Neon Payment Link in 17 Seconds
A six-shot Wise product spot that turns a glowing icon into a clear create-share-pay flow.
By @MoveStudioin for WiseSource offlineOriginal post ↗
Copies get_blueprint("REF-3597") for Claude. Connect Claude
The original post is no longer available on X
Why it works
The opening holds a small control for 33 frames, then cuts to a macro action emblem before the bright workflow at frame 71. Shot 3's reframes at frames 87 and 119 guide attention through a real UI without extra cuts; the dark result and benefit cards lead to a pale close at frame 429. Narration carries 35 words while the picture alternates strong brightness states and leaves the edit off an unreliable beat grid.
Blueprint
15 plates that take the film apart, from its format to a recipe you can run. Claude reads the same plates over MCP.
Plate 01
The format in one breath
(inferred) A tiny luminous control becomes an oversized action symbol; a bright interface proves one action; a dark result card and kinetic benefits finish in a pale brand close. The action is demonstrated before the claims, and a compact narration carries the film through stark field changes.
Why it works
- (inferred) The hook stays small until the cut at frame 33, then the control fills the screen before the bright proof begins at frame 71.
- (inferred) Shot 3 uses two internal reframes, at frames 87 and 119, to move from form detail to amount without adding shots.
- (inferred) Mean luma changes from the bright interface to the dark share state, then rises again for shot 6; the narration bridges these changes.
Plate 02
Format card
| Platform · aspect · length | X · 16:9 · 17.47 s · source 1280×720 · deliver 1920×1080 · 30 fps |
| Pace | 6 shots · 5 hard cuts · measured median 3.23 s |
| Script | Narration-led · 35 spoken words · about 175 wpm while speaking; cuts follow phrases, captions are selective |
| Voice | Bright adult commercial narrator, precise and animated |
| On screen | Abstract control · oversized icon · staged UI · share result · benefit type · brand close |
| Type | Seven cap-height levels, 16–167 px in the reference; essential copy ≥38 px; punchy build on twos |
| Sound | Tonal bed, no dependable steady pulse; cue to picture and phrases; X target −14 LUFS, ≤−1 dBTP |
| Structure | Six beats; action proof in shot 3, result in shot 4, benefit in shot 5, close in shot 6 |
Tools you'll need: Remotion for motion graphics · ElevenLabs or a recorded voice · a licensed or generated music track · Claude alone: yes
Frame sheets
Frame by frame
Stills taken at measured moments, each labelled with its time. Claude gets the same sheets over MCP.
Plate 03
The hook, frame by frame (first 3 seconds)
| Time | Picture | On-screen text | Words and sound | What it does |
|---|---|---|---|---|
| 0.00–0.50 | Small rounded control in a dark, soft green field | No readable headline | Product introduction begins | Withholds the product action |
| 0.50–1.00 | Badge and letters gather inside the control | Tiny mark only | Name phrase continues | Makes the object identifiable |
| 1.10–2.25 | Hard cut to an oversized cropped control and circular action glyph; glints and streaks | Symbol rather than sentence | Function phrase resolves | Enlarges the same visual idea |
| 2.37–3.00 | Hard cut to pale interface; first UI labels resolve | Interface heading and first field | Instruction starts | Converts intrigue to proof |
Hook formula (inferred): small {{FEATURE}} control → giant action glyph → real {{PRODUCT}} interface.
Why it holds (inferred): The scale change at the first cut is the visual hook. The second cut pays it off with a usable interface before the viewer has to decode a long claim.
Plate 04
Structure (beat sheet)
| # | Time (s) | Shots | Beat | What happens | Technique |
|---|---|---|---|---|---|
| 1 | 0.00–1.10 | 1 | Intrigue | A small control gains its badge. | Central negative space and a restrained scale-down. |
| 2 | 1.10–2.37 | 2 | Symbol reveal | The control becomes a cropped action emblem. | Cut, lateral element travel, glints and speed lines. |
| 3 | 2.37–6.10 | 3 | Action proof | A genuine {{PRODUCT}} workflow moves from options to a prominent outcome. | Pale UI, two internal reframes, number build and field detail. |
| 4 | 6.10–9.43 | 4 | Shareable result | The output becomes one prominent horizontal bar with compact actions. | Dark result card, check, pill, small icons. |
| 5 | 9.43–14.30 | 5 | Benefits | Several short verified benefits cycle in one central sentence. | Word substitution in a bright pill, supporting icons. |
| 6 | 14.30–17.47 | 6 | Brand close | The mark resolves on a pale field. | Letter build and soft peripheral arcs. |
Retention map (inferred): re-hooks at the first two cuts and the two shot 3 reframes · payoff in shots 3–4 · brand close in shot 6 · hard stop, not a fade.
At a glance
- Shots: 6 shots · 5 transitions · 17.47 s = 524 frames at 30 fps · shot length median 3.23 s (shortest 1.10, longest 4.87)
For agents: Shots
The measured data and build specs agents work from. Over MCP they get it all, with the full timeline as JSON.
Shots (measured)
6 shots · 5 transitions · 17.47 s = 524 frames at 30 fps · shot length median 3.23 s (shortest 1.10, longest 4.87). Frames are at 30 fps, first and last inclusive: a shot "33–70 · 38 f" is a Remotion <Sequence from={33} durationInFrames={38}>; at another frame rate, use the seconds.
| # | in–out (s) | frames @30 (first–last · count) | dur (s) | transition in | changes inside | scales (inferred) |
|---|---|---|---|---|---|---|
| 1 | 0.00–1.10 | 0–32 · 33 f | 1.10 | start | – | fixed |
| 2 | 1.10–2.37 | 33–70 · 38 f | 1.27 | cut | – | fixed |
| 3 | 2.37–6.10 | 71–182 · 112 f | 3.73 | cut | f87 reframe · f119 reframe | scales |
| 4 | 6.10–9.43 | 183–282 · 100 f | 3.33 | cut | – | scales |
| 5 | 9.43–14.30 | 283–428 · 146 f | 4.87 | cut | – | scales |
| 6 | 14.30–17.43 | 429–522 · 94 f | 3.13 | cut | – | fixed |
scales: fixed = keep this shot's length when the film gets longer or shorter · scales = stretch or shrink it with the length · optional = drop it for the 15 s cut.
Measurement notes: tempo low confidence (0.24): no steady pulse; beats are given but should not drive edits · key low confidence (0.05): Bb major vs Bb minor · cue sheet keeps 17 of 51 sound events (all near cuts, then the strongest)
Frame sheets (measured): shots, one labelled frame per shot (labels S<n> m:ss.s; + = just after a change inside the shot) · the full-length timeline, the whole film at fixed steps (labels S<n> m:ss.s f<frame>), 2 pages · close-up strips, 14 frames around each cut and change: f33 cut, f71 cut, f87 reframe, f119 reframe, f183 cut, f283 cut, f429 cut (sheet "transitions", 3 pages; labels S<n> m:ss.sss f<frame>): call get_frames('REF-3597'), or see them on the film page (Pro, or free films).
Plate 05
Shot grammar
Mix (inferred): two abstract control shots, one bright workflow, one dark result, one kinetic type benefit card, and one pale close.
Rhythm: The first two shots are shortest; the benefit shot is longest. All five measured boundaries are hard cuts, and only shot 3 has measured internal reframes.
Rules this editor follows (inferred):
- Keep the camera locked for the control, result and claim cards; animate their elements inside the frame.
- Reserve the most elaborate camera path for shot 3, where a viewer needs a guided tour of the UI.
- Use abrupt dark–pale field changes at shot boundaries rather than transition effects.
- Render moving art on twos at 30 fps; keep text rasterization sharp between held pictures.
At a glance
- Biggest moves: shot 3: complex over 3.73 s, ease-out.
- Transitions: 5 transitions: 5 cuts
For agents: Camera and motion · Transitions
The measured data and build specs agents work from. Over MCP they get it all, with the full timeline as JSON.
Camera and motion (measured)
Per shot, measured on the frames. "Camera move" names the camera's move; the numbers are the image's motion: pan in % of frame width (x) or height (y) per second, +x = content moves right (so a pan left), +y = content moves down; zoom per second > 1 = content grows (push in). "Over the shot" is the total, with px at 1920×1080. Speed is the move through the shot, about one character per 0.5 s (▁ still → █ its peak), then the peak in % of width per second. Cadence: "ones" = a new picture every frame, "twos" = each picture held two frames. Blur is relative to this film (0 = its sharpest shots, 1 = its blurriest); motion = share of the frame changing, 0–1. "?" = confidence under 0.5: a hint, check the sheets. The labels describe how the image moves, not where a 3D camera went: an object flying toward a still camera can read as a push in.
In 5 of 6 shots the camera holds still and something inside the frame moves: see Element motion right under this table.
| # | camera move | pan x · y (%/s) | zoom (/s) | over the shot | ease | speed · peak | cadence | blur | motion | conf |
|---|---|---|---|---|---|---|---|---|---|---|
| 1 | static? · element moves ↓ | +0.0 · +0.0 | ×1.000 | none | hold | ▁▁▁▁ | ~25 fps | 0.76 | 0.03 | 0.37 |
| 2 | static? · element moves ↓ | +0.0 · +0.0 | ×1.000 | none | hold | ▁▁▁▁ | twos | 0.65 | 0.29 | 0.36 |
| 3 | complex (shake 3.5%/s) | −2.4 · −8.0 | ×0.999 | x −9.1% (−175 px) · y −30.0% (−324 px) · roll −6.2° · jump at f87: ×2.45, x +49.8%, y +60.3% · jump at f119: ×0.74, x −51.3%, y +4.0% | ease-out | ▄▁▂▂▆▁▁ · 60%/s | twos | 0.60 | 0.16 | 0.65 |
| ↳ 2.57–2.83 s: complex | +12.5 · +8.8 | ×1.216 | x +3.3% (+64 px) · y +2.3% (+25 px) · ×1.05 scale · roll −5.9° | linear | ||||||
| ↳ 2.90–3.43 s: push in | −0.7 · −0.7 | ×1.077 | ×1.04 scale | ease-out | ||||||
| ↳ 3.43–3.90 s: pan right | −12.8 · −0.9 | ×1.111 | x −6.0% (−115 px) · ×1.05 scale | ease-in | ||||||
| ↳ 3.97–4.37 s: pan right | −13.1 · −1.4 | ×0.960 | x −5.2% (−100 px) · y −0.6% (−6 px) · ×0.98 scale | ease-out | ||||||
| ↳ 4.37–5.23 s: tilt down | −1.0 · −34.1 | ×0.950 | x −0.9% (−17 px) · y −29.6% (−320 px) · ×0.96 scale | ease-in-out | ||||||
| ↳ 5.23–6.03 s: pull out | +0.1 · −1.7 | ×0.901 | y −1.3% (−14 px) · ×0.92 scale | ease-in | ||||||
| 4 | static? · element moves ↓ | +0.0 · +0.0 | ×1.000 | none | hold | ▁▁▁▁▁▁▁ | twos | 0.42 | 0.23 | 0.46 |
| 5 | static? · element moves ↓ | +0.0 · +0.0 | ×1.000 | none | hold | ▁▁▁▁▁▁▁▁▁▁ | twos | 0.26 | 0.16 | 0.35 |
| 6 | static · element moves ↓ | +0.0 · +0.0 | ×1.000 | none | hold | ▁▁▁▁▁▁ | twos | 0.91 | 0.04 | 0.57 |
Element motion (measured): in these shots the frame holds still and something inside it moves: a card, a UI panel, a product, a word. Region = where it moves (x · y · w · h % of the frame); numbers as above, for the moving region; "moving" = share of the shot in motion; ↳ = the move changes direction.
| # | region x·y·w·h % | element move | x · y (%/s) | zoom (/s) | total while moving | ease | speed · peak | moving | conf |
|---|---|---|---|---|---|---|---|---|---|
| 1 | 40 · 43 · 19 · 11 → 40 · 44 · 19 · 10 | scale down | +0.2 · +0.1 | ×0.846 | ×0.90 scale in 0.6 s | ease-out | ▆▃▁▁ · 22%/s | 0.55 | 0.53 |
| ↳ 0.00–0.60 s: scale down | +0.2 · +0.1 | ×0.846 | ×0.90 scale | ease-out | |||||
| ↳ 0.63–1.07 s: static | +0.0 · +0.0 | ×1.000 | none | hold | |||||
| 2 | 36 · 39 · 13 · 22 → 6 · 36 · 54 · 28 | slide right | +18.1 · +0.1 | ×1.034 | x +21.7% (+416 px) · ×1.04 scale in 1.2 s | ease-out | ▆▂▁▃ · 62%/s | 0.95 | 0.65 |
| ↳ 1.10–2.30 s: slide right | +18.1 · +0.1 | ×1.034 | x +21.7% (+416 px) · ×1.04 scale | ease-out | |||||
| 4 | 25 · 34 · 44 · 16 → 36 · 24 · 31 · 59 | complex | +0.1 · −0.5 | ×0.981 | y −1.6% (−17 px) · ×0.94 scale · roll −2.1° in 3.3 s | ease-in | ▃▂▂▂▂▁▅ · 24%/s | 0.98 | 0.76 |
| ↳ 6.10–6.37 s: complex | +0.0 · −11.9 | ×0.863 | y −3.2% (−34 px) · ×0.96 scale | linear | |||||
| ↳ 6.37–8.97 s: scale down | +0.2 · +0.6 | ×0.954 | y +1.5% (+16 px) · ×0.88 scale · roll −2.1° | irregular | |||||
| ↳ 8.97–9.37 s: scale up | +0.0 · +0.1 | ×1.281 | ×1.10 scale | ease-in | |||||
| 5 | 18 · 3 · 76 · 72 → 30 · 47 · 41 · 6 | complex? | +0.1 · −0.1 | ×0.977 | y −0.5% (−6 px) · ×0.91 scale · roll +3.7° in 4.1 s | ease-in | ▂▃▁▁▂▁▂▂▃▅ · 50%/s | 0.84 | 0.48 |
| ↳ 9.43–10.17 s: static | +0.0 · +0.0 | ×1.000 | none | hold | |||||
| ↳ 10.17–10.43 s: rotate | +0.0 · +0.1 | ×0.988 | roll +4.3° | ease-out | |||||
| ↳ 10.43–11.23 s: scale down | −0.2 · −0.5 | ×0.944 | ×0.95 scale · roll −0.7° | irregular | |||||
| ↳ 11.23–13.70 s: scale up | +0.3 · −0.1 | ×1.085 | x +0.7% (+13 px) · ×1.22 scale | irregular | |||||
| ↳ 13.70–14.23 s: scale down | −0.7 · +0.1 | ×0.631 | ×0.78 scale | ease-in | |||||
| 6 | 46 · 47 · 17 · 7 → 40 · 48 · 19 · 6 | complex | −0.9 · +2.4 | ×0.923 | x −1.5% (−29 px) · y +4.0% (+43 px) · ×0.88 scale · roll +5.0° in 1.7 s | irregular | ▅▂▆█▅▁ · 28%/s | 0.53 | 0.50 |
| ↳ 14.50–15.37 s: scale down | −1.8 · +3.1 | ×0.869 | x −1.5% (−30 px) · y +2.7% (+29 px) · ×0.89 scale · roll −1.8° | ease-out | |||||
| ↳ 16.30–17.10 s: rotate | +0.0 · +1.6 | ×0.986 | y +1.2% (+14 px) · ×0.99 scale · roll +6.8° | ease-out | |||||
| ↳ 17.10–17.37 s: static | +0.0 · +0.0 | ×1.000 | none | hold |
Focus (measured): shot 1: sharp inside 0 · 0 · 100 · 100, no defocus (deep focus) · shot 2: sharp inside 0 · 0 · 100 · 100, no defocus (deep focus) · shot 3: sharp inside 0 · 0 · 100 · 100, no defocus (deep focus) · shot 4: sharp inside 8 · 0 · 83 · 100, no defocus (deep focus) · shot 5: sharp inside 0 · 0 · 100 · 100, no defocus (deep focus) · shot 6: sharp inside 0 · 43 · 33 · 57, about 6 px blur outside at 1080p. Box = x · y · w · h % of the frame. In 2D, blur the layers outside the box by that many px; in 3D, set the focus distance on the box and open the aperture until the background blur matches.
Biggest moves: shot 3: complex over 3.73 s, ease-out. Locked-off shots: 1 of 6; 4 more could not be tracked (shown as "static?" or "not measured": check the sheets). Animation cadence: each picture held for two frames (on twos): 15.3 unique frames per second of 30 while things move (held-frame share 0.49, 381 moving frames). Match it, or the motion will feel smoother or choppier than the reference.
Transitions (measured)
5 transitions: 5 cuts. Frames are at 30 fps; a transition of n frames lasts n ÷ 30 s. Hard cuts are reliable; the blur types (whip versus zoom) are the weakest labels, so read their confidence and check the sheets.
| into # | at (s) | frame @30 | type | length | conf |
|---|---|---|---|---|---|
| 2 | 1.10 | 33 | cut | 0 f | 1.00 |
| 3 | 2.37 | 71 | cut | 0 f | 1.00 |
| 4 | 6.10 | 183 | cut | 0 f | 1.00 |
| 5 | 9.43 | 283 | cut | 0 f | 1.00 |
| 6 | 14.30 | 429 | cut | 0 f | 1.00 |
Changes inside shots (the picture changes without a cut: a reframe, a hand-off behind black, a mask):
| shot | at (s) | frame @30 | change |
|---|---|---|---|
| 3 | 2.90 | 87 | reframe: jump x2.45 |
| 3 | 3.97 | 119 | reframe: jump x0.74 |
What each shot shows (inferred from the sheets)
| # | Type | Framing | What's on screen | Text / overlay |
|---|---|---|---|---|
| 1 | Abstract product control | Small, centered | Luminous pill with badge and glint | Tiny mark |
| 2 | Symbol macro | Cropped left, broad right field | Thick letterform, round action glyph, star flares | Glyph only |
| 3 | UI tour | Full UI, then magnified regions | Input, selector, amount, action button | Real UI labels and number |
| 4 | Result graphic | Centered | Check, horizontal output bar, action row | Short headline, link text |
| 5 | Kinetic type | Centered | Sentence with changing pill word and motif icons | Benefits only |
| 6 | End card | Centered | Letter build, mark, peripheral arcs | Brand close; add CTA text in adaptation |
Plate 06
Visual style guide
- Look (inferred): A deep brand background, glowing accent control, pale functional interface, then dark result/benefit cards and a pale end card. The reference uses charcoal green and lime; translate their roles through
{{BRAND_BG}}and{{BRAND_ACCENTS}}. - Graphics (inferred): Rounded pills, hard white glints, thin speed lines, outline motifs, controlled bloom and peripheral blur. Keep UI surfaces crisp.
- Transitions: Five instantaneous cuts; the two inside-shot changes are reframes.
- Branding (inferred): Put
{{LOGO}}at the pale close and{{CTA_URL}}as readable text beneath it. The reference closes with its mark and year, so this adds a useful call to action to the new version.
At a glance
- Type scale (cap px): 167 · 76–82 · 58–60 · 45–49 · 32–37 · 21 · 16–17 (7 levels) among the text above.
- Phone minimum: cap height ≥ 2% of frame width = 38 px at 1920×1080
- Whole film (time-weighted):
#0C110634% ·#F5FDF131% ·#1C2D1012% ·#CAD4C05% ·#2E53185% ·#B2F2753%. - Curve facts: average 0.48 · darkest 0.08 at 14.2 s · brightest 0.98 at 2.5 s · sudden changes at 2.50 s (brighter by 0.64), 6.25 s (darker by 0.77), 14.50 s (brighter by 0.81).
For agents: Type · Type spec · Palette by shot · Brightness curve · Layout boxes · Material card
The measured data and build specs agents work from. Over MCP they get it all, with the full timeline as JSON.
Type (measured)
Sizes are cap height (the height of a capital letter) in px at the 1080p deliverable, 1920×1080. Font size ≈ cap ÷ 0.71 for a typical sans (Inter 0.73, Geist 0.71, SF Pro 0.70, Instrument Sans 0.72): check your own font's cap-height ratio. Cap heights are estimated from text-recognition boxes (median error about 11% on real text; text under about 13 px at 1080p and non-Latin scripts are not read). Box = x · y · w · h as % of the frame, from the top-left.
| text | shot | on screen (s) | cap px | ≈ font px | cap % of height | box x·y·w·h % | position |
|---|---|---|---|---|---|---|---|
| "Create payment link" | 3 | 2.5–4.5 | 82 | 115 | 7.6 | 4 · 10 · 43 · 11 | left, top (inside 5% of the edge) |
| "Product or service" | 3 | 2.8–3.8 | 58 | 82 | 5.4 | 36 · 70 · 33 · 6 | centre, lower third |
| "43.74 → 213.00 (counting)" | 3 | 4.0–4.8 | 167 | 235 | 15.5 | 45 · 44 · 28 · 16 | centre, middle |
| "Bank transfer and 1 more" | 3 | 5.0–6.0 | 45 | 63 | 4.2 | 16 · 18 · 35 · 6 | left, top |
| "Payment methods" | 3 | 5.0–6.0 | 32 | 45 | 3.0 | 16 · 10 · 22 · 6 | left, top |
| "Boom" | 3 | 5.3–6.0 | 49 | 69 | 4.5 | 43 · 55 · 9 · 5 | centre, middle |
| "SHARE YOUR LINK" | 4 | 6.3–9.3 | 60 | 85 | 5.6 | 35 · 39 · 32 · 6 | centre, middle |
| "Copy" | 4 | 6.3–9.3 | 17 | 24 | 1.6 | 36 · 76 · 3 · 2 | centre, lower third |
| "https://wise.com/pay/r/OAFOtpw3VCI1XX8" | 4 | 6.3–6.8 | 37 | 52 | 3.4 | 25 · 53 · 50 · 5 | centre, middle |
| "Give feedback" | 4 | 6.5–9.3 | 21 | 30 | 1.9 | 46 · 85 · 9 · 2 | centre, bottom |
| "Open link" | 4 | 6.5–9.3 | 16 | 23 | 1.5 | 53 · 76 · 6 · 2 | centre, lower third |
| "Create new" | 4 | 6.5–9.3 | 16 | 23 | 1.5 | 62 · 76 · 6 · 2 | right, lower third |
| "O friction" | 4 | 7.8–9.3 | 34 | 48 | 3.1 | 46 · 53 · 10 · 4 | centre, middle |
| "They" | 5 | 9.5–14.3 | 47 | 66 | 4.4 | 31 · 47 · 8 · 7 | left, middle |
| "pay" | 5 | 9.8–10.8 | 32 | 45 | 3.0 | 46 · 48 · 4 · 4 | centre, middle |
| "instantly" | 5 | 10.0–14.3 | 45 | 63 | 4.2 | 54 · 46 · 14 · 7 | centre, middle |
| "borderless" | 5 | 13.5–14.3 | 48 | 68 | 4.4 | 39 · 47 · 15 · 5 | centre, middle |
| "/ WISe" | 6 | 14.5–15.3 | 76 | 107 | 7.0 | 39 · 46 · 24 · 10 | centre, middle |
Plus 5 smaller or briefer text items, cap 13–50 px, mostly labels inside interfaces: all in the timeline JSON.
Type scale (cap px): 167 · 76–82 · 58–60 · 45–49 · 32–37 · 21 · 16–17 (7 levels) among the text above.
Left out: 12 reads that are not clean words or were seen in a single frame ("0.00", "INR", "CAD"…): blurred, moving or partly hidden text the recognizer misread. They stay in the timeline JSON, not in the type scale.
Phone minimum: cap height ≥ 2% of frame width = 38 px at 1920×1080. Why: in a phone feed the film fills the screen width, about 390 pt, and 2% of that is 7.8 pt, the cap height of 11 pt text, Apple's smallest recommended text size. Words the viewer must read go at or above it; smaller text can only be decoration. Below it in the reference: "Copy" (17 px, shot 4), "Give feedback" (21 px, shot 4), "Open link" (16 px, shot 4), "Create new" (16 px, shot 4), "O friction" (34 px, shot 4), "Payment methods" (32 px, shot 3) and 2 more above and 4 of the smaller items. Size these up in your version, or treat them as decoration.
Type spec (inferred)
Assume a 0.71 cap-height-to-font-size ratio for {{BRAND_FONT}}; check the actual font. Inter is a free fallback only. The lower three measured levels contain text too small for required reading; raise essential words to the 38 px cap phone minimum.
| Level | Cap px at 1080p | Implied font px | Weight · case · tracking | Colour pair | Motion |
|---|---|---|---|---|---|
| Numeric hero | 167 | 235 | 750 · digits · −0.04em | Dark ink on pale surface | Count/reveal in 2 f steps, ease-out cubic-bezier(.18,.8,.25,1) |
| Main heading/close | 76–82 | 107–115 | 700 · mixed or upper · −0.035em | Dark ink on pale surface | Letter build over 8–12 f on twos |
| Action heading | 58–60 | 82–85 | 700 · upper or sentence · −0.02em | {{BRAND_ACCENTS}} on {{BRAND_BG}} | Opacity/scale over 8 f, cubic-bezier(.2,.8,.2,1) |
| Claim/body | 45–49 | 63–69 | 600–700 · sentence · −0.02em | Pale text on {{BRAND_BG}} | Replace a pill word over 6 f, hold on twos |
| Supporting label | 32–37 measured; ≥38 if required | 45–52 measured; ≥54 required | 500–650 · sentence · −0.01em | Dark ink on pale UI or pale on dark | Slide/opacity over 6 f; raise readable copy |
| Small action | 21 measured; ≥38 if required | 30 measured; ≥54 required | 500 · sentence · 0em | Pale on dark | Pop over 4 f; otherwise decorative |
| Micro UI | 16–17 measured; ≥38 if required | 23–24 measured; ≥54 required | 500 · sentence · 0em | Accent on dark or dark on pale | Static icon-label detail; do not rely on it to explain the action |
Palette by shot (measured)
Colours measured on the frames, with their share of the frame; luma 0 = black, 1 = white. These are the reference's brand colours: map them onto {{BRAND_BG}} and {{BRAND_ACCENTS}} by role (background, surface, accent), don't reuse them as the format. Neighbouring shots with the same palette share a row.
| # | luma mean · p95 | colours (share of frame) | highlights (bright pixels) |
|---|---|---|---|
| 1–2 | 0.28 · 0.98 | #0E1208 45% · #233716 16% · #B2F275 16% · #3D6E20 12% · #E4EBDD 11% | #F7FDF4 ≈6370 K 94% |
| 3 | 0.96 · 0.99 | #F5FDF1 90% · #B0F96C 4% · #BFC3BA 3% · #66635F 2% · #B3DC88 1% | #F7FFF3 ≈6340 K 74% · #F8FFF3 ≈6300 K 19% · #F7FDF4 ≈6370 K 7% |
| 4–5 | 0.18 · 0.93 | #0C1106 51% · #1C2D10 26% · #2E5318 14% · #519327 6% · #95A78A 3% | #E4F3DA hue 132° ≈6110 K 44% · #8DD552 hue 128° tinted 42% · #98AA8A hue 130° tinted 13% |
| 6 | 0.88 · 0.98 | #ECF7E4 47% · #CAD4C0 20% · #E8FFD5 17% · #A1B091 12% · #6C8257 4% | #F3FFEA hue 132° ≈6180 K 54% · #F0FFE6 hue 132° ≈6110 K 41% · #F4FDEE hue 133° ≈6270 K 5% |
Whole film (time-weighted): #0C1106 34% · #F5FDF1 31% · #1C2D10 12% · #CAD4C0 5% · #2E5318 5% · #B2F275 3%.
Brightness curve (measured)
Mean luma per 1 s, one character each, grouped in tens; p95 = the bright highlights. Scale: ▁ = 0 (black) → █ = 1.0 (white); luma runs 0–1.
0s 10s
mean ▂▃▆███▄▂▂▂ ▂▂▂▂▄▇██
p95 ▆████████▆ ▄▄▅▅▅███
Curve facts: average 0.48 · darkest 0.08 at 14.2 s · brightest 0.98 at 2.5 s · sudden changes at 2.50 s (brighter by 0.64), 6.25 s (darker by 0.77), 14.50 s (brighter by 0.81).
Layout boxes (inferred)
Coordinates are x · y · w · h in percent of the 16:9 frame, from top left. The measured boxes cover recognized text; art may extend beyond them.
| Element | Shots | Box x · y · w · h (%) | Source · confidence | Notes |
|---|---|---|---|---|
| Opening control | 1 | 40 · 43 · 19 · 11 | measured element region · high | Ends near 40 · 44 · 19 · 10 |
| Macro glyph/control | 2 | 36 · 39 · 13 · 22 → 6 · 36 · 54 · 28 | measured element region · high | Layer extends beyond crop |
| UI heading | 3 | 4 · 10 · 43 · 11 | measured text box · high | A crop loses it |
| UI field label | 3 | 36 · 70 · 33 · 6 | measured text box · high | Center lower third |
| Numeric result | 3 | 45 · 44 · 28 · 16 | measured text box · high | Largest text |
| Result heading | 4 | 35 · 39 · 32 · 6 | measured text box · high | Over bar |
| Output URL bar text | 4 | 25 · 53 · 50 · 5 | measured text box · high | Give bar additional padding |
| Benefit phrase | 5 | 31 · 46 · 37 · 7 | measured text boxes · high | Include changing central pill |
| Close mark | 6 | 39 · 46 · 24 · 10 | measured text box · high | Mark/word area from reference |
| New CTA text | 6 | 35 · 62 · 30 · 5 | estimate · low | Proposed adaptation beneath mark |
End card (inferred): Use a pale {{BRAND_BG}} inverse surface. Keep {{LOGO}} in the measured close area, and set {{CTA_URL}} below it at ≥38 px cap. Shot 6 spans frames 429–522; preserve its clear final card and hard stop.
Material card (inferred)
:root {
--brand-bg: {{BRAND_BG}};
--brand-accent: {{BRAND_ACCENTS}};
--surface: color-mix(in srgb, var(--brand-bg) 6%, white);
--ink: color-mix(in srgb, var(--brand-bg) 87%, black);
}
.dark-field { background: radial-gradient(ellipse 65% 85% at 80% 10%, color-mix(in srgb, var(--brand-accent) 43%, transparent), transparent 65%), var(--brand-bg); }
.control { border-radius: 999px; background: var(--brand-accent); border: 2px solid color-mix(in srgb, white 35%, var(--brand-accent)); box-shadow: 0 0 28px 7px color-mix(in srgb, var(--brand-accent) 40%, transparent), inset 0 2px 3px #ffffff88; transform-style: preserve-3d; }
.control-rim { transform: translateZ(-10px) translateY(7px); filter: blur(2px); opacity: .42; }
.ui-panel { background: var(--surface); color: var(--ink); border: 2px solid #0003; border-radius: 22px; }
.glint { filter: drop-shadow(0 0 18px #fff9); }
.end-arcs { filter: blur(6px); opacity: .65; }
Use CSS perspective around 900 px for the macro icon, 10 px layered extrusion, 18–28 px bloom glow and a vignette that darkens the outer 20% by about 35%. The reference behaves as layered 2D motion; no physical 3D render is needed. For the closing blur, use plate 5's shot 6 focus region, 0 · 43 · 33 · 57%, and about 6 px blur outside it; keep {{LOGO}} and CTA sharp as separate overlays.
Plate 07
Voice and delivery
Measured: The v1 transcript has 35 words, about 123 wpm across the film and 175 wpm while speaking. Plate 8 measures speech over 65% of the film; v1's 97% coverage conflicts with that newer measure. Pauses in the v1 facts have a 0.44 s median; pitch movement is animated.
Voice direction (inferred): Use an original adult narrator with crisp, friendly commercial energy. Set short clauses around the shot changes, stress the action and verified outcome, and let the pale close breathe. Captions should follow key nouns and verbs only, since the interface and benefit card already supply visible words.
Plate 08
Sound design
- Music (inferred): Sustained soft synth, low rounded bass and sparse bright ticks beneath the narrator. Keep a brief thin space as the bright UI lands, then let the bed fill out through the benefit run.
- Sound effects (inferred): Tiny tactile clicks may support shot 3 selection and shot 4 result. The cue sheet marks most strong transients as possible voice, so effects should remain lower than consonants and off stressed words.
- Silence and space (inferred): Preserve the phrase breaks; use the cue sheet's frame events to place quiet tonal details rather than trying to force cuts onto a beat.
At a glance
- Speech: words cover 65% of the film (35 words, v1 transcript): narration-led: the words carry it, cut on phrases and keep effects off the stressed words.
- Tempo: no steady pulse. The best guess, 112.35 BPM, has confidence 0.24, too low to build on: time the edit to the cue sheet below, not to a BPM.
- Key: unclear: Bb major or Bb minor (confidence 0.05); pick your own.
- Loudness of the reference (measured): −15.3 LUFS integrated, true peak 0.0 dBTP, range 3.4 LU. That is how this film was mastered, not a target (its peak is above −1 dBTP: don't copy that).
For agents: Sound grid · Original music bed
The measured data and build specs agents work from. Over MCP they get it all, with the full timeline as JSON.
Sound grid (measured)
Speech: words cover 65% of the film (35 words, v1 transcript): narration-led: the words carry it, cut on phrases and keep effects off the stressed words.
Tempo: no steady pulse. The best guess, 112.35 BPM, has confidence 0.24, too low to build on: time the edit to the cue sheet below, not to a BPM.
Key: unclear: Bb major or Bb minor (confidence 0.05); pick your own.
Sections (by energy of the whole mix, voice included):
| section | time (s) | shots | level (RMS) |
|---|---|---|---|
| intro | 0.0–10.0 | 1–5 | −14 dB |
| drop | 10.0–13.5 | 5 | −10 dB |
| outro | 13.5–17.5 | 5–6 | −14 dB |
Energy map (RMS per 1 s, ▁ = −22 dB → █ = −9 dB):
▆▅▁▅▅▅▆▄▅▅ ▇███▄▅▄▂
Cue sheet (17 cues: 1 at a cut, 0 on a beat). "On screen" names the picture event the cue hits within ±3 frames (a cut, a jump, a move starting, a line of text appearing, a brightness step), or says there is none:
| t (s) | frame @30 | shot | kind | strength | on screen (±3 f) | on beat |
|---|---|---|---|---|---|---|
| 0.09 | 3 | 1 | unknown · voice? | 0.94 | element scale down starts (shot 1) | |
| 2.69 | 81 | 3 | hit · voice? | 1.00 | "(*) Limit to 1…" appears | |
| 2.79 | 84 | 3 | tonal · voice? | 1.00 | "(*) Limit to 1…" appears | |
| 2.93 | 88 | 3 | unknown · voice? | 1.00 | jump ×2.45 in shot 3 | |
| 4.71 | 141 | 3 | tonal | 0.79 | no visible event | |
| 6.90 | 207 | 4 | hit · voice? | 0.76 | "Any platform" appears | |
| 7.87 | 236 | 4 | tonal | 0.71 | "O friction" appears | |
| 8.85 | 265 | 4 | tonal | 0.70 | element scale up starts (shot 4) | |
| 9.31 | 279 | 4 | unknown · voice? | 0.72 | "They" appears | |
| 9.45 | 284 | 5 | tonal · voice? | 0.27 | cut into shot 5 | |
| 10.19 | 306 | 5 | unknown · voice? | 1.00 | element rotate starts (shot 5) | |
| 10.96 | 329 | 5 | unknown · voice? | 0.85 | no visible event | |
| 11.10 | 333 | 5 | tonal · voice? | 0.71 | element scale up starts (shot 5) | |
| 11.63 | 349 | 5 | tonal | 0.81 | "no delays" appears | |
| 11.96 | 359 | 5 | tonal · voice? | 0.93 | "no delays" appears | |
| 12.54 | 376 | 5 | unknown · voice? | 0.96 | no visible event | |
| 12.93 | 388 | 5 | tonal · voice? | 0.67 | "secure" appears |
"voice?" = the cue sits on a spoken word (13 of 17): that is the narration, not an effect to copy.
Loudness of the reference (measured): −15.3 LUFS integrated, true peak 0.0 dBTP, range 3.4 LU. That is how this film was mastered, not a target (its peak is above −1 dBTP: don't copy that).
Loudness targets for your version (common practice per platform; the brief overrides them):
| where it plays | integrated | true peak max | note |
|---|---|---|---|
| YouTube | −14 LUFS | −1 dBTP | louder masters are turned down; quieter ones are not turned up |
| X, LinkedIn (this reference) | −14 LUFS | −1 dBTP | no published normalisation: the file plays as mastered |
| TikTok, Reels, Shorts | −14 to −10 LUFS | −1 dBTP | played on phone speakers; short-form is often mastered hotter |
| Website or app (autoplay) | −16 LUFS | −1 dBTP | often starts muted; keep the unmuted level comfortable |
| Broadcast (EBU R128) | −23 LUFS | −1 dBTP | only when the brief asks for it |
Original music bed (inferred)
Choose 110 BPM in D minor as a composing convenience, not an edit grid: the measured 112.35 BPM guess has only 0.24 confidence and no steady pulse. Use a muted sine/sub bass, glassy two-note synth, soft noise breath and occasional short mallet. Shots 1–2 introduce a narrow high motif; shots 3–4 open a brighter chord and reduce bass under UI narration; shot 5 adds a low pulse but leaves the stressed benefit words dry; shot 6 resolves to a sustained tone. Put quiet decorative ticks near frames 3, 81/84, 141, 207, 236 and 265; leave frames 88, 306, 333, 349, 359 and 388 to the voice or duck effects there. Deliver a WAV bed and a separate cue/click stem for editing. Music-model prompt: “Original 17.5-second restrained electronic product bed, 110 BPM D minor feel, soft sub, glass tones, sparse mallet, room for brisk narration, bright final resolve, no borrowed melody.”
Plate 09
Packaging
- Title (inferred):
One {{FEATURE}}, one clear result — {{PRODUCT}}. - Cover (inferred): Tiny accent control centered on
{{BRAND_BG}}, with one off-center glow and no small copy. - Post copy (inferred): One concrete action, one verified benefit, then
{{CTA_URL}}in plain text. - Audience signals: The captured post had 221 views, 7 likes and 1 comment. This sample does not identify a best-performing beat.
Plate 10
Script template
(inferred) Write about 35 original words at roughly 175 wpm while speaking. Place the first noun at shot 1, finish the function phrase in shot 2, explain only what the real UI proves in shot 3, identify the output in shot 4, speak verified benefits in shot 5, and land the brand/CTA in shot 6. Use selective on-screen phrases in sync with spoken nouns; keep every required phrase ≥38 px cap.
[beat 1 · shot 1 · 3 words] Meet {{PRODUCT}} today.
[beat 2 · shot 2 · 3 words] One simple {{FEATURE}}.
[beat 3 · shot 3 · 7 words] Choose a setting, enter the detail, create.
[beat 4 · shot 4 · 7 words] Your result is ready to share anywhere.
[beat 5 · shot 5 · 10 words] State only three verified benefits in short, separate phrases.
[beat 6 · shot 6 · 5 words] {{PRODUCT}}. Find it at {{CTA_URL}}.
Plate 11
Production plan
Two routes (inferred)
Minimum: Claude alone for the coded picture and music. Remotion with CSS 3D draws the control, UI, output bar, benefits and end card in one 1920×1080, 30 fps project; Claude synthesizes a simple original WAV bed in code. It uses perspective transforms, layered extrusion, masked blur and a bloom pass. This reaches the contrast and timing with simpler lighting and less polished sound. A recorded or TTS voice and real {{UI_ASSETS}} are user-supplied inputs, not outputs Claude can truthfully invent.
Full: with the toolkit. Supply genuine {{UI_ASSETS}} or rebuild the real flow in Remotion; export a 1920×1080 PNG sequence with alpha at 30 fps for the workflow. Build all motion, cards and final compositing in Remotion, passing camera keyframes in JSON at 30 fps. Record an original voice or use ElevenLabs, handing over a 48 kHz WAV; produce or license an original music WAV plus click/cue stem, then mix against the voice and render 1920×1080 H.264 at 30 fps. The toolkit calls for motion, voice and music, so no Blender stage is required.
Asset honesty: Use real product captures or your own UI rebuilt in code. Never generate product UI, screenshots, metrics, reviews or outputs that imply actual use. Here, the field selection, amount and resulting bar must describe an actual {{PRODUCT}} workflow; if it cannot, replace the UI proof with truthful type.
Plate 12
Prompts
Script prompt (inferred)
Write 33–37 original spoken words for {{PRODUCT}} at about 175 wpm during speech. Use the six numbered beats in plate 4 and explain only the action shown by genuine {{UI_ASSETS}}. Short phrases should land at the measured shot boundaries, and the benefit phrases must be verifiable. Return voice lines and selective on-screen words separately. Keep necessary on-screen text at 38 px cap or larger. End on {{LOGO}} and {{CTA_URL}} as text. Do not use the reference's claims, brand marks or wording.
Caption spec (inferred): Put only key action/result/benefit phrases on screen. Render through {{BRAND_FONT}}, use the type levels in plate 6, and keep captions out of real UI fields.
Music prompt (inferred): Original restrained electronic bed as specified in plate 8; deliver separate 48 kHz WAV music and cue stems so voice remains clear.
Plate 13
Edit recipe
How it's built (inferred)
Signature move: shot 3's guided UI reframe. Assemble a truthful, oversized UI as a flat source panel, with independent text/number layers above it. At frame 71 hard-cut from the icon to the pale UI. A short settle runs through frames 77–85 with about ×1.05 scale and small roll; at frame 87 jump to the measured ×2.45 reframe, x +49.8%, y +60.3%. Do this as a direct transform switch on a held pair of frames, with a 2-frame directional-blur bridge only if the jump feels too brittle; do not turn it into another cut. From frames 87–118, follow the measured push and rightward pan segments. At frame 119 jump to ×0.74, x −51.3%, y +4.0%, then animate the amount and field through the measured pan/tilt and pull-out segments. Use cubic-bezier(.18,.8,.25,1) for ease-out, (.55,.05,.8,.55) for ease-in and (.42,0,.58,1) for ease-in-out. Quantize transforms to twos; sample internally at 60 fps and composite a 180° shutter blur only on fast moving layers. Keep type as a sharp top layer. The gotcha is blurred, illegible UI from scaling a 1080p screenshot: render or capture {{UI_ASSETS}} at 4K before the ×2.45 reframe.
Other element moves. In shot 1, scale the opening control to ×0.90 over frames 0–17, then hold it to frame 32. At frame 33 hard-cut to shot 2: slide the enlarged control by the measured +21.7% frame width across frames 33–69 with ×1.04 scale; place glyph and glints in separate layers so the macro stays crisp. At frame 183 hard-cut to shot 4; build the result card from back to front: field, check, bar, copy, icon row, glints. Its element first eases smaller, then scales up across the final measured segment (plate 5). At frame 283 hard-cut to shot 5; swap only the highlighted word and motif icons while the sentence anchor holds. The low-confidence movement estimate for shot 5 is a hint: the sheets show central word replacement, not a traveling camera. At frame 429 hard-cut to the pale shot 6; build letters over roughly frames 429–436, assemble {{LOGO}}, add the peripheral arcs, and leave a sharp {{CTA_URL}} text line below. Plate 5 measures the end element changing scale/roll and settling by its final static segment. The sheet around 15.8 s suggests a logo-to-year replacement inside shot 6; the measured transition table lists no internal change there, so treat it as layer animation within shot 6, not a cut. No end fade is measured.
Cut and brightness handling. Keep the hard cuts at frames 33, 71, 183, 283 and 429 at 0 f; do not crossfade. The frame strips show the pale UI visible on the first frame of shot 3, the result field on the first frame of shot 4, and the pale close on the first frame of shot 6. Match the measured brighter/darker steps at frames 71, 184 and 431 with composition backgrounds; the one-frame lag in the latter two is a rendered brightness settling detail, not a new edit.
Build order
- Load the timeline JSON and lock six shot sequences and all five cut frames.
- Record the script for beats 1–6 and align its clauses before scoring.
- Build the shot 3 UI source and its two reframes; verify real values and legibility.
- Animate the shared control of shots 1–2, then the output and claim layers in shots 4–5.
- Build shot 6's mark and new text CTA; maintain the measured bright close and hard end.
- Add the original bed and low-level cues, duck under speech, export and run plate 14 checks.
Plate 14
QA checklist
- Six shots and five cuts match plate 4 at frames 33, 71, 183, 283 and 429, within ±1 frame.
- Shot 3's internal reframes are at frames 87 and 119, with the measured scales in plate 5; no extra shot boundary appears.
- Moving art updates on twos at 30 fps, while essential UI text remains sharp.
- Every necessary on-screen word has cap height ≥38 px at 1920×1080; adapt to the plate 15 aspect minima.
- The dark/pale changes follow plate 6, including the bright close and no fade to black.
- Narration totals about 35 words, with phrases aligned to the six beats; effects stay clear of the stressed words listed in plate 8.
- X/LinkedIn export measures about −14 LUFS integrated and ≤−1 dBTP; inspect the cue frames in plate 8 against the voice.
-
{{UI_ASSETS}}proves the stated action and the amount/result is authentic;{{LOGO}}and{{CTA_URL}}are readable text/art, not a QR code.
Plate 15
Make it yours
Brand slots
| Slot | Replaces in the reference | Notes |
|---|---|---|
{{PRODUCT}} | Named payment service | Use actual product name and true action |
{{BRAND_FONT}} | Reference sans type | Supply licensed brand font; Inter only fallback |
{{BRAND_BG}} | Dark green base and pale inverse | Use your own dark/pale pair |
{{BRAND_ACCENTS}} | Lime glow and controls | Supply distinct accent palette |
{{LOGO}} | Reference symbol/wordmark | Use real mark asset |
{{CTA_URL}} | Reference destination link | Put as plain readable text at close |
{{FEATURE}} | Payment-link action | One concrete product operation |
{{UI_ASSETS}} | Payment creation interface | Real capture or faithful coded UI |
What this film avoids (inferred): no on-camera host, stock footage, long feature list, full-frame caption track, decorative app chrome, QR code, app-store badges or invented user outcomes.
Brand-distance warning (inferred): A lime control, deep forest gradient, chain glyph and similar payment UI together would read as the source brand. Change the action symbol and accent geometry while keeping the small-to-macro-to-real-UI progression.
Adapt the aspect (inferred)
- 9:16: Re-lay out rather than center-crop: stack the UI heading above the field and number, center the output bar and icons, put benefit text in a vertical safe column, and keep
{{LOGO}}/CTA away from top and bottom platform UI. Essential type must reach the measured 22 px cap minimum at 1080×1920; use larger sizes for the output bar. - 1:1: Center-crop the dark control shots, then move the lost shot 2 element, UI heading and payment labels inside the square. Re-center the result bar and place
{{LOGO}}/CTA within platform UI safe margins; keep necessary cap height ≥22 px at 1080×1080.
Adapt the length (inferred)
- 15 s: Keep beats 1–4 and 6, compress the scalable UI/result and benefit wording, and preserve shot 3's signature reframes. Drop only optional benefit material if a faster version needs it.
- 30 s: Keep all six beats; spend added time on one genuine extra step inside beat 3 and one verified use case after beat 4, while preserving the opening and close cadence.
- 60 s: Add new demonstrated actions between beats 3 and 4 and new evidence after beat 5; record new narration clauses for them. Do not stretch the hook, two internal jumps or end-card hold into dead time.
The creator's signature (don't copy): The reference's exact mark, lime/forest pairing, payment-specific glyph, slogans, UI values and music.
The transferable format (do copy): Small luminous control → oversized action symbol → guided real UI → output card → short benefit substitutions → clear mark and text CTA, paced to narration.
Source: https://x.com/MoveStudioin/status/2108446908528435257 · measured with dissect 1.1 and timeline v2 on 2026-10-10 · (measured) = observed · (inferred) = construction reading
For agents: Aspect conversions · Length cuts
The measured data and build specs agents work from. Over MCP they get it all, with the full timeline as JSON.
Aspect conversions (computed from the measured boxes)
Aspect conversions (computed from the measured boxes): a centre crop of the reference frame, checked against its text boxes and moving elements.
| to | deliver at | a centre crop keeps | measured boxes kept | boxes a crop loses | phone minimum | so |
|---|---|---|---|---|---|---|
| 9:16 | 1080×1920 | middle 31.6% of the width (cut 34.2% each side) | 16 of 28 | "Create payment link", "(*) Limit to 1…", "Product or service", "43.74 → 213.00 (countin…" … | 22 px cap | re-lay out: a crop loses too much |
| 1:1 | 1080×1080 | middle 56.2% of the width (cut 21.9% each side) | 24 of 28 | "Create payment link", "Payment methods", "Bank transfer and 1…", moving element, shot 2 | 22 px cap | centre crop, then move the lost boxes inside |
Length cuts (computed from the scales flags)
Length cuts (computed from the scales flags): frames per shot at 30 fps; fixed shots keep their length, optional shots go first when the cut is shorter, the scaling shots share what is left. Snap each cut to the nearest beat when plate 8 has a steady pulse.
| # | flag | reference (f @30) | 15 s cut | 30 s cut | 60 s cut |
|---|---|---|---|---|---|
| 1 | fixed | 33 | 33 | 33 | 33 |
| 2 | fixed | 38 | 38 | 38 | 38 |
| 3 | scales | 112 | 89 | 179 | 179 |
| 4 | scales | 100 | 80 | 160 | 160 |
| 5 | scales | 146 | 116 | 234 | 234 |
| 6 | fixed | 94 | 94 | 94 | 94 |
| total | 523 f · 17.4 s | 450 f · 15.0 s | 738 f · 24.6 s + 5.4 s new beats | 738 f · 24.6 s + 35.4 s new beats |
30 s: stretching tops out at ×1.6 (24.6 s); add 5.4 s of new beats (more of the scaling beats' pattern with new content), never a longer hold on the fixed shots · 60 s: stretching tops out at ×1.6 (24.6 s); add 35.4 s of new beats (more of the scaling beats' pattern with new content), never a longer hold on the fixed shots.
Recipe
One prompt that makes a film like this with Claude. Use the method; make the footage, words and brand your own.
Make a 17.5 s 16:9 film for {{PRODUCT}} in the format of REF-3597 (glowing control to product flow). Brand: font {{BRAND_FONT}}, background {{BRAND_BG}}, accents {{BRAND_ACCENTS}}, logo {{LOGO}}, call to action {{CTA_URL}}. Feature: {{FEATURE}}; UI: {{UI_ASSETS}}. Load get_blueprint("REF-3597", format: "json") first; follow its shot frames, camera numbers, type boxes and cues. Narration leads: write about 35 original words at 175 wpm while speaking. Put the name in shots 1–2, action in shot 3, result in shot 4, verified benefits in shot 5, and close in shot 6. Captions follow keywords. Beat 1, 0–1.10 s: tiny luminous control; beat 2, 1.10–2.37 s: giant action glyph; beat 3, 2.37–6.10 s: real UI; beat 4, 6.10–9.43 s: output bar; beat 5, 9.43–14.30 s: changing benefit words; beat 6: pale brand close. Reframe shot 3 at frames 87 (×2.45) and 119 (×0.74). Use Remotion for motion and UI, supplied voice, and original music; Minimum is Remotion with CSS 3D and code-synthesized music. Hit JSON cues without masking stressed words. Render 1920×1080 at 30 fps, H.264 MP4; essential type ≥38 px cap, X master −14 LUFS and ≤−1 dBTP. End on {{LOGO}} plus {{CTA_URL}} as text, without QR codes or store badges. Use real {{PRODUCT}} captures or rebuild its true UI in code; never generate UI, fake screenshots or fake results. Never copy reference colors, font, logo, mascot, slogans or music.Films like this
Tagged product launchmotion graphicsfintechdark uineon greeninterface animationvoiceoverhorizontal


