Generate the viral two-person booth format without learning video prompting. LobbyBooth combines two identity references with a fixed performance scene and renders a ten-second widescreen clip.
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.
General AI video tools expose dozens of models, ratios, resolutions, motion controls, and prompt fields. That flexibility is useful for filmmaking but slows down a trend workflow. This generator narrows the choices to the ones that affect the result: the two subjects.
The production path runs a reference-to-video model against a fixed studio plate: both uploaded photos are sent as identity references and the prompt keeps each performer on one side. The ten-second duration gives the motion time to settle without making a short social clip unnecessarily expensive.
Generation runs as an asynchronous task. After submission, the interface shows a processing card and polls for status instead of holding the browser request open. When the provider reports success, the video appears in Recent Creations. System failures and timeouts restore the reserved video automatically.
Three steps, no settings. The generator handles the scene for you.
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 generator uses a single fixed orange-booth scene rather than a template gallery. The set, the hanging microphone and the camera path all come from the same plate, so the only inputs are your two photos, which keeps results consistent between runs.
A stable preset lets the backend validate duration, resolution, media count, and model support before it reserves a video. It also makes failures easier to diagnose. If a result swaps faces, the first fix is usually a better source photo, not a longer prompt. Clear inputs and fixed roles outperform extra adjectives.
One-time packs start with one 10-second 720p video and scale to three or ten videos. Purchased videos never expire.
Ready to make your own? Open the hotel lobby ai video generator and turn two photos into a ten-second clip.
Two photos and one video from your pack. Upload one person or pet per photo, press generate, and the first photo is placed on the left and the second on the right. There is no prompt, model or aspect-ratio setting.
Usually a few minutes. You can leave the page - the clip is saved to your creations, and the video is only consumed once the render completes.
The reserved video returns to your balance automatically, including refusals by the provider's content-safety check. You are only charged for clips you actually receive.
