Create a 15-second vertical 9:16 cinematic short video with native audio and…

Create a 15-second vertical 9:16 cinematic short video with native audio and emotional storytelling. Main character: an East Asian woman in her late 20s. Second character: an East Asian man in his late 20s. Setting: modern Japanese city. Story structure: Scene 1 (0-4s): In a cozy cafe at night, the woman and the man are sitting across from each other after a date. The atmosphere is soft, intimate, and slightly emotionally tense. The man gives a small gentle smile and says in natural Japanese, “また連絡するね” (“I’ll text you again”). The woman smiles softly, trying to stay calm, and replies in natural Japanese, “うん、待ってる” (“Okay, I’ll wait”). Use natural lip sync, subtle voice acting, and realistic cafe ambience. Scene 2 (4-8s): Cut to the woman alone in her bedroom at night, sitting on her bed and looking at her smartphone, waiting for his message. No notification appears. Her expression slowly falls, showing quiet disappointment and emotional vulnerability. Soft bedroom lighting, calm silence, subtle room ambience. Scene 3 (8-12s): The woman walks alone through a quiet city street at night, replaying the conversation in her mind. The streetlights glow softly. Her expression is reflective and slightly hurt. Gentle footsteps, distant city ambience, emotional continuity from the previous scene. Scene 4 (12-15s): Morning light. The woman sits by a window or in a quiet cafe, places her phone down, takes a gentle breath, and regains a subtle sense of calm and hope. End on a soft, emotionally healing note. Warm morning light, peaceful ambience. Requirements: - Keep the woman’s identity consistent across all scenes. - Strong short-form storytelling with clear emotional progression: hope → waiting → disappointment → quiet recovery. - Natural Japanese dialogue audio. - Accurate lip sync and believable facial expressions. - Soft cinematic lighting. - Elegant, realistic visuals. - Muted beige, dusty pink, soft brown, cream, and deep navy color palette. - Smooth transitions between scenes. - Optimized for social media short-form video. - No subtitles, no on-screen text, no watermark.