Hotel Lobby AI Video Generator

Drop in two photos — you and your best friend, your partner, your sibling — and they take over the orange room from the Hotel Lobby performance. Same mic, same moves, same back-and-forth.

  • 2 photos · one per performer
  • 15 seconds · 720p
  • Vertical, square or wide
  • Original audio
AI example
Left · photo 1Right · photo 2

Two original characters dropped into the orange-room routine with the original audio. These two photos went in; yours take the same left and right spots.

Add two photos · one person each

One subject per photo · JPG, PNG or WebP · Up to 10MB each. Drop photos into the boxes or click to upload.

Format

15 s · 720p · Original audio

Sign in after adding your photos.

Only use photos you’re allowed to use. It takes a few minutes. You can leave, it’ll be in History.

What goes in, what comes out

Hotel Lobby AI video examples

Under each video are the two photos that went in. Both pairs are characters we made for this page.

Two strangers, one mic

He takes the left, she takes the right. Their outfits carry over, and they hit the same turn on the same beat.

Original man portrait in a burgundy overshirt
Left
Original woman portrait in a blue denim jacket
Right

Photo 1 goes left,
photo 2 goes right.

Red panda meets snow leopard

A red panda and a snow leopard run through the arm reach, the watch check and the spin.

Original red panda character in a green varsity jacket
Left
Original snow leopard character in a violet jacket
Right

Photo 1 goes left,
photo 2 goes right.

Your result depends on your photos. Faces and hands can shift a little from take to take.

How to make a Hotel Lobby AI video

  1. 01

    Add two photos

    One person per photo. Photo 1 ends up on the left, photo 2 on the right. Hit the swap button if you want them the other way round.

  2. 02

    Pick a frame

    Vertical 9:16 for TikTok, Reels and Shorts, square 1:1 for feeds, or widescreen 16:9. Every video is 15 seconds at 720p.

  3. 03

    Create and download

    Sign in, check the price on the button and hit create. It takes a few minutes. Grab the MP4 when it’s done.

Why it’s called Hotel Lobby

It has nothing to do with hotels. Hotel Lobby is a performance video: two rappers in an orange room, one mic hanging from the ceiling, trading lines and turning on cue. That routine is the part everyone wants to copy.

You can’t get it from a text prompt. Describe an orange room and the AI makes up its own moves. So we start from the real performance and swap in your two photos. The moves stay. The faces change.

Give each performer a clear photo

One subject per photo

Crop out anyone else in the shot. With two faces in one photo, the AI has to guess which one you meant.

Show the face

Straight on or slightly angled, in good light, no sunglasses. A far-away full-body shot gives it very little to work with.

The outfit comes too

Whatever they’re wearing in the photo is what they wear on stage. Pick the fit you want to see.

Light matters more than resolution

A sharp phone photo in daylight beats a blurry high-resolution one. Avoid heavy filters and strong shadows across the face.

Hotel Lobby video credits

One price for every video: 450 credits for 15 seconds at 720p, in any frame. The one-time $9.99 pack covers one video, and the button shows the price before anything is charged.

See credit packs and subscriptions

Hotel Lobby AI video FAQ

What is a Hotel Lobby AI video?

It’s the orange-room duet from Quavo and Takeoff’s Hotel Lobby performance (two performers, one hanging mic) remade with the two people in your photos. This is an independent tool, not affiliated with the artists or COLORS.

Why not just use a text prompt?

A prompt can give you an orange room, but the AI will invent its own moves. Starting from the real performance keeps the routine people recognize.

Which photos work best?

One clear face per photo, straight on or slightly angled, in good light. Photo 1 goes on the left and photo 2 on the right. Use the swap button to switch them.

Will it look exactly like us?

Close, but not perfect. Faces and hands can shift a bit, especially when someone turns away. Clear, well-lit photos make the biggest difference.

Which AI model does it use?

Seedance 2.0. It follows the original clip for the moves and camera and uses your two photos for the faces and outfits.

How long is the video and what size is it?

Every video is 15 seconds at 720p. Pick vertical 9:16 for TikTok, Reels and Shorts, square 1:1, or widescreen 16:9 before you create.

How many credits does it cost?

450 credits per video. The one-time $9.99 pack covers one video.

Does the video have sound?

Yes. The original audio of the routine is added to your video from the first second. Give it a quick listen before you post.

Where do I find my video later?

It shows up here when it’s done and stays in your History. Hit Download MP4 to save it.

Pick the two stars of your next duet

Add your photos