Foot Tap Unroll Reveal
A real viral video decoded into image steps and 4-second clips you can remake with your product.
A first-person shot looks down at someone's slippered feet tapping a rolled-up bundle on the rug while a voiceover counts down. A foot nudges the bundle open, then a hard cut shows the product worn full-length, with a feature demo in close-ups and a cozy payoff. The countdown plus a mystery cylinder makes people stay to see what it unrolls into.
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, high angle looking down at the floor from seated chest height, vertical 9:16 framing. the person on camera, long brown hair, fitted white short-sleeve t-shirt, white pajama shorts with a small Christmas-tree print, lower legs only in frame. The left foot is raised just above the your product (your product), which lies rolled into a tight horizontal cylinder on a beige shag rug. The right foot rests flat on the rug. the scene: Hardwood floor, a lit Christmas tree with wrapped gifts, a white sofa, large windows with garland across the top. Warm night light from the background lamps and tree lights, soft and even, not aimed at the camera. 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 2.1s.
Hyper-realistic UGC TikTok style vertical video, shot on iPhone. the person on camera sits just out of frame in the scene, only the lower legs visible, the left foot hovering over the rolled-up your product (your product) lying on the rug. 0-1s: the left foot comes down and taps the top of the rolled your product once while the right foot stays flat on the rug. 1-2s: the left foot lifts and taps the your product a second time, then settles back to hover just above it, ending in the end keyframe pose by the 2.1s mark. The your product stays rolled and does not move. 2-3s: holds the pose, perfectly still, only a slow natural breath-like settle. 3-4s: stays frozen in the same pose. Audio: a soft foot tap on the rug, the rolled your product thudding lightly, 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.