Separate left and right references
Upload one portrait per role, check the thumbnails, and swap positions before submitting.
Put your duo in the orange booth. Add a photo for each performer and create an original rap exchange with a hanging microphone, rhythmic gestures and a fresh beat.
Two-photo duet · Original AI audioFollow progress, watch your results, download MP4s or share from your device. These creations are private to your account.
Loading…
Hotel Lobby AI here is a two-photo, orange-booth rap video template. A minimalist warm backdrop, a suspended silver microphone and a clear two-person frame let the performers carry the scene. It is a performance look, rather than a literal hotel-interior tour.
The first image guides the left performer and the second guides the right. The preset asks them to trade short lines, react independently and keep both faces visible. H3 or Seedance 2.5 creates a new performance with original synthetic vocals and music; exact identity matching, words and gestures can vary.
The public preview above is an existing original orange-stage Rap Video AI example. The Hotel Lobby preset uses a center hanging microphone for new generations; the preview is not a remake of the original song or a demonstration of exact choreography transfer.
Upload one portrait per role, check the thumbnails, and swap positions before submitting.
Orange walls and floor, a center hanging mic and a steady two-person shot are built into the prompt.
The model generates a new beat and synthetic rap vocals alongside the performance. Download the result as MP4.
Put one person, character or pet in each image. Use the left and right upload boxes to set the cast. Demo portraits are available if you want to explore first.
Choose Classic duo, Birthday shout-out or Friendly rap battle. You can generate with the preset alone, or add names, a topic and short original lyrics. Select English or Chinese vocals.
Choose H3 or Seedance 2.5 directly, then open the settings to adjust duration, resolution and format. The default H3, 768P, 5 seconds and 9:16 costs 120 credits; Seedance 2.5 at 480P for 5 seconds costs 153 credits. The displayed quote applies to your current selection.
Sign in and generate. Follow progress on this page or in My videos. Buy credits if needed and return here to continue. Play the finished clip with sound, then download the MP4 or use the device share menu.
Credit cost changes with model, duration and resolution. New verified accounts can use their active 120-credit welcome grant for the default H3 5-second setting, subject to the welcome offer's validity and usage limit. Purchases from this page return here, and the device draft keeps your photos and settings. Confirmed failed jobs return their credits. Your generated videos stay in your private history; sharing a caption links to this creator without exposing a private video URL.
No. Upload two photos and use a performance template. A topic or original lyrics are optional; the scene, composition and action directions are already prepared.
Yes. Upload a portrait in each slot. Different outfits or expressions help make the two roles easier to distinguish. You can swap their positions before submitting.
It creates original AI music and synthetic vocals. It does not supply the original commercial recording, reproduce its exact choreography or clone a named artist's voice.
JPG, PNG and WebP up to 10 MB per photo, with both dimensions at least 256 px and neither over 5,760 px. The upload is resized automatically. Use photos you have permission to use.
No. The model creates a new video from character references. Appearance, lip movements, lyrics and the set can vary; there is no frame-for-frame replacement of an existing performance.
Yes. After successful generation, download an MP4 from this page or My videos. Compatible devices can share the file directly; otherwise download and upload it to your chosen social platform.