Vertical 9:16, 15 seconds, photoreal fashion film, locked camera, NYC downtown street, crosswalk, ONE WAY sign, red traffic light, tall glass towers, bright daylight. Same family group the whole video, same faces, same positions, same dog: center young woman, two men in suits on the left, small boy, older grey-bearded man, blonde woman on the right, golden retriever sitting on the sidewalk. Hard outfit cuts only, hidden by passing cars. No morph, no glow, no particles. Look 1: all black tailoring, woman in black mini dress, pink bow, pink boots. Look 2: electric blue suits, woman pink hair, blue crop top, silver metallic pants, platform boots, beige bag. Look 3: chocolate brown suits, woman pink jacket, leopard bucket hat, brown leggings, pink socks. Look 4: olive green suits, woman streetwear, neon socks, combat boots. Look 5: hot pink suits, woman rainbow check mini dress, yellow hat. Look 6: yellow suits, woman brown trench, white boots. Look 7: all black again, woman leather jacket, white shirt, black shorts, knee boots. Final 2 seconds: same black look, group walks toward camera across the crosswalk, light turns green, dog on leash, natural steps, no face change. Watermark text bottom center: Shamus DESIGN.
This clip was generated with Seedance 2.5 by ByteDance. The prompt on this page is the exact text used to create it.
The example was generated with Seedance 2.5 using: 16:9 · 0:15 · Cinematic · Fashion · 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.