一键在 Manus 中运行任何 Skill

render-glassy-matte-grwm

星标1,046

分支193

更新时间2026年7月18日 06:18

Assemble a multi-scene GRWM beauty-demo ad from a config — a locked-identity creator applies ~5 products step by step while a SEPARATE ElevenLabs voiceover narrates and every scene cut is snapped to the VO's product-name word-starts (Whisper word-level timestamps), then ~5 Playwright product overlay cards (real PDP-verified taglines) are composited onto the master each on its product-NAME word-start, the SEPARATE VO is mixed on top of a ducked music bed at loudnorm I=-14, clean-white 3-words/cue captions are burned, and the video closes on a flat-lay end card. This is the FREE deterministic assembly stage (re-cut to the VO word-starts, hard-concat, Playwright card render + card composite, VO plus music mix, caption burn, flat-lay end card); the VO, scene clips, product cutouts, and music come from create-music-elevenlabs / create-image-gpt-image-fal / create-video-fal. Use for the glassy-matte-grwm format.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

gooseworks-ai

gooseworks-ai/goose-skills

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

render-glassy-matte-grwm

Assemble a multi-scene GRWM beauty-demo ad from a config — a locked-identity creator applies ~5 makeup/skincare products step by step at a vanity, a separate ElevenLabs voiceover narrates the routine, and every scene cut is snapped to the VO's product-name word-starts, with ~5 Playwright product overlay cards on the product-name beats, a ducked music bed, burned captions, and a flat-lay end card. This capability is the FREE, deterministic assembly — the Whisper-driven re-cut + hard-concat, the Playwright card render + card composite, the VO + music mix, the caption burn, and the flat-lay end card.

This is the multi-scene beauty demo, distinct from the single-take apparel outfit-reveal (ugc-grwm, one Seedance reference-to-video call with native lip-sync and minimal post). Here the timeline is driven by a SEPARATE VO and the scenes are re-cut to its word-starts.

scripts/config.example.json is the worked example (DIBS Beauty "5-Step Glassy Matte Routine", ~32s 1080×1920 9:16, 12 VO-snapped cuts + 5 product cards); scripts/PIPELINE.md maps every config block to its source step and scripts/README.md documents the free assembly.

Run

This is the FREE, deterministic assembly stage — it spends nothing. The paid inputs are separate capabilities — the SEPARATE narration VO (create-music-elevenlabs, or a user-supplied mp3; word-level Whisper timestamps set the timeline), ~7 Seedance scene clips one per product step (create-video-fal), the ~5 white-bg product cutouts + the flat-lay end-card still (create-image-gpt-image-fal), and the ducked music bed. Given the VO + .words.json + one clip per step + the ~5 product cutouts + the music bed, render-glassy-matte-grwm re-cuts each clip to its VO word-start window, hard-concats on the cut, renders + composites the product cards on the product-name beats, mixes the VO over the ducked music, burns the captions, and appends the flat-lay end card → the master. Re-cuts reuse the existing VO / clips / cutouts and cost $0.

Contract (the free assembly)

The SEPARATE VO drives the timeline — Whisper it first. The narration is a separate track (not a native take). Its word-level timestamps set every cut; the atempo'd VO ends shorter than the plan expects (a 1.15× VO landed ~27.5s), so time every window to the word-starts, never to a pre-planned grid.
Scene cuts snap to the "step N" word-start; cards snap to the product-NAME word-start. Cut to the next product when its step is announced; the card animates in ~1s later when the NAME is spoken. Both happen. ~12 cuts over ~32s (cuts/10s ≈ 3.75).
Hard-concat with a re-encode. Hard cuts on the VO word-starts, no dissolves; re-encode the concat -c:v libx264 -crf 20 — -c copy corrupts the duration when zoompan/PNG clips are in the chain.
Product cards — Playwright, real cutout, PDP-verified tagline. Playwright renders the card template at 2× scale (real white-bg cutout thumb + name + PDP tagline). The cutout must match the REAL product, not the Seedance scene's hallucinated barrel; the tagline is verified against the brand PDP (AI flat-lays hallucinate sublines). Composite each card onto the master snapped to its product-NAME word-start, 1s fade-in, held until the next product is named. PNG overlay inputs need -loop 1 -t <dur> — without it the PNG emits one frame at t=0 and the fade/enable filters silently no-op (cards go invisible).
VO leads the ducked music bed. Mix the SEPARATE VO on top of the ducked music (the VO is the lead), loudnorm I=-14. If the host ffmpeg lacks a filter, apad/atrim to length before the mix.
Captions — clean-white, override the preset. Clean-white captions from the VO's Whisper words, overridden to 3 words/cue, ~3.0% font, ~20% margin, NO pill, NO shadow (the default 5-words/4.5%/18% reads too dense). Burn last. If the host ffmpeg lacks libass, render the cues as timed PIL PNG overlays composited with ffmpeg overlay=…:enable='between(t,st,en)' at the same placement.
Flat-lay end card. Append the flat-lay still (ken-burns hold ~4s) — a gpt-image-2 flat-lay of the ~5 products; do NOT trust its AI-rendered sublines for the card taglines.
FFmpeg composite, deterministic, FREE. Re-cut, hard-concat, render + composite the cards, mix the VO over the ducked music, burn the captions, append the end card → a 1080×1920 30fps h264+aac master (~32s). No paid calls, no keys.

同仓库更多 Skills

同仓库

create-image-gpt-image-fal

gooseworks-ai/goose-skills

Generate a single photoreal or designed image with OpenAI gpt-image via fal.ai. Supports gpt-image-1 (default, fixed sizes — the FAL fallback for Higgsfield's `gpt_image_2`) and gpt-image-2 (`openai/gpt-image-2`, custom output sizes up to 3840px). Routes to text-to-image or the edit variant depending on whether a reference image is provided. Use for photoreal character anchors, scene keyframes, and designed sheets (e.g. storyboards) where precise layout and legible text matter.

2026-07-191.0k

render-cartoon-music-video

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.

2026-07-191.0k

render-cosmic-mythology-voiceover

gooseworks-ai/goose-skills

Assemble a cosmic-mythology-voiceover reel from a config — a warm spoken voiceover carries the whole narrative while N curated cosmic stills are weighted beat-synced across the delivered VO duration (cut_dur = VO_dur times weight over the weight sum, so emotional beats hold longer), Ken-Burns-zoomed per still (scale 2x, center crop, zoompan, fade-in first and fade-out last), ffmpeg-concatenated, the VO composited under the picture (libx264 crf18 plus aac), the ONE on-screen hook line faded on over the open with a drawtext alpha window, and Whisper/VEED captions burned along the bottom — never in-world text on a still. This is the FREE deterministic assembly stage (weighted sequence plus Ken-Burns plus concat plus VO composite plus hook overlay plus caption burn); the VO and the stills come from create-vo-elevenlabs and create-image-fal. Use for the cosmic-mythology-voiceover format.

2026-07-191.0k

render-creator-pip-listicle

gooseworks-ai/goose-skills

Assemble a creator picture-in-picture product-listicle ad from a config — the creator stays FULL-FRAME the whole beat (voice plus lips generated together per beat, no separate VO, no cut to a full-frame product shot), and on each product beat three persistent overlays ride on top for the WHOLE beat — a title pill top-center, the DEMO in a rounded PiP window top-right (the brand's real UGC clip MUTED, or for a no-UGC brand the product's own autocropped UI still / screen-recording sized to fill the window), and a bottom product card (rounded thumbnail plus 'N · CATEGORY' small-caps plus product NAME in a serif face). Hook plus CTA beats are the creator full-frame with the title pill only. Assembly builds ONE full-1080x1920 transparent overlay PNG per beat, overlays it on the creator clip (cover-scaled to 1080x1920) for the whole beat keeping the native audio, concats all beats, then burns captions LAST as timed PIL PNG overlays (this ffmpeg has no libass) timed deterministically from the known per-beat script.

2026-07-191.0k

render-food-product-sizzle

gooseworks-ai/goose-skills

Assemble a wordless macro-tabletop food-product sizzle ad from a config — normalize fps and SAR across ~4 photorealistic macro clips (hands tearing, flat lay, bite, box hero), concat them, apply a global anti-AI grain pass (eq plus hqdn3d plus noise), composite the audio (a non-diegetic acoustic music bed plus a couple of short diegetic SFX like a snap and a tear placed at measured cue points, loudnorm), composite a STATIC end card entirely in PIL (real logo PNG plus real product PNG plus a serif heritage headline plus a CTA — never AI-rendered text), and burn optional serif stat-callout pills at beats. This is the FREE deterministic assembly stage (normalized concat plus grain plus music and SFX mix plus PIL end card plus callouts); the macro keyframes, i2v clips, and music bed come from create-image-fal, create-video-fal, and create-music-elevenlabs. Use for the food-product-sizzle format.

2026-07-191.0k

render-split-screen-creator

gooseworks-ai/goose-skills

Assemble a split-screen creator ad from a config — a two-zone vertical composite where a supplied AI-creator lip-sync take fills the BOTTOM ~48% while real 16:9 product/demo clips run uncropped in the TOP ~52%, each top clip contain-fit with a darkened blurred cover-scale fill of the same clip (never black bars), a 3px brand-color divider between the zones, the creator slice cover-fit per the per-scene VO timing, scenes hard-concatenated with the body audio being the concatenated creator VO slices, an end card held on the last sharp frame ~3s, then the ASSEMBLED cut transcribed with local Whisper (not the raw VO — concat drops inter-scene silence) and word-level captions burned in the chosen style. This is the FREE deterministic assembly + caption stage (two-zone composite + blurred fill + divider + hard-concat + end card + captions); the VO comes from create-vo-elevenlabs, the anchor from create-image-gpt-image-fal, and the whole-VO lip-sync from a paid VEED Fabric 1.0 take (a no-atom upstream input). Use fo

2026-07-191.0k

name	render-glassy-matte-grwm
description	Assemble a multi-scene GRWM beauty-demo ad from a config — a locked-identity creator applies ~5 products step by step while a SEPARATE ElevenLabs voiceover narrates and every scene cut is snapped to the VO's product-name word-starts (Whisper word-level timestamps), then ~5 Playwright product overlay cards (real PDP-verified taglines) are composited onto the master each on its product-NAME word-start, the SEPARATE VO is mixed on top of a ducked music bed at loudnorm I=-14, clean-white 3-words/cue captions are burned, and the video closes on a flat-lay end card. This is the FREE deterministic assembly stage (re-cut to the VO word-starts, hard-concat, Playwright card render + card composite, VO plus music mix, caption burn, flat-lay end card); the VO, scene clips, product cutouts, and music come from create-music-elevenlabs / create-image-gpt-image-fal / create-video-fal. Use for the glassy-matte-grwm format.
status	active

render-glassy-matte-grwm

Run

Contract (the free assembly)

The SEPARATE VO drives the timeline — Whisper it first. The narration is a separate track (not a native take). Its word-level timestamps set every cut; the atempo'd VO ends shorter than the plan expects (a 1.15× VO landed ~27.5s), so time every window to the word-starts, never to a pre-planned grid.
Scene cuts snap to the "step N" word-start; cards snap to the product-NAME word-start. Cut to the next product when its step is announced; the card animates in ~1s later when the NAME is spoken. Both happen. ~12 cuts over ~32s (cuts/10s ≈ 3.75).
Hard-concat with a re-encode. Hard cuts on the VO word-starts, no dissolves; re-encode the concat -c:v libx264 -crf 20 — -c copy corrupts the duration when zoompan/PNG clips are in the chain.
Product cards — Playwright, real cutout, PDP-verified tagline. Playwright renders the card template at 2× scale (real white-bg cutout thumb + name + PDP tagline). The cutout must match the REAL product, not the Seedance scene's hallucinated barrel; the tagline is verified against the brand PDP (AI flat-lays hallucinate sublines). Composite each card onto the master snapped to its product-NAME word-start, 1s fade-in, held until the next product is named. PNG overlay inputs need -loop 1 -t <dur> — without it the PNG emits one frame at t=0 and the fade/enable filters silently no-op (cards go invisible).
VO leads the ducked music bed. Mix the SEPARATE VO on top of the ducked music (the VO is the lead), loudnorm I=-14. If the host ffmpeg lacks a filter, apad/atrim to length before the mix.
Captions — clean-white, override the preset. Clean-white captions from the VO's Whisper words, overridden to 3 words/cue, ~3.0% font, ~20% margin, NO pill, NO shadow (the default 5-words/4.5%/18% reads too dense). Burn last. If the host ffmpeg lacks libass, render the cues as timed PIL PNG overlays composited with ffmpeg overlay=…:enable='between(t,st,en)' at the same placement.
Flat-lay end card. Append the flat-lay still (ken-burns hold ~4s) — a gpt-image-2 flat-lay of the ~5 products; do NOT trust its AI-rendered sublines for the card taglines.
FFmpeg composite, deterministic, FREE. Re-cut, hard-concat, render + composite the cards, mix the VO over the ducked music, burn the captions, append the end card → a 1080×1920 30fps h264+aac master (~32s). No paid calls, no keys.