taste

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Taste

审美导向

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.
大多数AI视频建议都停留在如何渲染帧的层面。本技能则位于更高层级:帧应该呈现何种样貌、以何种顺序排列、配合何种节奏剪辑,最终产出的作品是一个具有明确意图的整体,而非零散生成内容的堆砌。
它编码了一种特定的审美取向——angelcore / cloud-trance / hyperpop风格家族(融合Bladee《Silver Surfer》时期的空灵trance与浓郁angelcore风格),提炼自大量保存的Reels视频以及一个包含约70个条目的视觉流派库。它的设计带有明确的主观倾向,因为审美是一种观点,而非菜单选项。
配套文件
references/genre-taxonomy.md
包含完整的命名流派目录。 本文档则是可落地执行的层面:涵盖情绪、剪辑规则、流水线以及节拍映射的镜头方案。

When to Activate

适用场景

  • 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.
  • 制作音乐视频、歌词视频、粉丝剪辑或可视化视频。
  • 制作短视频剪辑/影片时,风格感受比信息传递更重要。
  • 驱动AI B-roll生成(fal.ai、Veo、Kling等工具),且提示词需要连贯的风格方向而非零散氛围。
  • 制作情绪板或在渲染前确定视觉流派。
  • 用户提及“审美”“做成X风格”“给个方向”“angelcore”“cloud trance”“hyperpop edit”“Bladee”“dreamcore”,或是指定某个保存的参考案例时。
  • 当前剪辑能正常播放,但显得平淡、通用、AI感过重或风格不连贯时。
本技能建立在
video-editing
(机械操作)和
remotion-video-creation
(渲染工具)之上。前者用于解决怎么做的问题,后者用于解决做什么、为什么这么做的问题。

Core Thesis

核心论点

  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%.
  1. 审美是最终环节,但必须最先确定
    video-editing
    技能提到审美是最终的人工调整环节,但陷阱在于:如果只在最后才确定审美,那么上游的每一次生成和剪辑都是盲猜。在编写第一个提示词前就选定风格方向,然后让它约束所有后续环节。
  2. 连贯性优于新颖性。30个镜头统一一种风格,胜过30个镜头30种风格。一个命名流派(如下文所示)是能免费带来连贯性的约束条件。
  3. 跟着歌曲节奏剪辑,而非素材节奏。在音乐视频中,时间线就是波形图。每一次硬切都要落在节拍或瞬态音上。帧计算规则在流水线部分说明。
  4. 选择性生成,果断性剪辑。AI能生成不存在的B-roll,但无法生成审美。你仍需要舍弃80%的生成内容。

The Aesthetic Vocabulary (distilled)

提炼后的美学词汇

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:
FamilyGenres in itReads as
Ethereal / divinespiritualism, glacial folk, beacons, zen core, fairy taleweightless, holy, glowing, soft
Hyperpop / Y2K-cybercyberdelia, acid house, acid nora, neo aggressano, new liquidglossy, chrome, neon, kawaii-cyber
Dark / occultdark academia, smoke nostalgia, communist core, abstract techhigh-contrast, ominous, grain
Retro / printretro surfers, art deco, adventure pulp, classic advertising, magazine collage, bumper stickersflat, graphic, halftone, nostalgic
Organic / texturalmicrobiology core, weaving patterns, fruitage retro, cozy blanket, pacific punk wavetactile, macro, woven, wet
Systemic / datanumbers, mazes, code web, heatmap, pixel, 8-bitgridded, 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.
参考素材库涵盖了大量命名的视觉流派,完整列表见
references/genre-taxonomy.md
。关键不是记住70个流派名称,而是要明白流派名称就是一套完整的提示词和质量评估预设。选定一个流派,就继承了它的调色板、纹理、光线和主题内容。
流派会聚类成不同家族。选择一个主风格家族,最多搭配一个辅助风格
风格家族包含流派风格感受
空灵/神圣spiritualism、glacial folk、beacons、zen core、fairy tale失重、圣洁、发光、柔和
Hyperpop / Y2K赛博cyberdelia、acid house、acid nora、neo aggressano、new liquid光滑、镀铬、霓虹、卡哇伊赛博风
暗黑/神秘dark academia、smoke nostalgia、communist core、abstract tech高对比度、诡异、颗粒感
复古/印刷retro surfers、art deco、adventure pulp、classic advertising、magazine collage、bumper stickers扁平化、图形化、半色调、怀旧
有机/纹理microbiology core、weaving patterns、fruitage retro、cozy blanket、pacific punk wave触感、微距、编织感、湿润
系统/数据numbers、mazes、code web、heatmap、pixel、8-bit网格化、生成式、示意图
当前项目的主风格是空灵/神圣,搭配Hyperpop / Y2K赛博辅助风格——即圣洁光线与水晶光晕,点缀镀铬和霓虹元素。这种组合就是angelcore × cloud-trance的核心要求。

The Mood System — angelcore × cloud-trance

情绪系统 —— angelcore × cloud-trance

Distilled directly from the strongest reference reels. This is the concrete grade.
直接从最优质的参考视频中提炼而来,是具体的风格标准。

Palette

调色板

  • 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.
  • 基础色:近乎纯黑的背景(#05060a)和骨白色(#f4f1ea)。大多数帧只使用其中一种颜色。
  • 神圣辅助色:熔金/橘红色(#ffb24d → #ff7a18)——黑暗中唯一的暖光。
  • 水晶辅助色:彩虹色紫→青→粉散景(#8a6bff、#4fc3ff、#ff6ad5)——hyperpop风格光晕,用于明亮帧。
  • 警示辅助色(慎用):单色背景上的亮红色(#ff2a2a)——仅用于1-2次冲击性剪辑。
  • Hyperpop主题色:糖果粉头发/镀铬/亮白色搭配蓝天。
规则:每个镜头仅使用一种辅助色。金色用于暗帧;彩虹色用于亮帧;同一镜头中绝不混用。

Light & texture

光线与纹理

  • 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.
  • 黑暗中穿透单一暖光源(熔金光晕、神圣光束)。高对比度,深邃黑色。
  • 水晶/闪光散景、镜头光晕、光晕效果、漏光——神圣感,而非脏污感。
  • 暗帧添加胶片颗粒+轻微色差;亮帧保持干净光滑。
  • 负空间的微距细节:黑色背景中居中的核心物体(钥匙、眼睛、齿轮、花瓣、水滴)。
  • 主题元素:带翼人物、云朵、光环、天使、水晶结构、糖果赛博风肖像。

Motion

运动

  • 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.
  • 缓慢、漂浮、失重的镜头移动(漂移、缓慢推进、缓慢环绕)——cloud trance风格。
  • 仅在drop段落爆发速度。其余所有画面都要有呼吸感。
  • 粒子上升(熔渣、灰尘、闪光)——向上运动代表升华。

The Editing Grammar (distilled)

提炼后的剪辑规则

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.
从参考剪辑中,提炼出反复出现且定义风格的技巧:
  1. 节拍锁定硬切。主歌/drop段落不使用溶解转场。跟着底鼓节拍剪辑。观众的视觉应能感受到BPM。
  2. 黑色背景微距核心镜头插入。单一清晰物体居中于黑色负空间,保持1-2拍后剪辑。这类镜头的节奏蒙太奇是cloud-trance的标志性手法。
  3. 光晕/爆炸转场。白色或熔金光晕在瞬态音时充满画面,随后过渡到下一个镜头。即“神圣闪光”转场。
  4. 单色画面中的色彩突出。一段画面使用黑白,然后单个彩色元素(红眼、金焰、粉发)在重拍时突然出现。
  5. Drop段落前的速度渐变。在drop前最后一小节将素材从慢到快加速,在第一拍硬切到节拍速度。
  6. 关键词字幕高亮(仅适用于访谈/歌词段落)。全大写,1-2个单词用辅助色高亮,同步人声。用于歌词视频,不适用于纯可视化视频。
  7. 画中画反应镜头(仅适用于解说/剪辑评论)。访谈画面作为画中画叠加在B-roll上。音乐视频本身不涉及此技巧;记录是因为参考素材大量使用。
禁忌:节拍段落使用交叉溶解转场;同一镜头使用多种辅助色;镜头时长超过音乐乐句;画面中保留可识别的UI边框(裁剪掉);同一时间线混合不同宽高比。

The Pipeline — mixing the ECC video skills

流水线 —— 整合ECC视频技能

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
StepECC skill to loadWhat 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
,
motion-ui
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
本技能是指挥者,每个ECC技能都是乐器。不要跳过任何环节。
0. 审美导向(本技能)        在渲染前确定流派+情绪+剪辑规则
1. 结构(video-editing)  标记歌曲的时间节点:前奏/主歌/drop/桥段/尾声
2. 生成(fal-ai-media)   按流派提示词预设生成B-roll;舍弃80%内容
3. 剪辑(video-editing/FFmpeg)  节拍剪辑+重新构图为9:16;在时间线上整理精选素材
4. 合成(remotion-video-creation)  叠加层、光晕、歌词文本、节拍同步序列
5. 运动(motion-*技能)  缓动曲线、漏光/粒子运动、转场时机
6. 音频(fal-ai-media)  转场上升音效/冲击音效强化剪辑效果(歌曲本身在Ableton中处理)
7. 润色                    按上述调色板校色,最终节奏调整,导出
8. 分发(content-engine)  适配平台的版本+字幕/封面
步骤加载的ECC技能在此环节的作用
结构与剪辑
video-editing
FFmpeg剪辑/拼接/重构图、EDL、场景/静音检测
生成B-roll
fal-ai-media
按流派预设调用图像/视频模型
合成与叠加
remotion-video-creation
节拍同步
<Sequence>
、文本、光晕、遮罩
运动时机
motion-foundations
motion-patterns
motion-advanced
motion-ui
缓动效果、弹性效果、光线/粒子运动
服务器端视频处理
videodb
智能重构图、大素材索引
分发
content-engine
适配各平台的剪辑版本、封面、字幕
语音/歌词旁白
video-editing
(ElevenLabs模块)
仅在需要旁白时使用

Beat Math (lock cuts to the song)

节拍计算(剪辑锁定歌曲节奏)

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)}> ...
当前曲目为138 BPM,B小调。固定参数:
  • 每拍秒数 = 60 / 138 = 0.43478s
  • 每拍帧数 = fps × 0.43478
    24fps: 10.4330fps: 13.0460fps: 26.09
  • 1小节(4拍) = 1.7391s
    → 30fps: 52.17帧
  • 8小节乐句 = 13.913s
    → 曲目的循环时长
在Remotion中,将每个
from={}
对齐到节拍:
ts
const FPS = 30;
const BPM = 138;
const beat = (n: number) => Math.round(n * (60 / BPM) * FPS); // beat(n) → 帧位置
// 在节拍0,4,8,...处剪辑:  <Sequence from={beat(0)} durationInFrames={beat(4)}> ...

Beat-Mapped Shot Plan (this music video)

节拍映射镜头方案(本音乐视频)

The song arrangement (from the project's own notes) is Intro → Verse → Drop → Bridge → Drop → Outro (~2:05). Map taste to each section:
SectionGenre/mood leanGrammarShot ideas
IntroEthereal/divine, near-blackslow push, no cutsember bloom in the void; a single shaft of gold; dust rising
VerseDark + macro hero-on-blackhard cuts every 2 beatskey, eye, gear, water drop, petal — rhythmic macro montage
DropHyperpop bloom + crystallinespeed-ramp in, cut on the one, fastcandy-pink figure, chrome, iridescent bokeh, winged ascension
BridgeSpiritualism, weightlessone long held shot, color-popclouds + halo; single red accent punches once
Drop 2as Drop, intensifyadd divine-flash blooms on transientswings open, glitter burst, light leaks maxed
OutroGlacial folk, cold calmslow fade to blackcrystalline structure dissolving; ember dies out
歌曲结构(来自项目笔记)为 前奏 → 主歌 → Drop → 桥段 → Drop → 尾声(约2分05秒)。为每个段落匹配风格:
段落流派/情绪倾向剪辑规则镜头创意
前奏空灵/神圣,近乎纯黑缓慢推进,无剪辑黑暗中的熔金光晕;单一金色光束;灰尘上升
主歌暗黑+微距核心镜头每2拍硬切钥匙、眼睛、齿轮、水滴、花瓣——节奏化微距蒙太奇
DropHyperpop光晕+水晶风格速度渐变进入,第一拍硬切,快速剪辑糖果粉人物、镀铬元素、彩虹色散景、带翼升华
桥段灵性风格,失重感单个长镜头,色彩突出云朵+光环;单次红色元素冲击
Drop 2同Drop,强化效果瞬态音时添加神圣闪光光晕翅膀展开、闪光爆发、漏光拉满
尾声Glacial folk,冷静舒缓缓慢淡出至黑水晶结构溶解;熔金光晕熄灭

fal.ai Prompt Presets (per mood)

fal.ai提示词预设(按情绪分类)

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.
配合
fal-ai-media
使用。每个预设都是适配项目调色板的流派风格。所有预设末尾添加
9:16, vertical, cinematic, film grain, volumetric light, no text, no watermark
  • 神圣虚空:"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"
  • 微距核心:"extreme macro of an antique brass key / a human eye / interlocking gears, centered on pure black negative space, razor-sharp detail, single rim light"
  • 水晶光晕:"iridescent violet-cyan-magenta crystalline bokeh, glittering light refraction, dreamy lens flares, heavenly glow, soft focus, hyperpop angelcore"
  • 糖果赛博肖像:"candy-pink-haired figure, glossy chrome accents, bright blue sky, Y2K hyperpop, clean gloss, saturated, kawaii-cyber"
  • 带翼升华:"a winged figure ascending into clouds, halo of light, bone-white and gold, volumetric god-rays, ethereal, religious iconography, soft"
  • 清冷尾声:"pale crystalline ice structure slowly dissolving, glacial folk, cold blue and bone white, minimal, calm, fading to black"
每个预设生成6-10个素材,保留2-3个。若需动态效果,使用图像转视频模型将静态图动画化,或直接生成短剪辑;按运动规则保持镜头移动缓慢。

FFmpeg Recipes (cut + reframe)

FFmpeg配方(剪辑+重构图)

bash
undefined
bash
undefined

Reframe any landscape/raw clip to 9:16 (center crop)

将任何横屏/原始素材重构图为9:16(居中裁剪)

ffmpeg -i in.mp4 -vf "crop=ih*9/16:ih,scale=1080:1920" v.mp4
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)

将素材精确剪辑为138 BPM下的N拍(例如2拍=0.8696s)

ffmpeg -i in.mp4 -t 0.8696 -c copy beat2.mp4
ffmpeg -i in.mp4 -t 0.8696 -c copy beat2.mp4

Concatenate beat-selects into the verse montage

将精选节拍素材拼接为主歌蒙太奇

for f in selects/*.mp4; do echo "file '$f'"; done > concat.txt ffmpeg -f concat -safe 0 -i concat.txt -c copy verse.mp4
for f in selects/*.mp4; do echo "file '$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)

从录屏参考素材中移除UI边框/状态栏(裁剪上下部分)

ffmpeg -i reel.mp4 -vf "crop=iw:ih-300:0:150" clean.mp4
undefined
ffmpeg -i reel.mp4 -vf "crop=iw:ih-300:0:150" clean.mp4
undefined

Remotion Composition Skeleton (beat-synced)

Remotion合成框架(节拍同步)

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.
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" }); // 瞬态音时的神圣闪光
  return <AbsoluteFill style={{ background: "radial-gradient(#fff,#ffb24d)", opacity: o, mixBlendMode: "screen" }} />;
};

export const AngelcoreMV: React.FC = () => (
  <AbsoluteFill style={{ background: "#05060a" }}>
    {/* 主歌:黑色背景微距核心镜头,每2拍硬切 */}
    <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:水晶光晕+第一拍闪光 */}
    <Sequence from={beat(8)} durationInFrames={beat(16)}><Video src="/selects/crystalline.mp4" /></Sequence>
    <Sequence from={beat(8)} durationInFrames={beat(1)}><Bloom /></Sequence>
  </AbsoluteFill>
);
渲染命令:
npx remotion render src/index.ts AngelcoreMV out.mp4
。项目设置、音轨绑定和渲染参数请参考
remotion-video-creation

Key Principles

核心原则

  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.
  1. 在第一次生成前确定流派。选择一个主风格家族+一个辅助风格。
  2. 每个镜头仅使用一种辅助色。金色用于暗帧,彩虹色用于亮帧,红色仅用一次。
  3. 每一次硬切都落在节拍上。使用节拍计算;节拍段落不使用转场。
  4. 黑色背景微距核心镜头是标志性手法。熟练掌握;它支撑主歌段落。
  5. 生成10个,保留2个。连贯性来自筛选,而非更精准的提示词。
  6. 裁剪UI边框。最终画面中不要保留状态栏、字幕或UI元素。
  7. 审美最先确定,最后评估。设定方向,然后在每一次剪辑中坚持该方向。

Related Skills

相关技能

  • 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
    ,
    motion-ui
    — 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
  • video-editing
    —— 本技能所依赖的机械流水线(FFmpeg、重构图、EDL、润色)
  • remotion-video-creation
    —— 可编程的节拍同步合成与渲染
  • fal-ai-media
    —— 生成B-roll、转场音效和上升音效
  • motion-foundations
    motion-patterns
    motion-advanced
    motion-ui
    —— 缓动与运动时机
  • videodb
    —— 服务器端智能重构图与大素材索引
  • content-engine
    —— 适配平台的分发、封面、字幕
  • frontend-design-direction
    —— 同样遵循“先确定方向”原则,适用于UI设计