← 전체 10종

시나리오 01 · 검증 질문 — 오프닝 항공샷이 첫 비트에 들어가나

타워 선풍기

요구한 연출 — 오프닝 드론 상승 — 옥상 전체

사용자가 넣은 입력3개 발화 · 이미지 3장
보낸 말 1

제품 리뷰 영상 만들어줘.

보낸 말 2

타워 선풍기야 https://ugc-band-check.pages.dev/media/ref_fan.jpg 12만원

보낸 말 3

바람이 세면서 조용해. 연출은 오프닝을 드론이 위로 올라가면서 옥상 전체가 보이는 컷으로 시작해줘

제품 사진 (첨부)
페르소나 F1
페르소나 F1
대화 전문18턴
사용자

제품 리뷰 영상 만들어줘.

에이전트

제품 리뷰 영상을 만들어드릴게요! 어떤 제품으로 시작할지 골라주세요. 😊

사용자

타워 선풍기야 https://ugc-band-check.pages.dev/media/ref_fan.jpg 12만원

에이전트

타워 선풍기 사진 확인했어요 — 화이트 컬러의 원통형 디자인이네요. 브랜드 텍스트는 따로 없어서 그냥 '타워 선풍기'로 진행할게요. 하나만 더 여쭤볼게요 — 이 선풍기 쓰시면서 실제로 뭐가 좋아지셨어요? 예를 들면 "예전 선풍기보다 훨씬 조용해서 밤에 틀어놓고 자도 안 깬다" 같은, 직접 겪으신 변화가 있으면 알려주세요. (막연히 "좋아요" 보다 구체적인 게 있으면 영상 대본이 훨씬 자연스러워져요!)

사용자

바람이 세면서 조용해. 연출은 오프닝을 드론이 위로 올라가면서 옥상 전체가 보이는 컷으로 시작해줘

에이전트

좋은 정보예요! 바람 세기랑 조용함, 둘 다 장점이네요. 옥상 드론 오프닝 연출도 잘 기억해둘게요 — 다음 단계에서 반영할게요. 근데 하나만 더 여쭤볼게요 — "조용하다"는 건 전에 쓰시던 선풍기랑 비교했을 때인가요? 예전 건 어땠는지 (예: "예전 건 소음이 좀 컸는데 이건 훨씬 조용해") 알려주시면 훨씬 생생한 대본이 나올 것 같아요.

사용자

네, 이대로 좋아요. 이 내용으로 영상 만들어주세요.

사용자

'이 값에 이게 된다' 앵글로 진행해주세요

사용자

'정면 진행 데모' 형식으로 진행해주세요

사용자

'구마 위 옥탑방' 배경으로 진행해주세요

사용자

30대 느감 느뜩한

에이전트

죄송해요, 말씀해주신 내용이 깨져서 전달됐어요 😅 다시 한 번 알려주시겠어요? 예를 들면 "30대 느낌의 편안한 여성, 캐주얼한 옷차림" 같은 식으로 어떤 사람이 등장했으면 하는지 설명해주시면 그 모습으로 생성해드릴게요.

사용자

이 모델로 할게요

사용자

{"v": 1, "image": "https://assets-static.vcat.ai/public/apps_presets/reference/persona2608/F1_front.jpg", "mimeType": "image/jpeg"}

사용자

{"v": 1, "image": "https://assets-static.vcat.ai/public/apps_presets/reference/persona2608/F1_face.jpg", "mimeType": "image/jpeg"}

에이전트

타워 선풍기 리뷰 영상 대본이 완성됐어요. 위 스토리보드에서 각 장면과 대사를 확인해주세요. **요약** - 제품: 타워 선풍기 (화이트, 12만원) - 컨셉: "이 가격에 이게 된다" — 정면 진행 데모 - 장소: 구름 위 옥탑방 - 등장인물: 선택하신 모델 - 길이: 15초, 9:16 세로, 한국어 내레이션 ⚠️ 영상 생성은 이미지보다 크레딧이 꽤 더 소요돼요. 대본 확인 후 진행할게요!

사용자

이 대사대로 영상 생성해주세요

에이전트

타워 선풍기 리뷰 영상 완성됐어요! 위에서 확인해주세요 😊 옥탑방에서 드론이 위로 올라가는 오프닝으로 시작해서, "이 가격에 이게 된다"는 컨셉으로 12만원의 가치를 자연스럽게 어필하는 15초짜리 영상이에요. 다른 방향으로 다시 만들고 싶으시거나 수정하고 싶은 부분 있으시면 말씀해주세요!

에이전트가 제시한 보기6개 카드
보기
이 값에 이게 된다
그냥 써보고 좋았다
보기
정면 진행 데모
셀피 후기
사용법 튜토리얼
마이크로 스토리 광고
보기
구마 위 옥탑방
초고층 빌늩 옵쀍
보기
제가 제가지을 된 모데을 교를게요
직접 사진을 올릴게요
설임만 주세요, 생성해드릴게요
보기
이대로 만들어주세요
대본을 다시 써주세요
다른 부분을 바꾸고 슶어요
요구한 모델 vs 실제로 나온 인물모델 일치

모델 일치 지정한 F1 이 옥상 프레임 안에 그대로 나옵니다 — 드론 상승 오프닝

지정한 모델 — persona F1
영상에 실제로 나온 인물
첨부한 제품 사진
영상 모델에 실제로 보낸 참조 이미지3장

요청한 페르소나 사진이 영상 생성 호출에 그대로 실렸습니다.

페르소나
첨부 제품
페르소나
시댄스로 보낸 최종 프롬프트7977자
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 late 20s to early 30s, natural everyday look, casual comfortable styling, friendly and approachable demeanor. 100% match.
@Image2 — the product: 화이트 색상의 원통형 타워 선풍기, 깔끔하고 현대적인 디자인. 100% match; every word, logo and label exactly as the reference.
@Image3 — the person's face close-up, for face consistency 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 110 cm tall and 20 cm across at the base — roughly the height from an adult's waist to the floor, measured against an open hand held sideways it spans about five hand-widths tall. It must never look larger than her torso when standing beside it.

LOCATION:
On the weathered rooftop room's floor, beside the old iron railing where laundry lines and potted plants sit against a backdrop of Seoul rooftops far below under a surreal cloud-line.

FIRST FRAME:
0.0s — an aerial move rising straight up over the rooftop room until the entire rooftop and the surrounding cloud-covered skyline are visible below, then settling down into a steady handheld phone-style framing on the speaker for the rest of the clip, the person centred at medium distance, already standing next to the tower fan with one hand resting lightly on its upper edge, 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: an aerial move rising straight up over the rooftop room until the entire rooftop and the surrounding cloud-covered skyline are visible below, then settling down into a steady handheld phone-style framing on the speaker for the rest of the clip
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: reaching down with one hand and pressing the single touch button on the fan's base once, the other hand staying relaxed at her side
8–11s — The camera pushes in on the product as the vent column at the top of the tower releasing a steady, wide stream of air across the rooftop space in front of her so the result is unmistakable — it stays on it rather than cutting away.
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. a loose strand of her hair and the nearby laundry line both flutter steadily in the airflow while her voice stays clearly audible and untroubled beside the running fan 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.

DIALOGUE:
0–3s — "와, 여기 옥탑방인데 진짜 딴 세상 같지 않아요?"
3–8s — "이 타워 선풍기 켜놨는데 바람은 세게 나오는데 소리가 거의 안 들려요."
8–11s — "이거 십이만 원인데 이 정도면 완전 이득 아니에요?"
11–15s — "밤에 틀어놓고 자도 신경 하나도 안 쓰이더라고요."

PERFORMANCE:
LINE_1 — She wants the listener to feel the surreal rooftop setting before the product even matters; delivered with a light laugh and a wide sweeping glance around the space, genuinely charmed.
LINE_2 — She wants to hand over the unexpected discovery that strong airflow and silence coexist; she gestures toward the fan's vent while tilting her head to listen, eyebrows lifting in mild disbelief.
LINE_3 — She wants to land the value argument on the listener directly; a small confident nod, half-smile, like she's letting them in on a good decision.
LINE_4 — She wants to close on a calm, personal reassurance; softer voice, shoulders relaxing, eyes drifting slightly downward as if picturing herself asleep.
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:
- Molded matte-white plastic cylindrical tower body, smooth continuous surface with a slim vertical vent column.
- Internal bladeless-style airflow mechanism pushes a wide, steady stream of air out through the vent slits without visible spinning blades.
- Light enough to rock slightly if bumped but stands stably upright on its round base; the vent surface stays cool to the touch.
- NEVER: the tower fan must never visibly vibrate, rattle or produce a loud whirring/motor noise on screen — its whole appeal is that it stays whisper-quiet even at full airflow.
- Scale is fixed: about 110 cm tall and 20 cm across at the base — roughly the height from an adult's waist to the floor, measured against an open hand held sideways it spans about five hand-widths tall. It must never look larger than her torso when standing beside it.. No framing, however close, ever makes it read bigger than that

AUDIO:
No music. Room tone of the open rooftop — a faint breeze through the laundry lines, distant muffled city sounds drifting up from the streets far below, the fan's airflow itself staying inaudible as pure moving air with no hum or motor noise, and her spoken lines the clear, loudest 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:
an aerial move rising straight up over the rooftop room until the entire rooftop and the surrounding cloud-covered skyline are visible below, then settling down into a steady handheld phone-style framing on the speaker for the rest of the clip This applies to the opening of the clip and supersedes the register above for those seconds; the register above resumes elsewhere.

PROPS:
a laundry line with a few clothes swaying gently nearby