Shelf Shock Pet Play Montage
A real viral video decoded into image steps and 4-second clips you can remake with your product.
A woman in a festive onesie stands in a warehouse aisle with her dog, gasps and points off-screen. The camera pans to a shelf display of a festive bouncing dog ball, then a quick montage shows different big dogs chasing it at home. This is a variation of the parent concept: the water-test demos become dogs playing, and the store-shelf gasp stays.
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.
Handheld iPhone shot, vertical 9:16, held at chest height facing a store aisle. the person on camera, long straight dark hair, tanned skin, small gold earrings, zip-up festive holiday-patterned onesie with green cuffs, stands on the left of the frame holding a black leash in her right hand. She looks off to the right with a neutral, curious expression and her mouth closed. A large fluffy black, tan and white dog sits calmly on the right, also looking right. Behind them in the scene: Landmarks, floor surface and background props visible behind the subject, one main light source. Bright, even fluorescent light falls from directly overhead. Natural light, sharp focus, no blur, no bokeh. The vibe is candid, authentic, low-production UGC content, like a real TikTok video. Her neutral face and the seated dog are the focal point of the shot; the your product is not yet visible up close. 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 3.8s.
Hyper-realistic UGC TikTok style vertical video, shot on iPhone. the person on camera stands on the left in the scene holding a leash, a large seated dog beside her, both looking right with calm faces. 0-1s: she watches something off-camera with a neutral face, then her jaw suddenly drops wide open in exaggerated shock, her eyes widening while the dog stays sitting calmly. 1-2s: she keeps her mouth open, gasps with excitement and raises her right arm to point to the right, her body turning slightly toward it. 2-3s: the handheld camera begins a smooth sideways pan to the right, following her pointing arm; she and the dog slide out of the left edge of the frame. 3-4s: the pan slows and settles on a shelf display of your product (your product) above stacked retail boxes, steady and centred. Audio: a sharp gasp, the leash rattling, ambient store hum. Candid, slightly shaky handheld camera feel, 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.