I Love the Smiths AI Video

Cast two adults in the warm wood elevator exchange: the headphone listener stays behind while the speaker repeats the line and walks out.

Add the two role photos

One consenting adult who remains in the elevator wearing headphones. A second consenting adult who delivers the line and exits the elevator.

One consenting adult who remains in the elevator wearing headphones.

A second consenting adult who delivers the line and exits the elevator.

Loading photos…

Failed generations return credits

Reference preview

15.09 seconds · 720p · 9:16 reference · Original reference audio
Two adults · 15.09 secondsThe left listener wears headphones and stays in the elevator; the right speaker delivers the short exchange twice, then exits as the shot sequence completes.

Temporary photos are removed after the task. Read our privacy policy.

The two adult photos guide the listener and speaker identities; the elevator, headphones, wardrobe treatment, dialogue timing, exits and shot order come from the reference. Content rules · Report content

Video reference

The left listener wears headphones and stays in the elevator; the right speaker delivers the short exchange twice, then exits as the shot sequence completes.

Recreate a warm wood-panel elevator with fixed framing and original dialogue

The left listener wears headphones and stays in the elevator; the right speaker delivers the short exchange twice, then exits as the shot sequence completes.

The two adult photos guide the listener and speaker identities; the elevator, headphones, wardrobe treatment, dialogue timing, exits and shot order come from the reference.

The selected reference runs 15.09 seconds at original speed and keeps its complete shot window.

Keep the roles, action and scene aligned

The left listener wears headphones and stays in the elevator; the right speaker delivers the short exchange twice, then exits as the shot sequence completes.

The two adult photos guide the listener and speaker identities; the elevator, headphones, wardrobe treatment, dialogue timing, exits and shot order come from the reference.

The output follows the actual 720 × 1280 reference framing rather than stretching a different crop.

Visual generation is silent. After the media checks pass, the AAC track from the same locked reference snapshot is restored.

What this selected scene includes

Two adults

One consenting adult who remains in the elevator wearing headphones. A second consenting adult who delivers the line and exits the elevator.

Locked action and camera

The left listener wears headphones and stays in the elevator; the right speaker delivers the short exchange twice, then exits as the shot sequence completes.

Complete video with sound

Download the full 15.09 seconds scene with the selected reference audio.

Make your I Love the Smiths AI video

  1. Add both role photos

    One consenting adult who remains in the elevator wearing headphones. A second consenting adult who delivers the line and exits the elevator.

  2. Confirm permission and generate

    Confirm photo permission, then create the prepared scene for 10 credits.

  3. Review and download

    Check identity, role order, motion, prop contact, framing and sound before saving.

Prepare the photos for this scene

  • Photograph each subject alone rather than using a group photo.
  • Keep the face, hair or fur pattern and visible body clear.
  • Avoid hands, phones, stickers or filters covering the face.
  • Use a sharp image with even light.
  • Review identity, role order, hands or paws and scene contact points.

Questions about I Love the Smiths AI

How many photos do I need?+

Two adults: One consenting adult who remains in the elevator wearing headphones. A second consenting adult who delivers the line and exits the elevator.

What happens in the scene?+

The left listener wears headphones and stays in the elevator; the right speaker delivers the short exchange twice, then exits as the shot sequence completes.

Will my original background remain?+

No. The locked reference supplies the setting, camera, fixed props and shot order.

What comes from my photos?+

The two adult photos guide the listener and speaker identities; the elevator, headphones, wardrobe treatment, dialogue timing, exits and shot order come from the reference.

Will the result include sound?+

Yes. Audio is restored from the same selected reference snapshot after silent visual generation. There is no replacement-audio upload.

What format and price do I get?+

One generation uses 10 ReelTada credits and targets a 15.09 seconds 9:16 MP4 at 720p. Your balance is checked before upload and generation.

Make My Elevator Dialogue Video

Two adults, the complete 15.09 seconds scene and selected reference audio.