Three independent parts
Keep the nearest speaker, middle responder and far companion assigned to different photos.
The nearest friend gestures and laughs, the middle friend turns to respond, and the third stays behind them at the counter.
You Talking Bout Me AI recreates the three-person counter exchange using three separate adult photos. The nearest friend speaks and laughs, the middle friend asks the question and the far companion stays behind the pair.
To put yourself in the questioning role, use your photo in the second slot. These are speaking and depth positions, so the order matters more than who happens to look left or right in one frame.
The background counter and camera remain from the scene. Your photos provide three distinct appearances and outfits, without moving their backgrounds into the restaurant.
The joke depends on the pause and reaction between the nearest speaker and middle responder. The original recording stays with that exchange; uploading a photo does not change the voice or write a different reply.
Keep all three mouths and eyes clear in the source photos. Each adult appears at a different distance from the lens, and the camera’s movement changes how much of the far companion is visible.
The selected landscape scene is about 14 seconds long. Its 720p MP 4 includes the same reference dialogue at the original pace. It is a video output, not a GIF, a new script or a voice message.
Keep the nearest speaker, middle responder and far companion assigned to different photos.
Retain the pauses, gestures and reactions with the selected recorded exchange.
Save the landscape frame without cutting away the far companion.
Add the nearest speaker, middle questioner and far companion in that order.
Use one consenting adult per image and keep the mouths visible before starting the 10-credit scene.
Review all three faces and speaking turns, then save the MP 4 with dialogue.
Photo 2 plays the middle responder. Photo 1 is the nearest speaker, and Photo 3 is the far companion.
Yes. This version uses three separate adult photos for the three counter roles. It does not invent a missing friend or reuse the same upload automatically.
The clip uses the selected scene’s recorded dialogue. There is no script, voice upload, voice-cloning or soundtrack-selection input.
Each adult keeps the visible clothing and appearance from their photo. The restaurant counter, lighting and camera come from the reference scene.
This version casts three adults and keeps the 16:9 landscape composition. It has no pet or portrait-output selection.
The selected scene lasts about 14 seconds and outputs at 720p with reference dialogue. One video uses 10 ReelTada credits; the current balance is checked before photo upload and generation.
Take the three seats at the counter. Cast the nearest speaker, the middle friend asking the question and the quiet companion at the far end.