What you need before you start
You need two photos and enough credits for the resolution you want. The first is a clear photo of the person who should walk, and the second is a clear photo of the car that should explode. A photo with two people in it will not fill the person slot cleanly, and a photo with two cars in it will confuse the vehicle slot, so crop to a single subject first.
You do not need to film anything, find a road, or write a prompt. The walk, the camera move, the fireball and the audio all come from the prepared template.
Step 1: choose the right person photo
The person photo is one of the two inputs you control, so it is worth a minute of thought.
- Front-facing, with the whole face visible
- Even lighting, ideally from the front
- One person in frame, with no one else behind them
- No sunglasses, no heavy filters, nothing covering the face
A sharp, plain portrait gives the model reliable information about the face, which is what keeps the identity consistent across the clip. You do not need to pose like the reference walker. The stride and the timing are supplied by the template.
Step 2: choose the right car photo
The car photo fills the second slot, so the same rules apply.
- A three-quarter or front angle that shows the whole vehicle
- Even lighting, with the paint colour easy to read
- One car in frame, with no other vehicles behind it
- No heavy reflections or dirt that hide the body lines
The generator takes the body shape, silhouette, paint colour and trim from your photo, so a clean shot of the full car produces the most faithful scene. Decorative items such as roof boxes, stickers and ribbons are excluded on purpose, because they would otherwise be transplanted along with the vehicle.
Step 3: keep the template and set the frame
The scene is fixed, so there is nothing to describe. Set the output ratio and the resolution instead. Keep the native 9:16 frame for Reels, Shorts and TikTok, or pick a wider frame for a feed post or an embed. The credit cost is shown in the form before you submit.
Step 4: generate and download
Confirm the credits, submit the paid task, and wait for the render. Most tasks finish within a few minutes. The preview panel shows live progress, and the finished clip appears as soon as the provider returns the file. The template audio stays attached, so you can post the render without re-timing it.
Common questions
Do I need to write a prompt? No. The prompt is written and hardened inside the template, covering the scene, the single continuous take, the walk, the fireball and the removal of the original person and car.
Can I use a pet or a character instead of a person? The person slot accepts any single-subject photo, so a pet or a character portrait works the same way, as long as one subject is clearly in frame.
What if the result is not right? Failed generations refund unused credits automatically, and you can re-run with different photos. The photos are the only variable, so changing them is the fastest way to a different result.
Try it
Upload one clear photo of yourself and one clear photo of your car, keep the prepared template, and generate the clip. The generator page has the form, and the tutorial covers the walkthrough if you want the detail first.
Every clip is an AI-generated, stylized fictional effect. Nothing is filmed and nothing burns.
Ready to make your own version?
Upload your photo and your car photo and generate the explosion clip in a few minutes.