Hotel lobby AI video generator
Upload two photos and get the hotel lobby AI video look: two people or pets in a flat orange studio, one microphone hanging between them, taking turns to perform. The prompt below is already filled in and the frame is set to vertical 9:16. Swap in your two photos, run a cheap draft, then the final take.
Made with this model
Every clip below was rendered here, on the settings shown under it. The caption is the exact prompt that produced it.
Seedance 2.0 · 720p · 9:16 · 10s
Make one in three steps
Upload two single-subject photos
Left performer first, right performer second, because the prompt calls them @Image1 and @Image2. One person or one animal per photo, well lit, face visible, nothing else competing for the frame.
Keep the prompt, change only what you must
The prompt is a starting point, not a tested recipe. It fixes four things: where each subject stands, the orange studio, the single microphone and the turn-taking. Leave those alone and edit the gestures or the mood.
Draft at 480p, then go to 720p
A five-second 480p draft is 54 credits. Look at who ends up where before you pay for the 242-credit ten-second take at 720p.
Specs at a glance
| Model | Duration | Resolution | Native audio | Reference images | From |
|---|---|---|---|---|---|
| Seedance 2.0 | 4–15 seconds | 480p · 720p | Yes | Up to 9 | 31 credits for 5 seconds |
Why it has nothing to do with hotels
The name is borrowed from a song. The look comes from a 2022 COLORS performance: saturated orange studio, one hanging microphone, two performers alternating, a camera that does not move. Creators kept those ingredients and swapped the performers, so the scene is fixed and only the two subjects change.
That is why it works as a template, and why it ages fast. Interest in the phrase has already fallen well below its late-September peak, so if you want to make one, do it soon.
The prompt on this page is our own wording, with no real names and no song title. The sample above was rendered on this site from that exact prompt, using two generated reference photos, at 9:16, 720p and ten seconds. It is the first take we ran, not a pick from several, and your own photos will not give the same result, so treat the prompt as a starting point to iterate on.
Read the full hotel lobby guideWhat a hotel lobby clip costs here
Seedance bills by pixels, not by the clip, so a vertical 9:16 frame costs exactly what a 16:9 frame does at the same length, while a square crop is cheaper. For two reference images on Seedance 2.0: 54 credits for five seconds at 480p, 108 for ten seconds at 480p, 242 for ten seconds at 720p.
In currency our credits cost roughly 3.3 to 4.6 cents each depending on the plan or pack, so the 242-credit take is about $8 to $11. Figures checked against the model catalogue on 13 October 2026.
Seedance 2.0 is open to any signed-in account. If you only want to test a layout, the cheaper Seedance 2.0 Mini draft is available in the general reference-to-video generator at 34 credits for five seconds.
See credit packs and plansWhat it will not do
It will not reproduce the original performance. This generator creates new clips from reference images and a prompt, so you will not get the original choreography or camera work, and it cannot put your face into existing footage.
It will not include the song. Seedance can generate its own sound when audio is on, and it is off by default. Add a specific track afterwards in TikTok or Reels.
It will not check who is in your photo. Use your own photos, or ones from people who agreed to appear, and skip celebrities and minors.
How reference to video worksWhat to check in the draft
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, or feet that disappear into the floor.
Both performing at once. The turn-taking collapses into a double act. Fix the prompt, not the resolution: a higher resolution does not repair a wrong layout.