등산배낭 22리터 백팩

지마켓 실제 상품 — https://item.gmarket.co.kr/Item?goodscode=1729229868

골격 기본 register 를 그대로 두고 샷만 얹었습니다.

연출 반영됨 요구한 카메라 3대가 샷 목록으로 프롬프트에 실렸습니다

요청한 페르소나 사진이 영상 생성 호출에 그대로 실렸습니다.

STYLE:
Vertical 9:16, photoreal phone footage — eye-level, locked-off camera, natural skin and fabric texture, available light only. No on-screen text, no graphics of any kind.

Pore-level skin realism — visible pores, fine vellus hair, natural asymmetry in the face and hands. Skin stays unsmoothed and unretouched; part of the face is allowed to fall into shadow.
Matte, non-reflective surfaces. Lived-in, worn materials with real wear on them. No plastic sheen, no digital gloss.
Hair keeps individual strands and stray flyaways rather than a moulded shape.
This is a real person filmed on a phone, not a rendered portrait.

REFERENCES:
@Image1 — the person: a man with a muscular build, dark medium-length hair, calm and clean-cut demeanor. 100% match.
@Image2 — the product: a slim, slightly tapered cylindrical hiking backpack in khaki green and grey, with adjustable shoulder/waist straps, double zippers on the main compartment, mesh side pockets for water bottles, and "HUMONT" logo with "Azalea 22L" text printed vertically on the front. 100% match; every word, logo and label exactly as the reference.
@Image3 — the person's face close-up: same person as @Image1, appearance only.
@Image4, @Image5, @Image6 — further angles of the same product: appearance only.

Scope — @Image1 carries appearance AND performance: it is also how this person holds themselves. @Image2 carries appearance ONLY — no pose, no motion, no performance. @Image3 and beyond (further angles of the same product, or this person's face close-up) carry appearance only. No reference contributes a scene, a camera move or a spoken line, and where a reference and this prompt disagree about what happens, this prompt decides.

Real-world size — about 50 cm tall and 28 cm across at its widest, 22L capacity — roughly three times the length of an adult forearm from the top strap to the bottom, and about two open-hand-widths across. It must never look larger than the man's torso.

LOCATION:
an open mountain ridge trail with a dirt-and-rock path, low shrubs, distant layered peaks, and an open sky visible behind the speaker.

FIRST FRAME:
0.0s — an aerial drone rising high over the ridge until the whole mountain trail and layered peaks are visible below, the person centred at medium distance, already the backpack already worn on both shoulders with the waist strap fastened, sitting settled and upright against his back, looking straight into the lens mid-thought as if already talking to someone.

ACTION TIMING:
0–3s — Centred medium framing, product already held at chest or face height. He opens straight into what he wants to say — no preamble, no greeting. Shot as: an aerial drone rising high over the ridge until the whole mountain trail and layered peaks are visible below
3–8s — He raises the product toward the lens until it fills the middle of the frame, turns it once so the front face reads, then performs its one control: reaching one hand back to grip the left shoulder strap's padded webbing and pulling it slightly to show the tension, the strap staying in his fingers before he releases it back against his chest
8–11s — The camera pushes in on the product as rolling both shoulders under the fully-loaded pack as he walks a few steps along the ridge trail, the padded straps flexing against his shoulders without digging in so the result is unmistakable — it stays on it rather than cutting away. Shot as: a second drone tracking alongside the man at a steady distance as he walks the ridge trail with the pack on his back
11–15s — He lowers the product back to chest height, returns to centred medium framing, looks into the lens, and taps the product twice with a fingertip. As he rolls his shoulders and taps the strap, the padding visibly compresses a little under his fingers and springs back, and his shoulders stay loose and unhunched as he walks. He lands the closing line as he does. If anything came off the product at any point — cap, lid, seal, film, wrap, zip pull, band — it is still resting exactly where it was set down, visible in this frame; if the product has no separable part, nothing is set down and nothing is expected here. Shot as: a third drone circling directly overhead in a slow rotation around him as he stands on the ridge

DIALOGUE:
0–3s — "다섯 시간 산행 끝나고 어깨 상태 보여드릴게요."
3–8s — "이 가방 메고 능선 다 탔는데, 어깨 눌리는 느낌이 진짜 하나도 없었어요."
8–11s — "여기 스트랩 보이시죠, 무게가 어깨 위로 안 실려요."
11–15s — "산행 자주 다니면 이건 진지하게 하나 사세요."

PERFORMANCE:
LINE_1 — wants to prove a claim with his own body; rolls his shoulder once, slight exhale, matter-of-fact look to the listener.
LINE_2 — recounts something that genuinely surprised him; brief pause before "진짜 하나도 없었어요", almost a small laugh of disbelief.
LINE_3 — hands over the discovery to the viewer; taps the strap once with two fingers, tilts the pack slightly so the strap reads clearly.
LINE_4 — closes with a straight, useful verdict; steady eye line, one firm nod, no hedge in the voice.
Gaze stays engaged and alive the whole way through, with a natural blink cadence and active forehead and brows. No frozen mask-face, no dead eyes, no held stare parked between lines. Micro-motion continues while the person is not speaking — breathing, a small shift of weight, a glance.

PHYSICS:
- Shell is tightly woven ripstop-style khaki/grey fabric over a padded internal frame, holding its tapered cylinder shape even when moved.
- Shoulder and waist straps are thick foam-padded webbing that compresses slightly under load but springs back, not elastic stretch.
- Double zipper pulls click and drag with slight fabric resistance; mesh side pockets flex and snap back around a water bottle shape.
- NEVER: the backpack must never look flat, empty, or collapse inward when worn — it keeps its full structured volume throughout.
- Scale is fixed: about 50 cm tall and 28 cm across at its widest, 22L capacity — roughly three times the length of an adult forearm from the top strap to the bottom, and about two open-hand-widths across. It must never look larger than the man's torso. No framing, however close, ever makes it read bigger than that

AUDIO:
No music. Wind moving across the open ridge, the soft crunch of boots on dirt and gravel, the light rustle and creak of pack fabric and straps shifting as he moves, and his voice carrying clearly over it as the loudest element.

LOCKS:
① Exactly one product: one unit only, present from the first frame. It is never handed over, unboxed, revealed or duplicated — anything the use moment produces came from it on camera.
② Product surface text lock: print, logo and label exactly as @Image2. Nothing is ever printed onto it.
③ Only the person, the product and what PROPS names are what the shot features; the location's own fixtures and furniture may be present but stay unbranded and out of focus. No other brand's product, packaging, logo or readable mark appears anywhere, and no second person enters.
④ Lens gaze: to-lens throughout; eyes drop to the product only during the control and the use moment.
⑤ Continuity of parts and hands: if anything comes off the product — a cap, a lid, a film, a wrap, a zip pull, a band — it stays visible somewhere in frame for the rest of the clip and is never re-attached, re-sealed or allowed to vanish between shots. Many products have no separable part at all; for those this clause simply does not apply and nothing is expected to be set down. The hands obey the same continuity either way: a control that needs two hands is not performed while one hand is holding something else.

CAMERA:
Opening — an aerial drone rising high over the ridge until the whole mountain trail and layered peaks are visible below. Middle — a second drone tracking alongside the man at a steady distance as he walks the ridge trail with the pack on his back. Ending — a third drone circling directly overhead in a slow rotation around him as he stands on the ridge. These shots make up the clip's coverage — the camera changes between them inside the single take, and each supersedes the register above for its own seconds.

PROPS:
none