Toss Catch Then Use Montage
A real viral video decoded into image steps and 4-second clips you can remake with your product.
A partner walks in and tosses a folded gift to the seated POV viewer, who catches it, holds it up to the lens and unfolds it. Then a rapid montage shows the same item used in a new real-life place every ~2 seconds (airport, escalator, plane aisle, sidewalk, stairs, car park, beach). Compared with the parent concept (a draping toss with an accessory pack and a finished-result demo), this variation tosses one folded item, catches it into a close-up, and replaces the single demo with a multi-location use montage under one static gift-bet text.
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 seated eye level. the person on camera, long blonde ponytail, black hoodie and leggings, thin bracelet, shows only as bare lower legs at the bottom edge, feet toward a glass coffee table. Through an open white doorway her partner, a young man with short blonde hair, walks forward mid-stride in a light hoodie and shorts. At waist height he carries the your product (your product) folded up and tucked against his body. the scene: Visible walls, floor and surfaces, two or three main landmarks, one clear light source from one side. Daylight from the left and the room behind the doorway, no blur, no bokeh. The vibe is candid, authentic, low-production UGC content, like a real TikTok video. The partner walking in through the doorway is the focal point of the shot; the your product is folded and hidden against his body, not yet visible. 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 2.2s.
Hyper-realistic UGC TikTok style vertical video, shot on iPhone. the person on camera sits on a sofa in the scene, only her legs in frame, while her partner walks toward her holding the your product (your product) folded. 0-1s: Her partner strides forward with a small smile, the your product held at his waist, his reflection sliding across the glass table. 1-2s: He swings it up and tosses it toward the camera; the person on camera's hands rise from the bottom of the frame, catch it and pull it up to the lens with both hands, the your product filling most of the frame at 2.2s. 2-3s: holds the pose, perfectly still, only a slight handheld sway. 3-4s: stays frozen in the same pose, her partner standing small in the background. Audio: a soft whoosh as the folded fabric flies through the air, a light slap as hands catch it, quiet room ambience. 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.