What happens in the It's Time Christmas video, second by second?
Both versions copy the same 15 seconds of the 2026 clip, and your photo takes the singer's place in every shot:
| Time | What you see | Human | Pet |
|---|---|---|---|
| 0 to 2 s | Black cards: 11:59:58 PM, 11:59:59 PM, 12:00:00 AM | The countdown, as in the clip | The countdown, as in the clip |
| 2 to 3.7 s | A punk club on Halloween night, hands reaching in | You scream "It's time" into the camera in a black cat-ear headband, goth eye makeup and a studded leather jacket | Your pet roars at the camera in the studded leather jacket |
| 3.7 to 5.2 s | Frost covers the whole frame | The Halloween look freezes | The Halloween look freezes |
| 5.2 to 8 s | A snowy mountain village, a sleigh flies past | You sing in a red Santa outfit with white fur trim | Your pet in the red Santa outfit |
| 8 to 15 s | The camera pulls back as the tree grows | You stand on top of a giant Christmas tree, its star | Your pet stands on top of the tree |
How it works: the best AI video models available, including Seedance 2.5, edit the clip itself: they swap the singer for the person or pet in your photo and keep the countdown, the frost, the village and the tree. You get 15 seconds at 720p in a vertical 9:16 frame, with the song of the clip put back after the run. The mouth follows the clip, so it is close to the words but not exact lip sync. 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.
