A detailed prompt for generating a 10-second travel vlog video with specific scene transitions and consistency requirements.
Generate a 10-second realistic travel vlog style short video. The protagonist is always the same young Asian woman; her facial features, hairstyle, clothing, and body proportions must remain consistent throughout, with no face-swapping or outfit changes.
The video consists of 3 independent scenes: Beijing, Shanghai, and Guangzhou. City transitions are completed via 'hard cut after snap', with no background blending, spatial distortion, or building dissolves.
0-3s, Beijing.
The girl stands near a representative landmark in Beijing, looking natural and relaxed, hands empty. She looks at the camera, raises her right hand, and snaps her fingers. Immediately after the snap, the scene hard cuts to Shanghai.
3-6s, Shanghai.
The girl is already standing near the Bund or Lujiazui in Shanghai, holding a cup of coffee in her right hand. She walks forward naturally for two steps, then takes a sip of coffee.
After drinking, she walks to a railing platform or small table nearby where items can be placed, clearly putting down the coffee cup in her right hand. The cup must physically touch the platform, fingers fully release, and the right hand completely leaves the cup. Pause for about half a second to confirm the right hand is empty.
Then she raises her right hand again to snap her fingers. Immediately after the snap, the scene hard cuts to Guangzhou. The coffee cup remains in its original position in Shanghai, does not teleport with the person, and must not disappear, float, deform, or suddenly switch hands.
6-10s, Guangzhou.
The girl appears empty-handed near Canton Tower. She walks forward naturally for two steps, turns to look at Canton Tower, then stands at a suitable position to take a photo with the tower, finally looking gently at the camera and smiling to end.
Maintain a realistic mobile phone travel vlog texture throughout, slight handheld feel, natural and simple movements, center of gravity and limb motion conforming to real physical laws.
Special emphasis:
Shanghai segment: Right hand holds coffee → Sip → Place coffee cup on fixed platform → Fully release → Right hand empty → Snap again.
Do not skip the 'putting down coffee' action; do not allow the coffee cup to simply disappear.
Avoid: Face swapping, clothing changes, body proportion changes, character duplication, extra arms, finger deformities, coffee cup disappearance, coffee cup deformation, floating cups, hand switching, snapping while holding coffee, building fusion, simultaneous appearance of Beijing/Shanghai/Guangzhou landmarks, city background residuals, overly complex camerawork.
