What happens in the Dom Perignon car trend, second by second?
Both versions copy the first 15 seconds of the original clip, and your photo takes the driver's place in every shot. The car, the gas station, the camera, the cuts and the lyric captions come from the clip:
| Time | Lyrics on screen | Human | Pet |
|---|---|---|---|
| 0 to 3.8 s | "You say take me home", "I said Dom Perignon" | You stand in front of the white coupe under the gas station lights and mouth the hook with big hand moves. | Your pet stands in front of the car and moves its head and paws to the hook. |
| 3.8 to 6.6 s | "You said no, no, no", "I said" | A selfie at the car, then your finger taps the headlight on every "no". | A selfie close-up, then a paw taps the headlight. |
| 6.6 to 10.5 s | the beat | Quick cuts: you tap the plate and the wheel, open the door, touch the seat and the tail light. The car waits alone at the pumps. | The same quick cuts with its paw. |
| 10.5 to 15 s | "Hasta la vida loca", "te encanta la música" | The car drives past on a dark road, then you sing along at the wheel. | Your pet sits at the wheel and bobs its head to the beat. |
How it works: the best AI video models available edit the clip itself: they swap the driver for the person or pet in your photo and keep everything else. You get 15 seconds at 720p with the song of the clip put back on after the run, so "Toca Toca" plays over your video. A run takes 5 to 15 minutes, and the exact price shows on the Generate button before you spend anything. Every run is a new take, so results differ.
Why is it wide? The original clip is wide (16:9), and so are most copies of the trend, from the car versions to the motorbike ones. Your video keeps that frame, so the car and the whole gas station stay in the shot.
