Create a 10-second ultra-realistic vertical 9:16 TikTok selfie video using the uploaded image as ...

Create a 10-second ultra-realistic vertical 9:16 TikTok selfie video using the uploaded image as the exact first frame and visual reference. IDENTITY & APPEARANCE: Preserve the woman's exact face, facial features, curvy body, natural skin texture, dark messy bun, loose strands, brown eyes, winged eyeliner, gold hoop earrings, nose stud, necklace, olive-green top and black cardigan. Keep the original sidewalk, parked cars, trees, iron fence and natural daylight unchanged. No beautification or identity drift.CAME RA & REALISM: One continuous handheld smartphone selfie shot, arm's-length framing. Subtle natural hand movement, tiny camera shake, realistic autofocus and slight exposure adjustments. Authentic smartphone video quality, visible pores, fine facial details, natural daylight and soft shadows. No cinematic effects, cuts or artificial filters.ACTING & TIMING:0–1.5s: She immediately looks into the lens with a bold, challenging expression, slightly raises one eyebrow and starts speaking confidently.1.5–5s: She speaks with expressive eyes, natural head movements and subtle emphasis, maintaining direct eye contact.5–8.5s: Her expression turns playful and flirtatious. She gives a small knowing smile while delivering the question and call to action.8.5–10s: She finishes with a cheeky half-smile, a tiny head tilt and confident eye contact.EXACT DIALOG UE — MEXICAN SPANISH:“¡Ey, guapo, con migo no juegues! Tengo curvas, carácter y sé perfectamente lo que merezco. ¿Te dio curiosidad esta sonrisa? Sígueme y escríbeme, si te atreves, papito.”VOICE & LIP SYNC : Adult female voice, authentic Mexican Spanish accent, warm slightly husky tone, assertive, playful and naturally flirtatious. Fast conversational delivery, clear pronunciation, accurate Spanish lip synchronization for every word. Strong emphasis on “¡Ey, guapo!” and “si te atreves, papito.” Natural breathing and subtle pauses. She must visibly speak directly to the camera; no voice-over. Keep speech intelligible and synchronized throughout.NEGATIVE PROMPT: Fac e changes, identity drift, distorted mouth, bad lip sync, frozen expression, robotic movements, exaggerated gestures, plastic skin, beauty filters, deformed hands, extra fingers, warped background, changing clothes, camera cuts, zoom transitions, CGI, subtitles, text, logos, watermark, background music overpowering speech.