东京巷弄草莓甜点探店

Both MiniMax H3 Max and MiniMax H3 currently offer unlimited generations on @itsPolloAI.

So now is a great time to try them out for yourself.

Prompt of this video ↓
Realistic smartphone food vlog set in a charming neighborhood in Tokyo, Japan. The entire video must look genuinely recorded on a modern flagship smartphone by a real young Japanese female creator, never cinematic or AI-generated.
IMPORTANT: The young Japanese woman must wear a clearly visible bright orange shirt throughout the entire video. An orange bicycle must also naturally appear on the Tokyo street and be clearly visible in the scene.
0–4 seconds: A young Japanese woman wearing a bright orange shirt casually walks through a narrow Tokyo side street in the early evening, holding her smartphone at arm’s length and naturally vlogging. Traditional Japanese shopfronts, vending machines, small signs, utility wires, pedestrians, warm storefront lights, and a clearly visible orange bicycle create an authentic neighborhood atmosphere. She suddenly notices a tiny hidden dessert café and naturally turns the camera toward its entrance with an excited smile.
4–8 seconds: She walks into the cozy café while continuing the vlog. Her bright orange shirt remains clearly visible. The smartphone camera naturally adjusts exposure from the brighter street to the warm interior. Show a quick but realistic close-up of fresh strawberries, whipped cream, and soft cake layers being prepared, with subtle autofocus shifts and natural handheld movement.
8–12 seconds: She receives the strawberry cream dessert and holds it naturally toward the phone camera. She takes a spoonful, tastes it, and gives a spontaneous, believable happy reaction with subtle facial expressions. Realistic food textures, natural hand movement, and genuine creator behavior.
12–15 seconds: She walks back outside onto the warm Tokyo street, with her bright orange shirt clearly visible and the orange bicycle naturally present in the street environment. She smiles directly at the phone camera and naturally says, “Okay, this place was actually so good!” She casually ends the recording.
Authentic Japanese environment, realistic human behavior, natural walking physics, accurate skin texture, natural hair movement, realistic reflections, genuine food textures, imperfect smartphone framing, subtle autofocus hunting, automatic exposure adjustments, slight handheld shake, natural motion blur, realistic smartphone low-light noise, true-to-life colors, detailed background activity, seamless transitions between moments, genuine casual vlog energy, high-resolution smartphone footage, photorealistic documentary realism.
The bright orange shirt and orange bicycle must remain visually natural and realistic, blending naturally into the authentic Tokyo environment.
No cinematic camera movements, no drone shots, no artificial slow motion, no CGI appearance, no overly perfect beauty filters, no exaggerated acting, no text, no subtitles.