Swatch To Street Transformation
A real viral video decoded into image steps and 4-second clips you can remake with your product.
A creator holds up a raw design piece with the text "The inspiration...", then hard-cuts to a top-down shot of her hands making it, then shows the finished item worn from behind in three moody locations. The cuts land on the beats of a dramatic song, and the drum drop lands on the first on-body reveal.
Prompts are filled in for your product.
Make clip 1 of 4
1. Make the image. Open Nano Banana Pro, upload your product photo as the reference, paste this prompt and generate.
Static iPhone shot on a tripod, eye level, vertical 9:16 framing. the person on camera, long dark hair, black gothic outfit, silver rings, stands centered and close to the camera with a soft closed-mouth smile, looking straight into the lens. Both arms are spread wide at shoulder height, fingers pinching the top corners of the your product inspiration piece (your product), a large flat square held taut and covering the torso down to the thighs. the scene: Textured surfaces, a dark piece of furniture, soft natural daylight from one side. Soft natural window light comes from the left side of the room, not toward the camera. No blur, no bokeh, no cinematic grading. The vibe is candid, authentic, low-production UGC content, like a real TikTok video. The your product is clearly visible and the focal point of the shot. Photorealistic, iPhone camera quality, vertical 9:16 format.
2. Turn it into a 4-second clip. Open Seedance 2.5, set that image as the start frame (no end frame), paste this prompt, 4 seconds, generate. In CapCut you keep only the first 2.3s.
Hyper-realistic UGC TikTok style vertical video, shot on iPhone. the person on camera stands centered and close to the camera in the scene, both arms spread wide holding the your product inspiration piece (your product) taut across the torso. 0-1s: the person on camera smiles softly into the lens, holding the piece stretched wide and almost still, then starts to lift it a little toward the camera. 1-2s: the hands fold the piece inward from both sides, the person on camera steps back slightly and presses the folded strip against the chest with both hands, elbows out wide, head tilted with a confident smile, reaching the final pose by about 2s. 2-3s: holds the pose, perfectly still, only a slow blink. 3-4s: stays frozen in the same pose. Audio: a soft breath and the faint rustle of fabric as the piece is folded, quiet room tone. Locked-off static iPhone shot on a tripod, no camera movement, photorealistic iPhone quality, tack-sharp, no blur, no bokeh, no cinematic grading, 9:16 vertical format. No text overlays. Natural scene sounds only, no music.