E-commerce Lookbook — cinematic fashion b-roll + a pixel-perfect product-card overlay

A finished reel = vertical 9:16 + voiceover + music bed + a pixel-perfect product-card HTML overlay + 30–45s. Pass `aspect_ratio: "9:16"` to `generate_project` (it threads to every scene; keep the garment consistent across shots with `character_anchor:"always"` + a restated wardrobe — the model often returns 4:3, so the Ken-Burns step cover-crops to exactly 1080×1920, see the note below), animate in waves of ≤4–5 with `resolution:"auto"` (or use the Ken-Burns stills fallback when fal's video tier is flaky), stitch with `create_media model_override:"ffmpeg-concat"`, then lay `chatterbox-tts` narration over a ducked `music` bed with `create_media model_override:"ffmpeg-mux"` + `audio_fill:"loop"` (so audio covers the FULL reel — no silent tail), then composite a single `hyperframes-render` document — the product card — over the whole reel. A silent montage with the price melted into a blurry frame is a draft, not a deliverable — see the `short-form-video` skill's *definition of done* and the `hyperframes-overlays` skill for the overlay pattern.

generate_projectltx-q-i2vseedance-i2vchatterbox-ttsmusicffmpeg-concatffmpeg-muxhyperframes-render

Output

Hook → styling → detail → CTA
5–7 cinematic 9:16 beats
Same garment across shots
Brand voice + chic bed
hyperframes-render product card
9:16 MP4

Time

1 product → 30–45s vertical lookbook in ~6–12 min

Budget

$0.80–$4.00 per reel (5–7 beat keyframes + Ken-Burns/motion + TTS + music + hyperframes overlay)

Reliability

4.4

Customize this playbook

Fill in the fields below. Your answers are inserted into the complete recipe when you copy it.

exactly as it appears on the card — e.g. "The Camel Trench"

the exact price as it must read — e.g. "$189". This renders as HTML,

the size row, brackets = the highlighted/in-focus size —

e.g. "★★★★★ 4.9 (320)". Blank to omit the rating row.

the scarcity line — e.g. "Only 4 left in size M". Blank to omit.

the top-corner badge — e.g. "FREE SHIPPING". Blank to omit.

the button copy

restated in EVERY scene prompt to stop drift — e.g. "a camel

OPTIONAL — your real product shot; used via kontext-edit for the

the scenes to shoot — e.g. "city street morning, café window seat,

5–7 — hook → 2–3 styling beats → detail → CTA

ken-burns (DEFAULT — deterministic, exactly 9:16, zero garment drift)

e.g. "warm, confident, quiet luxury"

e.g. "downtempo fashion-runway, no vocals"

30–45