Two portrait photos. One 10-second duo performance with original audio. Check your credit estimate before generating.
Generator examples
Two portraits → one performance
Hotel Lobby AI: watch the duo replacement
These two AI-created adult portraits are the actual inputs to the sample. Watch how the blue overshirt and burgundy jacket carry into the performance. They are separate identity references, not a combined face or a new character description.
Hotel Lobby AI is built around one recognizable performance: two people in an orange booth beneath a hanging microphone. The goal is to change the performers while keeping the scene recognizable. Play the clip with sound, then compare both portraits against the opening, the middle cut and the ending. The landscape example above shows what one successful run produced.
Review your hotel lobby video across the cuts
A convincing first frame is only the start. Hotel Lobby AI needs to carry both people through movement, changes of angle and quick transitions. Use the player to pause at three points and check the result as a short performance rather than judging it from the poster alone.
- Opening
Confirm the two identities
Check that photo one maps to the initially left performer and photo two maps to the initially right performer. Compare the face shape, hair and clothing separately for each person. The intended assignment stays with the performer even if the camera changes position.
- Mid-cut
Look through the movement
Pause around a gesture or transition. Hands, accessories and clothing edges are useful clues when faces move quickly. A hotel lobby video should feel like one continuous duo performance, so check for merged faces, suddenly changed outfits or a person appearing twice.
- Ending
Watch the full finish with sound
Let the final seconds play rather than stopping after the first good shot. Check both identities again and listen for the original performance audio. Download the completed file only after you have reviewed the full clip at its natural speed.
Give Hotel Lobby AI two readable portraits
Each uploaded photo has a different job. The first defines one performer; the second defines the other. Choose a recent image with a visible face and enough clothing to communicate the look you want. You do not need matching backgrounds because the hotel lobby video follows the fixed booth scene.
- One person per file. Separate references reduce ambiguity. If your starting image contains a pair, prepare an individual crop of each person before uploading.
- Keep faces clear. Avoid strong motion blur, heavy filters, sunglasses that conceal the eyes or another person crossing the face. Even lighting makes facial details easier to read.
- Leave some clothing visible. A chest-up portrait communicates more than a tiny face crop. Distinct outfits also help you judge which identity is assigned to each performer.
- Check the upload order. Review both thumbnails before submitting. Fix the order first; writing a longer description is not part of this fixed-template workflow.
If a source picture needs a simpler crop or cleanup, prepare it in the AI photo editor and return with the two finished portraits. Keep changes modest: the aim is a clear reference that still looks like the intended person. Upload photos of people who have agreed to appear.
Choose the hotel lobby video frame before generating
9:16 · portrait
Choose this for a tall phone-screen composition. Hotel Lobby AI requests a portrait result while retaining the duo-performance brief. Review both people near the edges and during movement; a tall frame leaves less horizontal room than the landscape sample. This setting generates a new composition and is not a preview crop.
16:9 · landscape
Choose this for a wide frame, like the real example on this page. It gives you a horizontal view of the booth and the pair. It can suit a desktop player or a wider edit. Check the finished file in the place you intend to share it instead of assuming another platform will preserve its framing.
Both choices use the same fixed 10-second workflow and the current Voor credit estimate. Pick the format before submitting. If you want both formats, they are separate generations, so review the first result before spending credits on another. The example proves the landscape run shown here; individual portrait results may differ.
From portraits to a Hotel Lobby AI result
Sign in to Voor, upload the two portraits in order and choose your frame. Check the displayed credit estimate before selecting Generate. There is no template video to find, no soundtrack to attach and no long replacement prompt to compose. The fixed workflow supplies those parts so you can focus on the people.
Your hotel lobby video uses the same task status, result player and history as other Voor creations. Wait for the current task to resolve before submitting another one. When it finishes, review the video with sound and download the MP4 from the result. If you return later, look for the task in your history rather than creating another copy.
Hotel Lobby AI suits friends, consenting couples and fictional character pairs when the orange-booth performance is the desired outcome. It does not create a custom hotel advertisement, a new dance routine or new spoken dialogue. For your own reference movement, choose AI motion control. For a different scene from a still photo, explore image-to-video generation.
Before sharing, check identity consistency, framing and the audio in the downloaded file. Avoid representing an AI performance as a real recording of someone. Hotel Lobby AI is an independent creative workflow; the song and performance are not a claim of affiliation with their artists.
Hotel Lobby AI questions
What does Hotel Lobby AI make?
Hotel Lobby AI makes a 10-second duo performance video from two portrait photos. It replaces the two performers in a fixed orange-booth scene while following the original movement, camera cuts and audio. It is a specific character replacement workflow, rather than a generator for hotel interiors or room tours.
How do I make a hotel lobby video with two people?
Upload two separate photos with one person clearly visible in each. Put the person you want on the initially left side first, then add the person for the initially right side. Choose portrait or landscape, check the credit estimate and generate. Review faces across the whole clip before downloading the MP4.
Can Hotel Lobby AI use a single couple photo?
This workflow requires two separate portrait files. Crop each person into their own image before uploading, keeping the face, hairstyle and some clothing visible. Avoid feeding the same group photo into both slots: a separate reference for each performer gives the system a clearer identity assignment.
Does the hotel lobby video include audio?
The workflow requests the original performance audio. You do not need to upload a soundtrack or record a voice. It does not clone either person's voice or make them speak a custom script. Listen to the completed video before sharing, and check the platform's music rules for your intended use.
What does Hotel Lobby AI cost on Voor?
The generator shows the current Voor credit estimate before you submit. A clip is fixed at 10 seconds, with the same estimate for portrait and landscape. Each new generation is a separate task; changing your photos and generating again uses another estimate. This page does not promise a free full video.
Which hotel lobby video formats can I choose?
Choose 9:16 for a portrait video or 16:9 for a landscape video before submitting. The sample on this page is a real landscape result. Format is a generation setting, so selecting portrait does not simply crop the example. Subject placement and framing can differ between outputs.
Will Hotel Lobby AI keep both faces exactly right?
The workflow asks for consistent identities, clothing and performer positions, but results can vary. Clear individual portraits help. Check fast cuts, profiles, hands and the final frame for distortion or identity drift. The example demonstrates one successful result, not a guarantee that every photo pair will match perfectly.
Can I change the hotel lobby video background or choreography?
This page uses a fixed performance template. The orange booth, hanging microphone, original movement and edit timing are the intended structure. For your own motion clip, use a motion-control workflow instead. For a new scene described in words, use a general text-to-video generator.
Where do I find my Hotel Lobby AI result?
Sign in to generate using your Voor account. The task runs through the normal Voor generation workflow, with status and completed results in your history. Wait for the task to finish before trying again. Once complete, play the result and use its download action to save the MP4.
Create your hotel lobby video
Choose two clear portraits, select a format and check the Voor credit estimate.
Make my duo video