Create a 15-second ultra-realistic 16:9 landscape video featuring the same naturally attractive 24-year-old Korean woman with long loose dark hair, minimal makeup, an oversized maroon hoodie, and loose casual pants. Maintain consistent facial identity, hairstyle, outfit, and proportions throughout. Shot 1 (0–3s): In a quiet neighborhood park on a sunny afternoon, she sits on a wooden bench flipping through a paperback book and notices a small folded note tucked between the pages. Shot 2 (3–6s): Over-the-shoulder close-up of her hands carefully removing and unfolding the creased note. Shot 3 (6–9s): Medium close-up as she discovers a simple, slightly crooked smiley face drawn on the paper. Her eyebrows lift in surprise, then her expression softens into a genuine smile. Shot 4 (9–12s): From a closer side angle, she looks around curiously, then back at the note, letting out a tiny amused laugh while smoothing the paper with her fingertips. Shot 5 (12–15s): She refolds the note, places it inside the book, holds the book against her chest briefly, and gives the person filming a warm, shy smile before standing and walking away. Visual style: Authentic early-2000s Sony MiniDV home-video footage, filmed by another person, never a selfie. Slight handheld shake, imperfect framing, natural reframing, occasional autofocus hunting, subtle exposure shifts, faded colors, soft contrast, realistic skin texture, and gentle sunlight through trees. Intimate, spontaneous, and heartwarming, not cinematic. Motion quality: Smooth, continuous real-time movement with natural page handling, realistic fingers and paper creases, and consistent character identity. Keep the note a single physical object with the same smiley face whenever visible. No extra text, changing drawings, disappearing objects, distorted fingers, stuttering, judder, frame skipping, duplicated frames, or slow motion. Audio: Natural park ambience, distant birds, faint traffic, page turning, paper rustling, and her quiet chuckle. No music, narration, or artificial sound effects.
This clip was generated with Wan 3.0 by Alibaba. The prompt on this page is the exact text used to create it.
The example was generated with Wan 3.0 using: 16:9 · 0:15 · Cinematic · Realistic · Portrait. Reusing these settings gives the closest match.
Copy the prompt as-is first, then change the subject while keeping the camera, motion, and lighting terms. Video models are sensitive to wording, so expect a few runs.
Yes. Prompts work best as starting points — swap scenes, adjust pacing terms, or change the aspect ratio to fit your project.