Skip to content

How to Use Your Own Reference Video for Hotel Lobby AI

Short answer: yes. Under Soundtrack & moves, choose Your clip and upload a video. The two people from your photos copy the clip’s moves, gestures and camera movement in the orange booth or on another stage, and the clip’s background is replaced. The video is as long as the part you use, 2 to 15 seconds, and a 10-second video on Wan 3.0 at 480p is 5 credits.

It is a good fit for filming your own take on the routine. On October 1, 2026, Victoria Monét and Quavo re-shot the booth themselves, captioned “No AI” (Revolt via Yahoo); a clip like that, filmed by you, can be the moves for your two photos. We checked the upload, trimming and pricing steps on October 5 with a 10-second clip of two AI-made dancers we made ourselves. We have not yet published a finished video from an uploaded clip.

Updated

Illustration of a video clip with a play button, an arrow and a two-person booth.

HOTEL LOBBY AI · YOUR OWN MOVES

Your clip, their faces

  • Your clip
  • Your photos
  • Booth video
AI · Illustration · Hotel Lobby Video

What the photos, the clip and the sound each control

InputWhat it decidesWhat it does not decide
Your two photosWho performs: faces, hair, clothesThe moves
Your clipThe moves, gestures, head turns, timing and camera movementWho appears or where: its people and background are replaced
The stageThe set: the orange booth or another stageThe moves
The soundWhat the left person lip-syncs to on Wan 3.0, or an AI rap on SeedanceThe moves
Two photos decide who performs, your clip decides the moves and the camera, the sound decides what the left person raps. All go into one booth video.
Two photos decide who performs, your clip decides the moves and the camera, the sound decides what the left person raps. All go into one booth video.Our illustration, not a real video frame · 2026-10-05

Bring your moves

Upload your clip here

Add the two photos, then open Soundtrack & moves and choose Your clip. The length buttons show the credits.

1

Your two performers

One person each. Left raps, right hypes.

2

Stage

3

Video & sound

This video: 6 credits. Ready in about 5 to 15 minutes; failed generations return your credits. View pricing

Prepare a clip that works

  • The file can be any length; 2 to 15 seconds of it are used.
  • MP4 or MOV, as your phone camera records it. Clips that are too large or too fast are converted in your browser.
  • Normal speed: slow-motion clips do not work.
  • Two people side by side, full body, facing the camera. The right performer follows the second person in your clip.
  • A steady camera. Camera movement and cuts are copied too.
  • A clip you filmed or have the right to use. Avoid clips of famous people: when our booth was re-shot from the original performance, some test videos took on the performers’ faces.

Upload the clip and pick the sound

  1. Add your two photos. Use full-length photos: with Your clip, the photos are not redrawn first.
  2. Tap Change on the sound row and choose Your clip under Moves, then upload the video.
  3. If the clip is longer than the video, drag the orange frame to the part you want. The length buttons show the credits for each length your clip allows.
  4. Pick the sound: Your clip’s sound (picked first when the clip has sound), the Hotel Lobby track or Your song. A clip without sound falls back to the Hotel Lobby track. On a Seedance model, the sound is an AI rap.
  5. Check the format. Picking Your clip switches it to Match clip, the shape closest to your clip.
  6. Tap Create video.
1: a 10-second clip of two AI-made dancers loaded as Your clip, with the lengths it allows and their credits. 2: the editor afterwards, set to 9:16 to match the clip, 5 credits for 10 seconds.
1: a 10-second clip of two AI-made dancers loaded as Your clip, with the lengths it allows and their credits. 2: the editor afterwards, set to 9:16 to match the clip, 5 credits for 10 seconds.Actual interface, English · 2026-10-05

Price and wait with your own clip

Part of the clip usedWan 3.0 480pWan 3.0 720p
Up to 5 seconds3 credits4 credits
About 8 seconds4 credits6 credits
About 10 seconds5 credits8 credits
About 12 seconds6 credits10 credits
About 15 seconds7 credits12 credits

A part between two lengths is priced at the next length up. The stage and the sound do not change the price. A Wan 3.0 video is usually ready in about 5 to 15 minutes.

What to expect from a reference video

  • The model is asked to copy the moves, gestures, timing and camera. We have not measured how closely it follows an uploaded clip.
  • Cuts are copied. When our built-in clip had a cut every few seconds, every test video had the same cuts.
  • Faces in the clip can leak into the result, as the original performers did in our early tests. Use clips of people who agreed to it.
  • With only one person in your clip, the right performer has nobody to follow. We have not tested that case.
  • The clip’s background never shows: the stage replaces it.

Your clip or the built-in Hotel Lobby routine?

Use the built-in routine whenUse your own clip when
You want the trend’s exact look and movesYou want another dance, a skit or your own take on the routine
You only have face photos (the redraw fills in the body)You have full-length photos of both people
You want the Hotel Lobby track to line up with the movesYour clip has its own sound, or you bring your own song
Upload your clip

FAQ

Can I use my own video to guide the moves of two people from photos?

Yes. Choose Your clip under Soundtrack & moves and upload 2 to 15 seconds of video. The people from your photos copy its moves on the stage you pick.

Will my clip’s background show in the video?

No. The stage replaces the background; only the moves and the camera come from your clip.

Can I keep my clip’s sound?

Yes. Your clip’s sound is picked first when the clip has sound. You can switch to the Hotel Lobby track or your own song instead.

Can I use a TikTok dance as the reference?

Only a clip you filmed or have the right to use. Clips of other people can also carry their faces into the result.

Which models take my own clip?

Wan 3.0 on any stage, and the Seedance models with an AI rap.

How much does a video from my own clip cost?

The same as any video of that length: 5 credits for 10 seconds on Wan 3.0 at 480p. The sound and the stage do not change the price.

Sources

Hotel Lobby Video is an independent tool, not affiliated with Quavo, Takeoff, Migos, Quality Control Music, Motown or COLORS.