How to make the I Love The Smiths AI video
Two photos, one elevator scene. Keep the upload order clear.
Updated 2026-11-10
- 01Add the listener photo
Choose one adult whose image you have permission to use. This person takes the screen-left role: the listener who wears the headphones.
- 02Add the speaker photo
Choose the second adult. This person takes the screen-right role: the one who says "I love The Smiths".
- 03Generate and review
Check the price shown before generation. When the video is ready, check both faces, the headphones moment, the length and the sound before you post it.
Before you start
Use one consenting adult per photo. A clear face and good light help the model keep the two people distinct. Chest-up photos work best because the scene is a close two-shot.
- Do not swap the upload order after you choose the roles.
- You do not need headphones in the photo; they are added for you.
- Use only photos you have the right to use.
What the reference video controls
The reference provides the elevator, the camera, the pacing and the sound. Your photos provide each person’s visible identity and clothes.
Back to the generator: AI video templates


