The Hotel Lobby AI template is one fixed orange booth that works for friends, couples, or pets. Upload two clear photos and the scene, staging, camera direction, and identity handling are applied for you.
10s
10-second widescreen clip
16:9 / 720P
Ready for short-form posts
1
Technical failures are refunded
Two photos in. One duet video out.
Add two people or pets
Use clear, front-facing photos with one subject in each image. JPG, PNG, or WebP up to 5MB.
Upload 0 of 2 photos
Generated with Seedance 2.0 Mini
Built for two distinct identities
Reference-to-video keeps each subject anchored to a side of the scene to reduce face swapping.
A useful Hotel Lobby template is more than an orange background. It defines where each performer stands, which direction they face, how the microphones are placed, how much camera motion is allowed, and how the model should protect each identity. Those constraints turn a broad video model into a focused trend generator.
The booth uses a medium-wide locked composition with one hanging microphone, which keeps the left and right roles stable. Friend pairs work best with conversational gestures, and pet references work because distinct markings give the model strong anchors.
The booth does not include copyrighted performance footage or music. The stage image is original, and audio is not copied from the trend. If you want a soundtrack, add audio you created or have permission to use after downloading the video. This keeps the visual joke recognizable without depending on protected source material.
The template is already applied - these three steps are all you run.
Start with two portraits that are similar in crop and lighting. Each photo should show one person or pet. A calm front-facing image gives the model a stronger identity reference than a busy group shot or a frame taken during fast motion.
Place the intended left performer first and the right performer second. The generator preserves that assignment in its internal prompt. Files are checked before generation, and technical failures return the consumed video automatically.
Upload two photos and LobbyBooth renders the clip in the background from a fixed orange-booth scene, then shows the live task state with a download action when it finishes.
The default setup: warm orange backdrop, hanging microphone, locked medium-wide camera. It is the most stable pairing, which is why most examples on this site use it.
Two subjects staged left and right, trading lines. Any pair works - friends, siblings, a couple, colleagues - because the template only fixes the scene, not who is in it.
The same booth with animals instead of people. Fur markings, proportions and eye colour carry over from the photos, so a cat and a dog still look like themselves.
One booth serves every render: upload two portraits and the model keeps the scene, the hanging microphone and the camera path fixed. Separate, well-lit photos of the same kind of subject give the most stable result. More scene variants can be added later without changing the two-photo workflow.
Reference-to-video works best when the target scene is specific. A fixed backdrop and clear stage blocking reduce visual uncertainty, while two independent reference images give the model enough information to preserve faces, clothing, or fur. The template controls the scene so your photos remain the main variable.
Every pack works with the current orange booth. A small one-time pack is usually enough for a single pair, and failed technical jobs restore their video automatically.
Ready to make your own? Open the hotel lobby ai template and turn two photos into a ten-second clip.
No. There is one scene - the orange booth - and it is applied automatically. "Template" here means the fixed setup: backdrop, hanging microphone, camera move and music. It is not a design you assemble.
Not currently. Every render uses the same plate so results stay predictable. A different scene would mean a different plate and a new model pass, which we have not shipped.
They differ by who steps into the booth - friends, a couple, pets or characters - not by the scene itself. Pick the example closest to your photos and follow the same three steps.
