Use the Hotel Lobby AI filter to place two people or pets in an original orange performance booth. The tool handles the scene prompt for you, so the only creative decision is who appears in the duet.
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.
The Hotel Lobby filter is designed around one recognizable transformation: two separate portraits become a short widescreen performance in a warm orange studio. Unlike a general video editor, it does not ask you to mask subjects, keyframe movement, describe camera physics, or write a long prompt. The template already contains the visual direction.
The first image is treated as the performer on the left and the second as the performer on the right. That simple assignment matters because the most common failure in this trend is identity drift. Clear role labels, separate references, and a steady camera give the video model fewer reasons to blend facial details between subjects.
For best results, use portraits with open eyes, visible hairlines, and similar framing. Avoid screenshots with text, photos where another face appears in the background, or images with strong beauty filters. The result is meant for short-form social posting, so the default output uses a widescreen 16:9 frame.
The filter is one action, not an editing session: pick the pair, upload, render.
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 filter uses an original warm orange set with a single hanging microphone and restrained performance movement. People and pets both work because the two source photos carry the identities. The backdrop is built for this tool rather than taken from an existing music performance.
A filter should remove decisions, not add them. LobbyBooth fixes the scene, duration, aspect ratio, and model settings while leaving the subject choice to you. This makes results easier to compare and gives the generation backend a repeatable target. Two separate photos also produce more reliable identities than asking a model to interpret a crowded group picture.
One-time packs suit a single post or a small batch. Larger packs lower the price per video, and unused videos stay in your account.
Ready to make your own? Open the hotel lobby ai filter and turn two photos into a ten-second clip.
The look is the same - two people facing each other in an orange booth with a hanging microphone - but this is not an in-app filter. It renders a standalone ten-second clip you can post anywhere, from two photos you upload.
Any clear, front-facing photo works: one person per photo, eyes visible, no sunglasses or heavy beauty filters. The booth, lighting, camera move and music come from our fixed plate, so only the performers change.
Not yet. The workflow is built around two still photos, because that is what keeps identities stable across the clip. If you want to test a pair, the single video pack is the cheapest way to see the result.
