Hotel Lobby AI Video: How to Make One

A hotel lobby AI video takes two photos and returns a short clip of those two subjects trading turns in front of a flat orange backdrop, one microphone hanging between them. On our platform that is a reference-to-video job: 242 credits for ten seconds at 720p, or 34 credits for a five-second draft to check the setup first. The rest of this post is the setup, a prompt to start from, and what the clip will not do.

Prices and specs verified 2026-10-08 against our production model catalogue.

What is a hotel lobby AI video, and why does it have nothing to do with hotels?

It is a remix format, and the name is borrowed from a song. The look comes from a 2022 COLORS performance of "Hotel Lobby": saturated orange studio, one hanging microphone, two performers alternating, a camera that does not move. Dreamina's guide to the trend describes the same fixed ingredients, and AI IDE List's explainer notes that the phrase rarely refers to an actual hotel lobby any more.

Creators drop in friends, couples, pets and fictional characters. That substitution is the whole trend, and it is why the content works as a template: the scene is fixed, only the two subjects change.

Interest is already past its peak. Google Trends data for the phrase shows it rising from 20 September, topping out around 25 and 26 September, and falling to roughly a tenth of that peak by 6 October. If you want to ride it, do it this week.

How do you make a hotel lobby AI video?

Use reference mode with two single-subject photos. Each photo should show one person or one animal, well lit, face visible, with nothing else competing for the frame.

1. Open the hotel lobby generator, which is reference mode on Seedance 2.0 with the 9:16 frame and the prompt below already filled in. (The general reference-to-video page works too if you want to pick the model yourself.)
2. Upload the left performer first and the right performer second. The order matters, because the prompt refers to them by number.
3. Set the frame to 9:16, which is the shape the trend is posted in.
4. Paste a prompt that fixes four things: where each subject stands, the orange studio, the single microphone, and the turn-taking.
5. Run a cheap draft before the final.

Here is a prompt to start from. It is our own wording and contains no real names and no song title. We rendered it once on this site, using a generated tabby cat and corgi as the two references, at 9:16, 720p and ten seconds; you can watch that clip on the hotel lobby generator page. It is one take, not a guarantee, so treat the prompt as a starting point:

@Image1 stands on the left and @Image2 stands on the right of a seamless saturated orange studio, a single vintage microphone hanging from the ceiling between them. Static locked-off wide shot, both subjects fully in frame, no camera movement and no cuts. @Image1 performs first with confident hand gestures toward the camera while @Image2 nods along, then they swap roles. Both keep the exact faces and clothing from their reference photos. No on-screen text, no logos.

The @Image1 and @Image2 tags are how our reference mode ties each photo to a part of the scene. Details are on the Seedance 2.0 page.

What does a hotel lobby AI video cost?

Credits come straight from upstream cost (one credit is one cent of compute), and the same function the generator calls before submission produced these figures for a 9:16 frame with two reference images.

Two things in that table are worth knowing before you pay.

Seedance bills by pixels, not by the clip. A 9:16 frame costs exactly what a 16:9 frame costs, because the pixel count is the same, while a square crop is cheaper. The mechanism is explained in our MiniMax H3 vs Seedance cost breakdown.

Reference mode on Seedance 2.0 tops out at 720p. It runs on the fast tier, so there is no 1080p or 4K option for this kind of job.

In currency, our credits cost between roughly $0.033 and $0.046 each depending on the plan or pack, which puts the 242-credit take at about $8 to $11. The $28 pack gives 560 credits, enough for two final takes. Current rates are on the pricing page.

For comparison, Renoise's page lists a free clip as 4 seconds at 480p and vertical, with a watermark, on Seedance 2.0 Mini. Other sites sell one 10-second vertical video for about $5 to $10. Our range sits in the same neighbourhood and carries no watermark.

How should you test before spending 242 credits?

Run a 5-second draft on Seedance 2.0 Mini at 480p for 34 credits. Look for the failures that waste a final render:

• Faces merging or swapping. The two subjects blend into one person, or the left subject turns into the right.
• Side switching. Subjects change places mid-clip when the roles swap.
• Hands and feet. Extra fingers, feet that disappear into the floor.
• Both performing at once. The turn-taking collapses into a double act.

Use the draft to judge composition and who ends up where, not final quality. In our own small comparison of Mini against the standard tier, Mini fell behind on lighting and on how cleanly motion resolved. That test was three clips, so it is a caution, not a measurement. If the draft is wrong, fix the prompt rather than raising the resolution, because a higher resolution does not repair a wrong layout.

What will a hotel lobby AI video not do?

A few honest limits, because some of what you find online promises more.

• It will not reproduce the original performance. Our generator creates new clips from reference images and a prompt. It cannot take existing footage and replace the people in it, so you will not get the original choreography or camera work.
• It will not include the song. We do not generate or license the original track. Seedance can generate its own sound if you turn audio on, and it is off by default. For a specific song, add it afterwards in TikTok or Reels.
• It will not check who is in your photo. Moderation on our side screens for NSFW content, not for identity. Use your own photos or ones from people who agreed to appear, and skip celebrities and minors. Some pages on this trend ask for the same.
• No API. The generate endpoint only accepts a signed-in browser session.
• It is not free. A local model would be, but every render here costs credits.

Which model should you pick for a hotel lobby AI video?

Pick Seedance 2.0 at 720p for the final, with Seedance 2.0 Mini at 480p for drafts. Both are available without a subscription, and both take up to nine reference images, far more than this trend needs.

Seedance 2.5 accepts up to 30 references and longer clips. That is overkill for two subjects, and it needs a subscription, at 463 credits for the same ten seconds. Reserve it for scenes with many reference subjects, such as a group version. The Seedance 2.5 page covers when it is worth the extra credits.

If you are after the other two-photo trend of the moment, the Raindance AI video guide uses the same reference-mode workflow with a pier-and-rain scene.