@Image1 is the exact starting frame. Preserve faces, identities, clothing, bodies, car, street, l...
@Image1 is the exact starting frame. Preserve faces, identities, clothing, bodies, car, street, lighting, composition and positions. Vertical 9:16, 8s. Fixed low-angle smartphone camera, subtle handheld movement, no cuts/zoom. 0–1.5s: Man becomes emotional, covers his face, shoulders trembling as he cries. 1.5–3.5s: Still covering his face, he cries: “Why me again?” 3.5–4.5s: He keeps crying. Woman stops applying lipstick, looks at him, closes her compact mirror and sighs. 4.5–7.5s: She looks at him and says calmly: “You’ll buy a new one, you’re rich, after all.” 7.5–8s: He keeps crying; she holds the closed mirror and looks at him. Realistic restrained acting, accurate lip-sync, clear English dialogue, natural city ambience, crying/breathing and mirror snap. No extra dialogue, subtitles, music, new characters, visual changes, face drift, deformation, exaggerated expressions, slow motion or cinematic movement. Man speaks BEFOR woman; no overlapping dialogue.
Free to start · Generate videos and images with AI in seconds