StudioThe orange-booth guide

The orange-booth guide

How to make a Hotel Lobby AI video

Two people, one hanging microphone and an orange studio. Start by deciding whether you want a new duet or the moves from a particular video.

By Hotel Lobby StudioGeneration coming soon · Paid access
The quick answer

A photo-to-video tool can use two portraits to make a new performance in an orange booth. To reproduce the timing of a particular clip, choose a motion-transfer workflow that also accepts that video.

What is the Hotel Lobby AI effect?

For the video effect, the recognizable scene is a pair of performers sharing a suspended microphone, with an orange backdrop and a front-facing camera. Renoise’s Hotel Lobby page describes this look and distinguishes a new performance generated from photos from copying an existing performance.

When you search for a “Hotel Lobby filter” or “Hotel Lobby AI template,” look at what the tool actually asks you to upload. A photo generator and a motion-transfer tool can produce similar settings while using different inputs.

Choose the workflow for your idea

Your goalNew scene from photosMotion transfer
InputsPortrait references and a scene descriptionA source video and character references
MovementA newly generated performanceMovement guided by the source clip
Best fitAn original duet with the orange-booth lookThe timing and gestures from footage you can use
This studioThe workflow we are preparingNot supported here

For example, Higgsfield’s Genjutsu guide describes Motion Transfer as taking movement from an existing video and applying it to a new character or scene. That requires a video reference; two portraits alone do not specify the original choreography.

Plan a two-photo duet

  1. Choose one photo per person

    Use adult subjects who agreed to appear. Pick a clear face and visible shoulders or upper body. Our photo and prompt guide gives you a short checklist.

  2. Keep the scene simple

    Start with two people, one microphone, an orange background and a steady camera. Decide who stands on each side and ask for one short exchange.

  3. Generate, then inspect

    Once generation is available, this studio is configured for a 5-second, vertical 9:16, 480p silent clip. Review the faces and movement before downloading or posting.

What you can try here today

The photo setup lets you choose and remove photos on your device.

Add sound when you post

This studio’s planned output has no audio. Upload your downloaded clip in your social app, choose an available sound, and preview the timing before posting. The video does not promise lyrics synchronized to lip movement.

Music availability depends on the account and region. TikTok explains that business accounts use its Commercial Music Library when adding sound. Check the sound available for your intended use in the app. TikTok’s music library guide explains the account and region settings.

Check the result before you share it

  • Do both people remain recognizable from the first frame to the last?
  • Do the hands, microphone and cable stay coherent as they move?
  • Is the camera steady, with both people visible in the vertical frame?
  • Does the chosen audio fit the short exchange, without suggesting exact lip sync?

If you want exact movements, revisit the workflow choice before spending time on repeated photo-only generations.

For current format, photo handling and generation availability, see the studio FAQ.