What happens in the tying my shoes video, second by second?
Both versions copy @merkurianin's AI clip, one continuous shot from a phone lying low on the park path. Your photo takes the cat's place; the park, the cup, the cash and the people walking past stay as they are:
| Time | What happens | You | Pet |
|---|---|---|---|
| 0 to 1 s | Walk-up | You walk in with a drink cup. | Your pet walks in upright with the cup. |
| 1 to 4.5 s | The shoe | You set the cup down and crouch to tie your shoe while people walk past. One drops a bill in the cup. | It sets the cup down and bends over its paws. |
| 4.5 to 6 s | The switch | You spot the cash, look into the camera with a huge grin and sit down behind the cup. | The same big grin, and it sits behind the cup. |
| 6 to 11 s | Payday | More people drop cash; a group bends down to fill the cup. You keep grinning. | It grins and rubs its paws. |
| 11 to 13 s | The end | You sit behind a cup full of money. | The same, with your pet. |
How it works: top-quality AI video models, including Seedance 2.5, edit the clip itself: they swap the cat for the person or pet in your photo and keep everything else. You get 13 seconds, vertical 9:16 at 720p, with the clip's original sound put back after the run. 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.
