Camera Work Mansion Greeting

Copy prompt

Shot count: 5 | Duration: 15s | Aspect ratio: 16:9
[REFERENCE IMAGE]
Use @Image1 as the first frame. IMPORTANT: the red curved line and the
Japanese annotation words ("スタート", "エンド") drawn on @Image1 are NOT part
of the scene. Do not render, keep, or animate them. Treat the image as if the
red line and that text do not exist — the final video must show only the room
and the five women, with clean skin and clear background, no red marks and no
leftover annotation text.
The red line is ONLY a camera-path guide: move the camera along the path of the
red line, in the order from the "スタート" point (bottom-left) to the "エンド"
point (center), pushing in on each woman the line passes over, in this order:
blonde (left) -> gold-dress woman -> far-right woman -> burgundy woman ->
center Japanese woman.
[SCENE SETUP]
A gorgeous European-style mansion lounge at night. Gilded ornate walls,
a crystal chandelier, deep velvet sofas, large arched windows with soft city
night lights behind. Five stunningly beautiful women in their 20s seated in a
row, left to right:
1. Scandinavian blonde woman, ivory satin gown.
2. Black woman, gold sequined dress.
3. Japanese woman (center), long black hair, deep-red silk dress.
4. Latina woman, burgundy velvet dress.
5. Indian woman (far right), emerald embellished gown.
Each woman gives the camera an attractive, genuine smile and greets in her
native language exactly when the camera pushes in on her. A matching caption
appears at the same moment.
Lighting: warm golden interior light, soft diffuse key light on faces,
gentle candle and chandelier glow, cinematic warm tones.
──────────────────────────────────────
Shot 1 (0-3s): Start from a low-angle wide framing over the marble table on the
left, then settle on the blonde Scandinavian woman. She smiles warmly at the
camera and says hello in Swedish.
Camera: slow push-in on the blonde woman.
Audio: soft, charming female voice, Swedish: "Hej".
Text: "Hej" (white bold sans-serif, gold outline, bottom-center).
Shot 2 (3-6s): Reframe to the Black woman in the gold sequined dress. She gives
a radiant smile to the camera and greets in French.
Camera: slow push-in on the woman in gold.
Audio: warm, elegant female voice, French: "Bonjour".
Text: "Bonjour" (white bold sans-serif, gold outline, bottom-center).
Shot 3 (6-9s): Swing across to the Indian woman on the far right. She smiles
gracefully at the camera and greets in Hindi.
Camera: slow push-in on the woman on the far right.
Audio: graceful, gentle female voice, Hindi: "Namaste".
Text: "नमस्ते" (white bold, gold outline, bottom-center).
Shot 4 (9-12s): Move back left to the Latina woman in the burgundy velvet dress.
She gives a passionate, charming smile and greets in Spanish.
Camera: slow push-in on the woman in burgundy.
Audio: passionate, warm female voice, Spanish: "Hola".
Text: "Hola" (white bold sans-serif, gold outline, bottom-center).
Shot 5 (12-15s): Final move to the Japanese woman in the center. She gives the
most captivating smile of all and greets in Japanese.
Camera: slow push-in on the center Japanese woman.
Audio: sweet, captivating female voice, Japanese: "Konnichiwa".
Text: "こんにちは" (white bold gothic, gold outline, bottom-center).
──────────────────────────────────────
Style: cinematic vertical-grade quality in 16:9, 4K, ultra-high resolution,
rich detail, natural colors, soft beautiful skin texture, luxurious gold and
deep-red palette, soft cinematic depth of field.
Consistency: maintain each woman's distinct appearance, stable faces, clear
facial features, normal body proportions, no deformation or drift, five women
only, no extra people. Keep each native-language caption text accurate and
legible.
Avoid: jitter, distortion, deformation, blur, shake, ghosting, flickering,
extra people, extra text, watermark, red line, red marks, drawn lines,
annotation text, "スタート", "エンド".

Shot count: 5 | Duration: 15s | Aspect ratio: 16:9 [REFERENCE IMAGE] Use @Image1 as the first frame. IMPORTANT: the red curved line and the Japanese annotation words (“スタート”, “エンド”) drawn on @Image1 are NOT part of the scene. Do not render, keep, or animate them. Treat the image as if the red line and that text do not exist — the final video must show only the room and the five women, with clean skin and clear background, no red marks and no leftover annotation text. The red line is ONLY a camera-path guide: move the camera along the path of the red line, in the order from the “スタート” point (bottom-left) to the “エンド” point (center), pushing in on each woman the line passes over, in this order: blonde (left) -> gold-dress woman -> far-right woman -> burgundy woman -> center Japanese woman. [SCENE SETUP] A gorgeous European-style mansion lounge at night. Gilded ornate walls, a crystal chandelier, deep velvet sofas, large arched windows with soft city night lights behind. Five stunningly beautiful women in their 20s seated in a row, left to right:

  1. Scandinavian blonde woman, ivory satin gown.
  2. Black woman, gold sequined dress.
  3. Japanese woman (center), long black hair, deep-red silk dress.
  4. Latina woman, burgundy velvet dress.
  5. Indian woman (far right), emerald embellished gown. Each woman gives the camera an attractive, genuine smile and greets in her native language exactly when the camera pushes in on her. A matching caption appears at the same moment. Lighting: warm golden interior light, soft diffuse key light on faces, gentle candle and chandelier glow, cinematic warm tones. ────────────────────────────────────── Shot 1 (0-3s): Start from a low-angle wide framing over the marble table on the left, then settle on the blonde Scandinavian woman. She smiles warmly at the camera and says hello in Swedish. Camera: slow push-in on the blonde woman. Audio: soft, charming female voice, Swedish: “Hej”. Text: “Hej” (white bold sans-serif, gold outline, bottom-center). Shot 2 (3-6s): Reframe to the Black woman in the gold sequined dress. She gives a radiant smile to the camera and greets in French. Camera: slow push-in on the woman in gold. Audio: warm, elegant female voice, French: “Bonjour”. Text: “Bonjour” (white bold sans-serif, gold outline, bottom-center). Shot 3 (6-9s): Swing across to the Indian woman on the far right. She smiles gracefully at the camera and greets in Hindi. Camera: slow push-in on the woman on the far right. Audio: graceful, gentle female voice, Hindi: “Namaste”. Text: “नमस्ते” (white bold, gold outline, bottom-center). Shot 4 (9-12s): Move back left to the Latina woman in the burgundy velvet dress. She gives a passionate, charming smile and greets in Spanish. Camera: slow push-in on the woman in burgundy. Audio: passionate, warm female voice, Spanish: “Hola”. Text: “Hola” (white bold sans-serif, gold outline, bottom-center). Shot 5 (12-15s): Final move to the Japanese woman in the center. She gives the most captivating smile of all and greets in Japanese. Camera: slow push-in on the center Japanese woman. Audio: sweet, captivating female voice, Japanese: “Konnichiwa”. Text: “こんにちは” (white bold gothic, gold outline, bottom-center). ────────────────────────────────────── Style: cinematic vertical-grade quality in 16:9, 4K, ultra-high resolution, rich detail, natural colors, soft beautiful skin texture, luxurious gold and deep-red palette, soft cinematic depth of field. Consistency: maintain each woman’s distinct appearance, stable faces, clear facial features, normal body proportions, no deformation or drift, five women only, no extra people. Keep each native-language caption text accurate and legible. Avoid: jitter, distortion, deformation, blur, shake, ghosting, flickering, extra people, extra text, watermark, red line, red marks, drawn lines, annotation text, “スタート”, “エンド”.