Start with two individual portraits. The left photo plays the listener and the right photo plays the speaker. You can check both roles in the local preview.

Choose and check the two portraits
Use one consenting adult per photo. Pick clear faces in even light and avoid sunglasses that hide the eyes. Add the listener on the left and the speaker on the right. Swap them if the roles are reversed.
Choose a frame for the elevator
Use 9:16 for a vertical post or 16:9 for a wider composition. Keep room around both heads for the headphones and the turn toward the speaker.
Review the scene before submitting
Check that each preview shows the intended person. Review the credit cost, duration and audio notes before generating.
Sources and editorial notes
Studio instructions describe the current I Love The Smiths AI workflow. Creative briefs are optional planning examples; the studio generates with built-in scene and style scripts. Third-party guides link to their official documentation and do not imply an integration or a quality ranking. Read our editorial approach