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, casual pants, and a soft knitted scarf. Maintain identical facial identity, clothing, and proportions throughout. **0–3s:** On a quiet autumn neighborhood sidewalk, she walks slowly holding a steaming takeaway coffee with both hands, smiling softly. **3–6s:** She pauses beside a garden wall, warms her fingers around the cup, and closes her eyes briefly. A light breeze moves her hair and scarf. **6–9s:** She takes a small sip, finds it unexpectedly hot, pulls the cup away, blinks in surprise, and gives it a mildly offended but amused look. **9–12s:** She gently blows on the coffee and tries another tiny sip, looking satisfied as she gazes at the sunlit trees. **12–15s:** She resumes walking, cradling the cup against her hoodie. Noticing the camera, she gives a brief, shy smile before looking ahead. **Visual style:** Authentic early-2000s Sony MiniDV home-video footage filmed by a friend. Slight handheld shake, imperfect framing, spontaneous reframing, occasional gentle autofocus hunting, subtle exposure shifts, faded colors, soft contrast, natural skin texture, realistic steam, and warm autumn afternoon light. Candid, cozy, unpolished atmosphere. **Motion:** Smooth, continuous real-time movement with realistic walking, fingers, sipping, expressions, and rising steam. Strict character consistency. No stuttering, judder, frame skipping, duplicated frames, slow motion, sudden jumps, exaggerated reactions, or artificial cinematic movements. **Audio:** Natural outdoor ambience only—footsteps, faint breeze, distant neighborhood sounds, and clothing rustle. 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 · Peaceful. 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.