Cuban Quartet

Prompt

CINEMATIC MUSIC VIDEO — 45 SECONDS Use the uploaded reference image. Preserve the exact identity, facial features, clothing and positions of all four Cuban singers. Do not redesign or replace any member. LEFT TO RIGHT: ROBERT — dark blue shirt, white hat, deep bass. CHANG — white shirt, light hat, rhythmic tenor. EHXM — center, black floral shirt, straw hat, deep raspy lead. MANOLO — right, white shirt, dark hat, warm baritone. SCENE: A beautiful colonial Cuban courtyard in Trinidad, surrounded by colorful architecture, tropical vegetation and warm golden-hour sunlight. A traditional Cuban ajiaco simmers in a large pot in front of the quartet. CAMERA AND ACTION: 0–5 SEC: Slow cinematic dolly-in. Steam rises from the ajiaco. The camera reveals the four singers. Robert begins his deep vocal bass rhythm. 5–12 SEC: Chang performs rhythmic vocal percussion. Close-ups of his lips and facial expressions. EHXM begins singing with accurate lip synchronization. His mature, gravelly voice drives the performance. 12–22 SEC: The camera slowly circles the quartet. Manolo delivers his melodic response. Cut between the four singers, maintaining their original identities. 22–35 SEC: EXPLOSIVE CHORUS. All four sing together: "Cuba es un ajiaco, ay, qué rico está, un poquito de aquí, un poquito de allá." Perfectly synchronized lips. Natural body movements, expressive faces and authentic four-part vocal harmony. The camera rises slightly, revealing the colorful courtyard. 35–45 SEC: EHXM leads the final phrase. The other three respond rhythmically. A cinematic overhead shot reveals the four singers surrounding the steaming ajiaco. End with a dramatic close-up of EHXM, followed by a wide shot of the entire quartet. VISUAL STYLE: Ultra-photorealistic, cinematic 4K, natural facial expressions, realistic human anatomy, authentic Cuban atmosphere, warm film grain, dynamic camera movement, shallow depth of field. IMPORTANT: Only EHXM sings the lead passages. All four sing together during the chorus. No instruments. No additional singers. No face morphing, no identity changes, no clothing changes. Maintain precise lip synchronization with the uploaded audio.