Best friends and couples
The classic format: one of you raps, the other points, laughs and dances on the beat. Good for anniversaries, birthdays and group chats.
The orange booth is open
Upload two photos. We put both people in the orange booth, under the single hanging mic, and render the Hotel Lobby rap duet. Your first preview is free.
Hotel Lobby
Orange stage, hanging mic, rap duet
One person per photo, taken any time. The lead (left) raps into the mic; the partner (right) hypes them up.
The lead lip-syncs to the Hotel Lobby track and the pair follow the booth choreography. Switch only if you want your own song or moves.
Your first preview is free. Unlock the full video for 10 credits. View pricing
The photos, the performance
Cats, chihuahuas, grandmas, anime heroes, best friends: the orange booth works with any two performers. These clips come from creators on X and other tools, credited under each one.
9:16 versions of the format from other creators.
Three steps
One clear photo per performer: the left one raps into the mic, the right one is the hype partner. Photos can be taken years apart and in different places.
Pick He or She for each spot, keep the Hotel Lobby clip or bring your own song or video, and press create. Rendering happens in the cloud, so you can close the tab.
Watch the preview. If you like it, unlock the clean MP4 with credits and post it anywhere. If a render fails, it costs nothing.
The trend, explained
The Hotel Lobby AI trend recreates Quavo and Takeoff performing their song "Hotel Lobby" on A COLORS SHOW: two people in a plain orange booth, sharing one microphone that hangs from the ceiling. People use AI to swap in themselves, friends, couples, grandparents or famous faces, then post the clip on TikTok, Reels and X.
Takeoff died in November 2022, and some fans find AI copies of the duo themselves disrespectful. This tool puts your people on the stage, not the original artists.
Read the full story of the trend →Who goes on stage
The classic format: one of you raps, the other points, laughs and dances on the beat. Good for anniversaries, birthdays and group chats.
Put grandparents, parents and kids in the booth together. The photos do not need to be from the same year or the same trip.
Upload a 2 to 15 second MP3 or WAV and the lead lip-syncs to it instead of the Hotel Lobby track. Audio uploads do not change the price.
Have a performance you want copied move for move? Upload a 2 to 15 second MP4 and the two people from your photos act it out.
Before you upload
The model copies faces, hair and outfits from your photos, so the input decides most of the result.
Works well
Skip these
Pricing
Your first preview is free. A standard 12-second HD video costs 10 credits to unlock or create. Buy a one-time pack that never expires, or subscribe.
$9.99 one-time
$9.99 per video
Checkout opens soon
$29 one-time
$5.80 per video
Checkout opens soon
$59 one-time
$2.95 per video
Checkout opens soon
$99 one-time
$1.98 per video
Checkout opens soon
$199 one-time
$1 per video
Checkout opens soon
Secure checkout by Stripe · Packs never expire · Subscriptions renew until canceled · Failed renders are never charged
Your first preview is free for every new account. It plays with a watermark. Unlocking the clean MP4 of a standard 12-second HD video costs 10 credits, and the smallest pack is 10 credits for $9.99.
No. The Hotel Lobby direction is built in: orange booth with the glowing halo, one silver mic hanging between the performers, the lead rapping and the partner hyping. You only add two photos and choose He or She for each spot.
Renders use MiniMax H3 reference-to-video. It reads your two photos, the reference clip and the reference track together, so the performers keep their own faces and outfits while copying the booth, camera and timing.
Choose a 12 or 15 second clip. Videos are 16:9 MP4 in HD (768p) or 2K. With your own reference clip, the video matches its length, from 4 to 15 seconds.
Usually 5 to 15 minutes. Most of that is waiting in the render queue; the render itself takes a few minutes. You can close the tab, and the video waits for you in My videos.
A 12-second HD video costs 10 credits and a 15-second one costs 12. 2K costs more, and a reference clip you upload is priced by its length. The exact number is shown on the button before you create anything.
Yes. Upload an MP3 or WAV of 2 to 15 seconds to change what the lead raps to, or an MP4 of 2 to 15 seconds to change the choreography. Longer files can be trimmed in the browser before upload.
You are not charged. Credits go back to your balance automatically, and if it was your free preview, you get it back too.
Uploaded photos and clips are deleted 7 days after the render finishes. Finished videos stay in My videos until you delete them or your account. Nothing is public unless you share the file yourself.
Only with their permission. Do not upload photos of people who have not agreed, of minors without a guardian, or of public figures to mislead anyone. We may remove content and accounts that break this rule.
Yes. It runs in any modern mobile or desktop browser. There is nothing to install, and you can leave the page while the video renders.
The booth is yours
Two photos in, one duet out. The first preview is on us.