></Sequence>
<Sequence from={beat(8)} durationInFrames={beat(1)}><Bloom /></Sequence>
</AbsoluteFill>
);
```
Render: `npx remotion render src/index.ts AngelcoreMV out.mp4`. See `remotion-video-creation`
for project setup, audio track binding, and render flags.
## Key Principles
1. **Decide the genre before the first generation.** Pick one primary family + one accent.
2. **One accent color per shot.** Gold in the dark, iridescence in the light, red once.
3. **Every hard cut lands on a beat.** Use the beat math; no transitions in tempo sections.
4. **Hero-on-black macro is the signature move.** Master it; it carries the verses.
5. **Generate 10, keep 2.** Coherence comes from rejection, not from prompting harder.
6. **Crop the chrome.** No status bars, captions, or UI in the final frame.
7. **Taste is decided first and judged last.** Set the direction, then defend it on every cut.
## Related Skills
- `video-editing` — the mechanical pipeline (FFmpeg, reframe, EDL, polish) this sits on top of
- `remotion-video-creation` — programmable beat-synced composition and rendering
- `fal-ai-media` — generate the b-roll, transition SFX, and risers
- `motion-foundations`, `motion-patterns`, `motion-advanced` — easing and motion timing
- `videodb` — server-side smart reframe and indexing for large footage
- `content-engine` — platform-native distribution, covers, captions
- `frontend-design-direction` — the same "decide a direction first" discipline, for UI