Replicating ChillFit's #6 ad, frame for frame — with Roxie in the chair

Overview — one variable, everything else pinned

A perfect replication is only meaningful if we change one thing. The controlled variable is the performer; every other element is either rebuilt to match the original exactly or reused verbatim from the source file.

Source anatomy — the full timeline

Measured with scene detection (threshold sweep at 0.10/0.25) plus frame sampling at the boundaries, and an ElevenLabs transcription of the audio track (language: nld).

Voiceover (full transcript, ends 20.8 s; music continues to 31.4 s)

"Ik ben 65. Ik doe deze work-out elke dag, gewoon 7 minuten per dag en na één week zul je een verschil opmerken. Na twee weken zullen anderen het opmerken en na drie weken zullen al je vrienden vragen hoe je het hebt gedaan. Het geheim? Download deze app."

Before assembly I'll re-run the transcription with --full to get word-level timestamps, and snap every caption in/out to the spoken word — the original's captions track the VO within ~0.1 s.

00.00 – 04.20Act A — the 3×3 grid hook

Nine simultaneous portrait panels, all the same set and framing, each a different chair move. Caption band sits between panel rows 1 and 2. This is the highest-effort shot to fake and the strongest test of character consistency: nine Roxies on screen at once.

So the grid costs only four dedicated extra clips (G1–G4); five panels are centre-crops of the Act B masters at staggered start offsets (and one mirror) so no two panels read as the same footage. Each panel is a 1:1.78 portrait crop scaled to 120×213 in the 360×640 master — small enough to be forgiving of minor artifacts, which is why the grid clips are the right place to absorb the weaker takes.

04.20 – 20.73Act B — the workout montage, five locked shots

One camera setup, five jump cuts. Every clip below is generated at 6 s and trimmed to its slot; generating a hair long gives trim room to pick the cleanest motion cycle. Shared prompt preamble for all five (and G1–G4):

Locked-off tripod shot, vertical 9:16, no camera movement. A fit woman in her
fifties with long wavy blonde hair, wearing a dark sage-green seamless workout
unitard and white crew socks, sits centred on a light wooden spindle-back chair
in front of white paneled closet doors with a black lever handle, light grey
carpet. Soft even daylight. She smiles naturally while exercising. Amateur
iPhone footage look, slight compression, true-to-life motion, no slow motion.

20.73 – 31.44Acts C–D — the app-UI tail

Act C · 28-day challenge cards (20.73 → ~28.3)

Parchment-textured page, header "28-DAAGSE STOELYOGA UITDAGING" in a heavy rounded serif (Cooper Black class), stats bar LENGTE 168CM · GEWICHT 100KG · DOEL 70KG (values red, goal green). Below, a 4×7 sketch calendar of seated exercises. A hand with red nail polish taps day 1 → the DAG-1 card zooms in: a live-action video of a heavier woman in a plum workout set doing seated knee lifts, three Dutch exercise lines, a cyan progress border animating around the card, four sketch thumbnails at the bottom. Back to the calendar, tap → DAG-11 card: the same woman visibly slimmer. The before/after arc lives inside these two card videos.

If rebuilt: the page is an HTML/CSS animation captured at 30 fps (parchment, calendar, zooms, cyan border), the tapping hand is a cut-out PNG animated in CSS, and the two inner card videos are generated — a softened, heavier "day-1 Roxie" variant and today's Roxie for day 11. That heavier variant is an identity edit of the charsheet (Nano Banana) used as the start frame.

Act D · End card (~28.3 → 31.44)

Magenta-to-pink gradient, three fanned iPhone mockups of the ChillFit app (plan list, workout player at 00:08, calories screen), ChillFit icon + script wordmark, "Planner voor thuistraining", App Store / Google Play badges. Contains no human.

Graphics kit — rebuilding every overlay

Every overlay is rebuilt at 720×1280 (2× the source) so the master looks clean, then the delivery encode downsamples to the source's exact 360×640 for honest A/B comparison.

Audio — reused verbatim

The source AAC track is demuxed once (ffmpeg -i source.mp4 -vn -c:a copy tail.m4a) and muxed under the remake untouched: Dutch VO to 20.8 s, music through 31.44 s. Zero re-recording, zero TTS, bit-identical audio — so any perceived difference between the two videos is visual by construction. If this later becomes a real 50Queen ad, the swap is an ElevenLabs English VO on the same word timings; out of scope for the experiment.

Generation plan — models, strategies, pilot

Model & constraints

• Video — MiniMax H3 (minimax_h3, 2K, ~4 cr/s: 24 cr per 6 s clip). Chosen per prior research: Seedance 2.0 reads too polished for UGC-style ads, and H3 was queued as the next candidate. Its param sheet exposes start_image/end_image, image_references and video_references — with one hard constraint: start-frames cannot be combined with reference media. That constraint forces the strategy split below.
• Stills — Nano Banana 2 (2 cr/img) for all start frames and identity edits, anchored on the Roxie charsheet.

Two strategies, raced on the pilot shot (W2)

Pilot = generate W2 both ways (48 cr), judge on: identity match to charsheet, motion match to source (side-by-side), set consistency, UGC texture. The winner generates the remaining 10 clips; the loser stays as the documented fallback per clip.

Start-frame factory (S2 path, also feeds S1's image refs)

1. Master set frame — Nano Banana with two references (Roxie charsheet + source frame at t=19.5, the calmest pose): "this woman seated on this chair in this exact room, hands on knees, smiling at camera." 4 candidates, pick 1.
2. Pose variants — edit the approved master into each clip's starting pose (arms in cactus, leg extended, etc.), one per clip that needs it (~7 edits). Editing the master rather than regenerating keeps the set literally pixel-stable across shots — matching the original's locked camera.
3. "Day-1 Roxie" (only if the tail is rebuilt) — heavier-build identity edit for the DAG-1 card.

Clip manifest

Assembly pipeline

1. Normalize — every generated clip → 720×1280, 30 fps, trimmed to its slot (best motion cycle chosen by eye).
2. Grid — 9 panel crops → xstack layout=3x3 on white, 4.20 s.
3. Body concat — A + W1…W5 cut at exactly 4.20 / 7.17 / 10.73 / 13.73 / 17.60 / 20.73 s.
4. Overlays — watermark PNG → muscle-strip PNGs (per-shot enable windows) → icon bug at 19.0 s → ASS captions burned last so outlines sit above everything.
5. Tail — splice source 20.73–31.44 s (re-encoded to match the master's encode so the joint is invisible), or the rebuilt Act C/D if that option is chosen.
6. Audio — mux the untouched source track; hard-trim master to 31.44 s.
7. Deliverables — remake_720.mp4 (master), remake_360.mp4 (source-matched), sxs_compare.mp4 (original | remake hstacked, shared audio).

Verification — how we score "perfect"

• Side-by-side sync cut — the hstacked comparison video is the primary artifact of the whole experiment; every review happens against it.
• Cut-sheet diff — paired stills at every cut point ±0.1 s, original over remake, one contact sheet.
• Caption timing — every caption in/out within 0.1 s of the original (word-timestamp check, scripted).
• Identity hold — Roxie recognisably the same person across all 11 clips and 9 simultaneous grid panels; the grid frame is the acid test.
• Set hold — chair, doors, handle position, carpet identical across shots (locked-camera illusion preserved).
• Scorecard — per-shot 1–5 on motion / identity / set / texture, logged in the evidence folder with the generation IDs, so the writeup can say precisely where current models succeed and fail.

Cost & approvals

Decision points before any generation runs