Create a 26-second ultra-realistic cinematic travel video featuring a beautiful young Korean woman exploring the streets of Tokyo, Japan, at night and during sunset, wearing a stylish black leather jacket with natural makeup and soft, wavy black hair. Begin with a rear-view shot of her walking across a busy Tokyo intersection surrounded by colorful neon signs, wet streets, and glowing city lights. Show her smiling warmly while holding a cute Japanese rice ball inside a brightly lit convenience store, followed by a candid moment of her buying a drink from a vending machine. Capture her walking beneath a traditional red Japanese torii gate, then turning back toward the camera with a playful smile in a narrow street decorated with glowing Japanese lanterns. Show her taking a casual selfie on a peaceful residential street and enjoying the riverside scenery as a train passes in the background. Include a cozy bookstore scene where she excitedly opens a travel book and smiles at the camera, followed by a peaceful sunset moment sitting beside the river with a takeaway drink. End with beautiful nighttime city lights, a joyful handheld selfie on an elevated bridge, and her smiling with the Tokyo skyline behind her. Use natural handheld smartphone camera movements, smooth cinematic transitions, authentic candid expressions, realistic skin texture, soft film grain, nostalgic early-2000s MiniDV aesthetics, moody teal-green night tones, warm sunset lighting, and shallow depth of field. Maintain consistent facial identity, hairstyle, outfit, and body proportions throughout the entire video, with realistic movements and a spontaneous travel-diary feeling, in a 16:9 widescreen aspect ratio.
This clip was generated with Seedance 2.0 by ByteDance. The prompt on this page is the exact text used to create it.
The example was generated with Seedance 2.0 using: 636:359 · 0:26 · Cinematic · Neon · Cityscape. 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.