Hotel Lobby AI Prompt: The Exact Prompt Our Generator Uses

On a Seedance model with the AI rap sound, no track is attached: the model writes the song itself. The reference clip goes up without its sound, so the model copies the moves and the booth but not the Hotel Lobby recording. Attachments are named in words (“reference image 1”), because kie documents no mention syntax for Seedance. This one is for the example topic below.

Recreate reference video 1 shot for shot: the same orange gradient backdrop with the round glowing halo behind the performers, the same single silver condenser microphone hanging from the ceiling between them, the same camera framing, timing and every movement, 9:16.

Performer on the left: the man from reference image 1. Performer on the right: the woman from reference image 2. Keep each person's face, hairstyle and outfit exactly as in their photo. Use only the people from the photos; ignore the photo backgrounds completely.

Soundtrack: an original hip-hop song made for this video, a punchy trap beat with deep bass and crisp hi-hats. The left performer raps an original, clean verse into the hanging microphone about: "Maya’s 30th birthday and her terrible parallel parking". Rap in the language of that topic. Clear rap vocals, lips in sync with every word, natural head nods and expressive mouth movement. The right performer is the hype partner: she points at the rapper, reacts, smiles and adds short ad-libs on the beat. Do not use any existing song, existing lyrics or the voice of any real artist. Around the 7-second mark the camera pulls back to a wider waist-up shot and she does a short playful dance move, as in reference video 1.

Single continuous shot. No split screen, no extra people, no captions or text on screen. Faces stay consistent from start to end.

1. The scene. “Recreate @Video1 shot for shot” hands the booth, the camera and the timing to the reference clip, and the prompt names the parts that matter most: the orange gradient backdrop, the round glowing halo and one silver condenser microphone hanging between the performers.
2. The identities. Each photo is tied to one side, and the model is told to keep face, hairstyle and outfit and to ignore the photo backgrounds. Without this line, performers swap sides or wear the reference clip’s clothes.
3. The roles. The left performer raps into the mic, lip-syncing to the audio; the right one is the hype partner who points, reacts and mouths only short ad-libs. Clips of 8 seconds or more add the camera pull-back and a short dance near the 7-second mark, as in the reference.
4. The guard rails. One continuous shot, no split screen, no extra people, no captions, faces consistent from start to end. These stop the most common failures.

• It needs a model that accepts reference images and a reference video, and ideally a reference audio track. MiniMax H3 reference-to-video and ByteDance Seedance 2.x take all three.
• Change the mentions to your tool’s syntax. We write @Image1 and @Video1; some tools expect “Image 1” and “Video 1”, others their own tags. Keep the order: left photo first, right photo second.
• Change the performer nouns. Our generator swaps only “man” and “woman” and the matching he or she; every other word stays fixed so results are comparable.
• Change the shape in the first line (9:16, 16:9, 1:1) to match the format you pick in the tool.
• Without a reference clip, describe the booth and the moves in words instead of “Recreate @Video1”. Tools such as Dreamina publish their own text-only prompts for this. We have only tested the version above.

On Hotel Lobby Video this prompt, the reference clip and the reference track are built in. You add two photos, pick He or She for each spot, and create. The first preview is free: one HD video of up to 12 seconds, with a watermark, once per Google account.