Communitygithub.com

render-cinematic-music-video (电影级音乐视频合成)

根据配置文件组装电影感真人风格音乐视频广告——原创演唱主题曲全程叙事,所有 35mm 胶片质感 i2v 片段按歌词窗口裁剪,依节拍硬拼接为三幕结构,主题曲以 loudnorm I=-14 混音,从歌曲自身字时间轴构建电影感下部衬线字幕,副歌高潮落下 hook 句,最终以真实品牌资产合成的品牌尾卡收尾。此为免费确定性组装阶段(裁剪到窗口 + 硬拼 + 主题曲混音 + 字幕 + 尾卡);主题曲、关键帧和片段来自 create-music-elevenlabs / create-image-gpt-image-fal / create-video-fal。适用于电影感音乐视频格式。

render-cinematic-music-video (电影级音乐视频合成) 是什么?

这个技能(`render-cinematic-music-video`)是一个免费的确定性视频组装管道,用于根据 JSON 配置文件生成电影感真人风格音乐视频广告。它完全不进行 AI 渲染或生成,而是将上游提供的资产(来自 ElevenLabs 的演唱主题曲、来自 Fal 的 35mm 胶片质感图像到视频片段、以及真实品牌尾卡资产)组装成最终的 1080×1920 视频。其工作流程包括:将每个片段精确裁剪到其歌词时间窗口,在节拍上硬拼接,用 loudnorm I=-14 混入主题曲,从主题曲自身字时间轴(而非 Whisper)烧录电影感衬线字幕,在副歌高潮处突出 hook 句,并在结尾覆盖真实品牌尾卡。该技能在 Claude Code、Cursor 及类似基于 markdown 的 AI 代理平台上使用。用户先在配置中选择创意方向(歌曲风格、歌手、演员、背景、故事弧),然后在提示词中调用 `gooseworks-ai/goose-skills` 来确定性地执行此组装——重新编辑仅需 $0,因为所有付费资产已生成。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/gooseworks-ai/goose-skills/tree/HEAD/skills/ads/capabilities/render-cinematic-music-video

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

render-cinematic-music-video

从配置文件组装一部电影感音乐视频广告:一部真人风格的短片电影,其中原创演唱主题曲作为配乐,每个视觉节拍都是一幅胶片感 tableau(柯达 Portra 颗粒、漏光、自然光、手持抖动),按歌词计时,编排为三幕结构(其形态由用户的 story_arc 选择决定),副歌高潮落下 hook 句。此功能是免费的确定性组装——裁剪到窗口、硬拼接、主题曲混音、字幕烧录以及品牌尾卡。

scripts/config.example.json 是工作示例(Hype and Vice 的“Game Day Girls”,约 28 秒 1080×1920 9:16 比例,14 个场景)——复制其结构,切勿复制其创意值;scripts/PIPELINE.md 将每个配置块映射到其源步骤,scripts/README.md 记录了免费组装过程。

运行

这是免费的确定性组装阶段——它不产生任何花费。付费输入是独立的能力:演唱主题曲(create-music-elevenlabs,force_instrumental 为 false——歌词即脚本,返回 mp3 + words_timestamps);每个节拍一个 35mm 胶片关键帧,统一风格包(create-image-gpt-image-fal);以及每个节拍一个 Kling 3.0 图像到视频片段(create-video-fal)。给定交付的主题曲 + words.json + 每个节拍一个片段 + 品牌尾卡资产后,render-cinematic-music-video 将每个片段裁剪到其歌词窗口,在节拍上硬拼接,混入主题曲,烧录电影感下部字幕,并覆盖尾卡 → 输出母版。重新编辑时复用已有的主题曲 / 关键帧 / 片段,成本为 $0。

选择

此阶段组装的创意内容由格式的 choices 在上游决定,在付费步骤之前向用户询问。工作示例中的值仅为示例,并非默认值:

  • song_style — 主题曲的流派、情绪、BPM 和编曲。示例使用了昂扬的 120 BPM 独立流行电影感主题曲。
  • vocalist — 演唱者。示例使用了自信而温暖的女主唱。
  • cast — 场景中出现的角色。示例使用了四位年轻女大学生。
  • setting — 地点 + 一天中的时间(驱动风格包的光线和色调)。示例使用了秋日黄金时段的美国大学城比赛日。
  • story_arc — 场景和歌词的三幕结构。示例使用了比赛日的一天:早晨 → 体育场巅峰 → 黄昏,并带有一个起源故事的暗示。

此组装仅通过配置(tableaux[] 窗口 + 字幕、主题曲、captions.accent_words、end_card.*)读取它们;其中没有任何硬编码。

契约(免费组装)

  • 演唱主题曲承担叙事——无需单独画外音。 生成的 ElevenLabs 音轨既是背景音乐也是脚本(force_instrumental 为 false);不要添加口语画外音或第二背景音乐。
  • 围绕交付的主题曲规划时间线。 主题曲首先生成,其长度会重塑/超出预期;将每个场景边界对齐到返回字时间轴中的歌词短语边缘——绝不将主题曲修剪到预先规划的网格上。
  • 字幕来自主题曲自身的字时间轴,而非 Whisper。 从音乐模型的 words_timestamps 导出 words.json,在歌词边界处按约 4 个词分组,并烧录电影感下部衬线字幕(--placement low),hook 句以粗斜体强调。Whisper 对演唱音频的处理会返回“🎵 Music Playing 🎵”。
  • 将 hook 落在副歌高潮处。 主角场景(is_hook)的计时使得关键句落在副歌高潮处;在字幕中强调该句。
  • 单一电影风格包 + 节拍上的硬切。 风格包(命名的胶片类型 + 颗粒 + 光晕 + 手持抖动)加上一个连续性锚点将每个片段联系在一起;将每个片段裁剪到其歌词窗口并硬拼接(可选择在主角揭示前做一个匹配切)——不使用叠化。
  • 尾卡来自真实品牌资产——绝不用扩散模型 AI 渲染文字标志。 使用真实资产(PIL/ffmpeg)合成锁定图形,或使用设计好的关键帧基板;扩散模型会使文字标志模糊不清。
  • FFmpeg 合成,确定性,免费。 将每个片段归一化到其节拍锁定窗口,硬拼接,混入主题曲(afade 淡入/淡出 + loudnorm I=-14),烧录字幕 ASS,覆盖尾卡 → 输出 1080×1920 h264+aac 母版。无需付费调用,无需密钥。

Individual skills in this repo

This repo contains 10 individual skills — each has its own dedicated page.

gooseworks-ai/goose-skills

Burned-in captions for a finished vertical video, three kinds. transcribe.py gets word timings from the video's own audio through the GooseWorks proxy (fal Whisper, bills the Ads agent, cents); captions.py burns one to three words at a time with Pillow + ffmpeg (no libass needed), either pinned to a split-screen seam (plate 25% above / 75% below) or at a fixed height, in a plate, outline or one-word serif style, with an optional red hook card; plates.py burns per-beat caption blocks (black, one union silhouette, placed in the emptiest band) for formats with no voice. The last caption (the CTA) holds to the final frame. Use as the last step of any video ad.

gooseworks-ai/goose-skills

Assemble a cartoon / animated / hand-crafted music-video ad from a config — a sung song carries the whole narrative while N per-bar i2v clips (one recurring animated character, one look pack) are each cut to their BAR window from librosa beat-tracking and hard-concatenated on the bar, VEED-whisper white bold-sans captions in the BOTTOM third (Alignment 2, above the logo bug, no pill) burned from the song's word timings re-spelled against the locked lyrics, a persistent brand logo bug held over the body (suppressed on the end card), and closed on a solid-brand-color PIL end card with the song still playing under it — never AI-rendered text. This is the FREE deterministic assembly stage (cut-to-bar + hard concat + logo bug + captions + end card + song mux); the song, character, keyframes, and clips come from create-music-elevenlabs / create-image-fal / create-video-fal. Use for the cartoon-music-video format.

gooseworks-ai/goose-skills

Assemble an editorial-motion podcast-clip ad from a config — a real clipped podcast MP3 carries the narrative while N flat limited-palette editorial-illustration keyframes (one look pack) are animated NOT by generative i2v but by DETERMINISTIC ffmpeg ken-burns (zoompan) + hard cuts (no crossfades, which expose geometric drift), each beat snapped to its spoken line, the real audio muxed, Whisper-driven captions burned only mid-sentence, and closed on a PIL brand end card — never AI-rendered text. This is the FREE deterministic assembly stage (ffmpeg ken-burns + hard concat + audio mux + captions + end card); the real audio is clipped from source and the keyframes come from create-image-fal. Use for the editorial-motion-podcast format.

gooseworks-ai/goose-skills

Analyze the message match between your ads and landing pages. Checks if the promise in the ad copy carries through to the landing page headline, body, and CTA. Flags disconnects that kill conversion rates. Works with Google, Meta, and LinkedIn ads.

gooseworks-ai/goose-skills

Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai. Multi-image reference (avatar + product + setting), native lip-synced VO + ambient audio (generate-audio on by default), internal multi-cut handling within one render. Routes through the GooseWorks FAL proxy (bills the Ads agent). The default clip atom for AI-creator UGC ads built on the NB2 + Seedance architecture. Validated on beauty-by-earth/video-01.

gooseworks-ai/goose-skills

Mandatory pre-publish review gate for a UGC video render. Transcribes the finished render's AUDIO with Whisper and word-diffs it against the approved spoken script, then gates set_final_render — blocking a render whose generated audio mis-voices a word (e.g. the approved "human-vetted" spoken as "human witted"), drops an approved phrase, or comes back silent. Runnable, gating counterpart to content-goose's review-transcript-integrity atom. Every ugc-video-formats recipe runs this after render and BEFORE set_final_render.

gooseworks-ai/goose-skills

Render pixel-accurate Apple Notes (iPhone, light mode) screenshot mockups from a JSON note spec. Outputs HTML + PNG at the iPhone 16/15 Pro native 1180×2556. Supports paragraphs, images, checklists, dividers, autocorrect underline, smart quotes, and an optional iOS keyboard chrome overlay used by the parent video-ad molecule.

gooseworks-ai/goose-skills

Extract competitor and customer intelligence from any company's landing page HTML. Discovers tech stack, analytics tools, ad pixels, customer logos, SEO metadata, CTAs, hidden elements, and more. No API keys required.

gooseworks-ai/goose-skills

Find speakers, hosts, and guest profiles at conferences and events on Luma. Two modes - free direct scrape for hosts, or Apify-powered search for full guest profiles with LinkedIn/Twitter/bio.

gooseworks-ai/goose-skills

Find Twitter/X influencers to promote a product or brand. Use when asked to find influencers, discover Twitter accounts for partnerships, identify creators in a niche, or build an influencer outreach list.

相关技能