← 전체 10종

시나리오 g08 · 검증 질문 — 실내니까 카메라 4대 이상 세팅. 와이드, 미디엄, 스틱 매크로, 그리고

플렌느 실내 디퓨저 200ml

요구한 연출 — 실내니까 카메라 4대 이상 세팅. 와이드, 미디엄, 스틱 매크로, 그리고

사용자가 넣은 입력3개 발화 · 이미지 3장

지마켓 실제 상품 — https://item.gmarket.co.kr/Item?goodscode=1537584297

보낸 말 1

제품 리뷰 영상 만들어줘.

보낸 말 2

플렌느 실내 디퓨저 200ml야. 지마켓 상품 링크는 https://item.gmarket.co.kr/Item?goodscode=1537584297 이고 제품 사진은 이렇게 여러 장이야: https://gdimg.gmarket.co.kr/1537584297/still/400 https://gdimg1.gmarket.co.kr/goods_image2/exlarge_moreimg/153/758/1537584297/1537584297_00.jpg https://gdimg1.gmarket.co.kr/goods_image2/exlarge_moreimg/153/758/1537584297/1537584297_01.jpg https://gdimg1.gmarket.co.kr/goods_image2/exlarge_moreimg/153/758/1537584297/1537584297_02.jpg

보낸 말 3

현관 들어설 때마다 향이 먼저 반겨서 기분이 좋아져. 실내니까 카메라 4대 이상 세팅. 와이드, 미디엄, 스틱 매크로, 그리고 마지막엔 얼굴 클로즈업으로 컷이 딱딱 바뀌게

제품 사진 (첨부)
페르소나 F3
페르소나 F3
대화 전문19턴
사용자

제품 리뷰 영상 만들어줘.

에이전트

저장해두신 제품으로 바로 시작하거나, 제품 페이지 링크를 붙여넣거나, 새 제품으로 시작해보세요!

사용자

플렌느 실내 디퓨저 200ml야. 지마켓 상품 링크는 https://item.gmarket.co.kr/Item?goodscode=1537584297 이고 제품 사진은 이렇게 여러 장이야: https://gdimg.gmarket.co.kr/1537584297/still/400 https://gdimg1.gmarket.co.kr/goods_image2/exlarge_moreimg/153/758/1537584297/1537584297_00.jpg https://gdimg1.gmarket.co.kr/goods_image2/exlarge_moreimg/153/758/1537584297/1537584297_01.jpg https://gdimg1.gmarket.co.kr/goods_image2/exlarge_moreimg/153/758/1537584297/1537584297_02.jpg

에이전트

플렌느 실내 디퓨저 사진 잘 확인했어요! (제품 페이지 링크는 접속이 막혀 있어서 분석은 못 했지만, 보내주신 이미지들로 충분히 파악했어요.) 두 가지만 더 여쭤볼게요 — 1. **어떤 향/컬러로 보여드릴까요?** 사진에 블랙체리(오렌지빛), 화이트머스크, 레드프루트 3가지 향이 보이던데, 대표로 하나 정해주시면 좋을 것 같아요. 2. **실제로 써보시니 뭐가 달라졌어요?** (예: "자기 전에 하나 켜두면 아침까지 향이 은은하게 남아있어요" 같은 느낌으로) 이 부분이 영상 속 리뷰 멘트의 핵심이 돼서 직접 겪은 걸로 알려주시면 좋아요.

사용자

현관 들어설 때마다 향이 먼저 반겨서 기분이 좋아져. 실내니까 카메라 4대 이상 세팅. 와이드, 미디엄, 스틱 매크로, 그리고 마지막엔 얼굴 클로즈업으로 컷이 딱딱 바뀌게

에이전트

딱 하나 안 맞는 것 없이 맞아떨어지네요 — 특별한 비교나 사연 없이 "써보니 좋더라"는 방향으로 갈게요 (현관 들어설 때 향이 반겨준다는 게 그 자체로 충분히 설득력 있어서요). 다음으로 어떤 스타일의 연출로 보여드릴지 볼게요.

사용자

정면 진행 데모로 할게요

에이전트

현관이라는 구체적인 장소는 저희 세팅 카탈로그에 정확히 맞는 항목이 없어서, 카탈로그에서 억지로 고르지 않고 말씀하신 "현관"을 그대로 프롬프트에 반영할게요. 카메라 세팅(와이드/미디엄/스틱 매크로/얼굴 클로즈업)도 그대로 살릴게요. 정리하면: - **방향**: 특별한 사연 없이 "써보니 좋았다" 진솔한 후기 - **연출**: 정면 진행 데모 (제품 들고 말하며 시연 → 추천) - **장소**: 현관 (사용자 지정, 멀티캠 와이드→미디엄→스틱 매크로→얼굴 클로즈업 컷 전환)

에이전트

どちらの方法で登場人物を決めますか?

사용자

제공된 모델 중에서 고를게요

에이전트

모델 프리셋을 열어드렸어요! 마음에 드는 모델을 끌어와서 첨부해주세요.

사용자

이 모델로 할게요

사용자

{"v": 1, "image": "https://assets-static.vcat.ai/public/apps_presets/reference/persona2608/F3_front.jpg", "mimeType": "image/jpeg"}

사용자

{"v": 1, "image": "https://assets-static.vcat.ai/public/apps_presets/reference/persona2608/F3_face.jpg", "mimeType": "image/jpeg"}

에이전트

이 모델로 진행할게요! 20대~30대 초반 여성, 긴 검은 머리, 캐주얼하고 단정한 분위기네요.

에이전트

스토리보드와 대본을 준비했어요. 위 보드에 표시된 자막에 인코딩 문제가 있어 보이니, 실제 대사를 다시 정확히 적어드릴게요: 1. (0-3s) "어? 문 열자마다 이 냄새 뭐야?" 2. (3-8s) "현관에 들어설 때마다 향이 먼저 인사해주니까 기분이 확 좋아져요." 3. (8-11s) "이 스틱들이 계속 향을 밀어 올리는 거 보이시죠?" 4. (11-15s) "이거 하나로 집에 들어오는 순간이 완전히 달라져요." **정리** - 제품: 플렌느 리드 디퓨저 (블랙체리) - 방향: 사연 없이 "써보니 좋았다" 후기 - 등장 인물: 선택하신 모델 (20대~30대 여성) - 장면: 현관, 와이드→미디엄(제품 제시+캡 오픈)→매크로(리드스틱)→얼굴 클로즈업 - 길이: 15초, 세로 9:16, 한국어 내레이션 ⚠️ 영상 생성은 이미지 생성보다 크레딧이 훨씬 많이 소요돼요. 대본이 마음에 드시면 바로 생성할게요.

사용자

이 대본으로 영상 생성해줘

에이전트

이 설정(15초, 세로 9:16, 오디오 포함)으로는 약 880 크레딧이 예상돼요. 바로 생성 진행할게요!

에이전트

15초짜리 리뷰 영상이 완성됐어요! 인스타그램 피드에서 어떻게 보일지 미리보기도 함께 준비했어요. (미리보기는 4:5로 살짝 크롭돼 보이지만, 실제 파일은 세로 9:16 그대로예요.) 혹시 이 제품을 나중에도 바로 쓸 수 있게 기억에 저장해둘까요?

에이전트가 제시한 보기4개 카드
보기
정면 진행 데모
셀피 후기
숨은 사용법 리빌
보기
제공된 모델 중에서 고르기
내 사진 사용하기
인물 설명만 주기
보기
이대로 생성해줘
대넣 다시 쓰자
다른 군람 바꿏을게
보기
플렜느 리드 디퓨저 200ml
작성기가 잡은 카메라4개 샷 · 1라운드

골격 기본 register 를 그대로 두고 샷만 얹었습니다.

openinga wide static shot taking in the whole entryway, the woman and the diffuser bottle both visible as she steps in
middlea medium shot framing her from the waist up as she picks up the bottle and talks about the scent
middlea close macro shot on the reed sticks and the orange liquid inside the glass, catching light on the surface
endinga tight close-up on her face as she reacts and delivers the last line, the cut landing hard on the change of shot
요구한 모델 vs 실제로 나온 인물연출 반영됨

연출 반영됨 요구한 카메라 4대가 샷 4개로 프롬프트에 실렸습니다

지정한 모델 — persona F3
영상에 실제로 나온 인물
첨부한 제품 사진
영상 모델에 실제로 보낸 참조 이미지3장

요청한 페르소나 사진이 영상 생성 호출에 그대로 실렸습니다.

페르소나
에이전트 생성
페르소나
시댄스로 보낸 최종 프롬프트8243자
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 Korean woman in her mid-to-late 20s, long straight black hair, casual and neat everyday style, calm and approachable demeanor. 100% match.
@Image2 — the product: a cylindrical clear glass reed diffuser bottle with a silver cap, filled with orange-tinted liquid, multiple thin reed sticks inserted, label reads 'FLrene BLACK CHERRY PREMIUM FRAGRANCE DIFFUSER'. 100% match; every word, logo and label exactly as the reference.
@Image3 — the person's face close-up: appearance only, no pose or performance beyond what LOCATION/ACTION TIMING specify.

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 carries 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 20 cm tall and 6 cm across, roughly 200 ml — about one and a half times the length of an adult palm, sitting comfortably held in one hand or standing on a table. It must never look larger than her forearm.

LOCATION:
a small home entryway just inside the front door, with a low shoe shelf and a wall hook holding a jacket, the kind of narrow hallway space right where someone steps in from outside.

FIRST FRAME:
0.0s — a wide static shot taking in the whole entryway, the woman and the diffuser bottle both visible as she steps in, the person centred at medium distance, already cradling the glass bottle in one hand near her waist, 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. She opens straight into what she wants to say — no preamble, no greeting. Shot as: a wide static shot taking in the whole entryway, the woman and the diffuser bottle both visible as she steps in
3–8s — She 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: holding the bottle steady in one hand and lifting the silver cap straight off with the other, the cap held pinched between two fingers off to the side Shot as: a medium shot framing her from the waist up as she picks up the bottle and talks about the scent
8–11s — The camera pushes in on the product as tilting the open bottle slightly so the reed sticks catch the light, the sticks staying upright and still as she brings them closer to show the liquid level inside so the result is unmistakable — it stays on it rather than cutting away. Shot as: a close macro shot on the reed sticks and the orange liquid inside the glass, catching light on the surface
11–15s — She lowers the product back to chest height, returns to centred medium framing, looks into the lens, and taps the product twice with a fingertip. the camera catches the orange liquid visibly wicking partway up the pale, damp section of the reed sticks compared to their dry tips, and a faint waft of scent implied by her reaction as she steps closer to the bottle She lands the closing line as she 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 tight close-up on her face as she reacts and delivers the last line, the cut landing hard on the change of shot

DIALOGUE:
0–3s — "어? 문 열자마다 이 냄새 뭐야?"
3–8s — "현관에 들어설 때마다 향이 먼저 인사해주니까 기분이 확 좋아져요."
8–11s — "이 스틱들이 계속 향을 밀어 올리는 거 보이시죠?"
11–15s — "이거 하나로 집에 들어오는 순간이 완전히 달라져요."

PERFORMANCE:
LINE_1 — genuine surprise at the scent hitting her the moment she steps in; she pauses mid-step, eyebrows lifting, nose catching the air before she even looks at the bottle.
LINE_2 — warmth breaking into a small, real smile as she connects the smell to her mood; she glances toward the entryway table where the bottle sits, one hand gesturing lightly toward it.
LINE_3 — quiet fascination as she leans in slightly toward the reeds, tilting her head, inviting the viewer to look closely with her rather than performing for them.
LINE_4 — a settled, confident nod to close, gaze steady and warm, the kind of small satisfied breath before the last word lands.
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:
- The glass bottle is clear and rigid, holding an orange-tinted liquid that sloshes gently with a faint liquid sound only when the bottle is tilted or moved.
- The reed sticks are thin, dry and rigid, drawing liquid up slowly by capillary action — they do not bend, drip, or visibly change while on camera.
- The silver cap is a separate metal piece that lifts off cleanly with a small metallic click and sits still wherever it is placed.
- NEVER: the liquid never sprays, foams, or shoots upward, and the reeds never bend, drip liquid, or move on their own.
- Scale is fixed: about 20 cm tall and 6 cm across, roughly 200 ml — about one and a half times the length of an adult palm, sitting comfortably held in one hand or standing on a table. It must never look larger than her forearm.. No framing, however close, ever makes it read bigger than that

AUDIO:
No music. Room tone of a quiet home entryway, the soft scuff of her shoes on the floor, a faint clink of the silver cap being set down, and her spoken lines staying the clearest sound throughout.

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 — a wide static shot taking in the whole entryway, the woman and the diffuser bottle both visible as she steps in Middle — a medium shot framing her from the waist up as she picks up the bottle and talks about the scent Middle — a close macro shot on the reed sticks and the orange liquid inside the glass, catching light on the surface Ending — a tight close-up on her face as she reacts and delivers the last line, the cut landing hard on the change of shot 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:
a low shoe shelf