Your photos. The orange booth.

Hotel Lobby AI generator: put yourself in the orange booth

Upload one portrait for a solo performance or two separate portraits for a duo. The preset sets the orange studio, suspended microphone, subtle performance movement and 9:16 format for you.

Free to try: one eligible 4-second, 768p MiniMax H3 guest preview. Longer clips use credits.

Upload photos and choose your template

Two friends, one suspended microphone, alternating gestures. Start with two separate clear portraits. The 4-second starter uses MiniMax H3. Review the generated audio and add your chosen platform sound after downloading.

698/2000
Aspect ratio

How to make your Hotel Lobby video

Choose a template, add the required photos in the workbench above, then generate. The starter preset selects MiniMax H3, 4 seconds, 768p, default audio settings and vertical framing. You can review the prompt before submitting.

  • Upload the left performer as Image 1 and the right performer as Image 2.
  • Keep the default short draft for your first attempt.
  • Watch the result, check faces and hands, then download your MP4.

A direct photo-to-video workflow

Your photos stay in the workbench while you adjust the template. Upload validation, generation status, retry handling and private downloads use the same Vidloop workflow as the main tool. No green screen or manual scene setup is needed.

Check your result before posting

Compare each generated face with its source, look for crossed arms or merged bodies, and check that the mic and backdrop stay consistent. If the model swaps the subjects, simplify the gesture and keep the left/right instructions. Add the platform sound after the visual draft is approved.

Hotel Lobby AI FAQ

What photos work best?

Use a sharp, well-lit photo of each person, with one person per image and the face unobstructed. Similar camera angles and lighting help a duo. A wider portrait with shoulders and hands visible gives the model more information than a tightly cropped selfie. JPG, PNG and WebP up to 10 MB per image are supported.

Will it copy the original performance exactly?

These presets generate a new orange-studio performance from your photos. Faces, gestures and timing can vary. They do not transfer the original choreography, reproduce an exact frame-for-frame performance or guarantee synchronized lips.

Does the video include the Hotel Lobby song?

The prompt requests a silent performance; generated audio may still be present. After downloading your clip, choose the licensed sound available to your account inside TikTok, Instagram or YouTube. Music availability and permitted uses depend on the platform, region and account.

What video do I receive?

A short generated MP4 in vertical 9:16 framing. The starter setup uses 4 seconds and 768p. Review both faces and hands before posting; higher resolutions and longer durations may require sign-in and credits. Rendering time depends on the provider queue and is not guaranteed.

Updated October 2, 2026. Model availability and trial eligibility are checked when you generate.