Create a vertical 9:16 image-to-video clip using the attached photo of the woman as the identity ...
Create a vertical 9:16 image-to-video clip using the attached photo of the woman as the identity reference. Keep her face, age, features, and overall appearance consistent with the photo. Style: photorealistic, natural, attractive, confident woman speaking directly to camera. Subtle natural movement only: slight head movement, blinking, expressive eyes, natural mouth movement, realistic facial expressions. Clean realistic lip sync. Performance: she speaks in clear native Mexican Spanish with an authentic Mexican accent. Her tone is emotional, like something has been building up inside her and she is finally saying it out loud. At the same time, she is playful, seductive, inviting, and slightly teasing. The delivery should feel personal and spontaneous, not like an ad. She looks straight into the camera with confidence, desire, and a hint of challenge. Emotion arc: starts bold and direct, then becomes more intense and emotionally honest, then ends playful and suggestive, as if inviting the viewer to imagine what could happen next. Dialogue (spoken exactly in Spanish): “Coger. Sí, así de claro. Las mujeres de más de 30 también tenemos deseo y ya no estamos para fingir lo contrario. No todo son flores, mensajes bonitos y romance. También queremos química, pasión y un hombre que sepa lo que quiere. Después veremos qué pasa.” Important: - accurate Spanish lip sync - native Mexican Spanish pronunciation - expressive delivery: fed up, emotionally charged, but flirtatious and alluring - no subtitles - no on-screen text - no background music - no extra people - keep the focus entirely on the woman
Free to start · Generate videos and images with AI in seconds