Recreate the Hotel Lobby AI setup with two photos, the orange backdrop, and one hanging microphone. The familiar motion is ready; choose your cast, review sound and credits, and make your version.
Orange booth · familiar routine
Moves
Sound
Add two photos and tick the permission box to generate.
Sample clip for illustration — not generated on this site. Muted so it can play on its own.
These two photos are the inputs for the example video above.Use one clear portrait for the left lead and another for the right partner. Photos do not need matching backgrounds. JPG, PNG, and WebP are accepted up to 10 MB each. Use pictures of yourself or people who agreed to appear.
Try this step in the generatorUpload your photo references
Enlarge interface screenshotThe orange stage, built-in motion, Wan 3.0, 12-second length, and landscape format are selected initially. Check whether the audio control says built-in, uploaded, or none. A motion reference alone does not promise that a particular licensed recording will accompany the result.
Try this step in the generatorChoose the video settings
Enlarge interface screenshotReview the quoted credits, confirm your input rights, and submit after signing in. Wait for the progress display to finish, then watch with sound before saving. The generated MP4 replaces the reference preview, and the job also appears in My videos.
Try this step in the generatorConfirm and create
Enlarge interface screenshotOrange booth · familiar routine
Hotel Lobby AI describes a recognizable photo-to-video remake: two performers share an orange studio and a microphone suspended between them. The name points to the music-performance trend rather than an actual hotel reception. This page opens the same generation engine used on the homepage, already set to the orange scene and built-in routine. The reference clip makes that target visible before you spend credits. Your two portraits provide the cast; the model renders a new performance around those identities. It is not a frame-perfect face overlay, so facial details and gestures can vary.
Concept illustration · not a generated video result
Two separate portraits become the lead and supporting partner. This preset restores the orange background and reference-track mode so an earlier setting change does not accidentally send you to a different stage. The card is a concept illustration of the planned cast, not a generated result.
Concept illustration · not a generated video result
Make a family remix using portraits you have permission to use. Keep the left-and-right roles clear and choose a view of each face without other people behind them. Older or low-resolution photos may lose detail; begin with a short test rather than expecting restoration of missing features.
Concept illustration · not a generated video result
Try the routine with two stylized pet portraits while keeping the same orange stage. This is an experimental cast: paws, mouths, and body proportions can be inconsistent. The preset changes the performance inputs, not the source video into a verified animal example. Inspect the output before sharing.
The orange background, single hanging microphone, and lead-and-partner choreography establish the look. The left photo supplies the lead; the right photo supplies the person responding beside them. The prompt asks the model to take their faces, hair, and clothing from those pictures, while the reference video supplies movement. It also tells the model to leave out the original performers and burned-in captions. These are instructions to a generative model, not a guarantee of exact identity preservation. Review the whole clip for brief face changes, transferred clothing, hands, and unwanted text.
Back to this generatorThe built-in Hotel Lobby motion is shared across the rap engine. Picking Studio Booth or Street Cypher changes the requested environment; it does not load a newly filmed routine. For this template, keep the orange stage selected. You can upload your own 2–15 second MP4 or MOV motion reference if you want another routine, but that is no longer a strict recreation of the default. The credit quote accounts for uploaded reference footage differently from the built-in trimmed clip.
Built-in audio is controlled by the site setting and, when available, can be selected in reference-track mode. You can instead upload a recording you are authorized to use or leave out the reference audio. With no supplied track, the model is not promising the original song. An original-rap model generates new music from a topic, which changes the nature of the remake and may reject real human portraits. The preview soundtrack and your eventual soundtrack are different decisions.
The default 16:9 frame leaves space for the two bodies and hanging microphone. For TikTok, a 9:16 output is available in Video settings, alongside square and other supported ratios. Vertical framing can move or crop elements of a landscape routine, so check both sides of the frame. Lengths are 5, 8, 10, 12, and 15 seconds. Resolution affects output detail and credits; it cannot repair an obscured face or ensure that every hand movement matches the source.
The generator shows a quote for the current settings, and the server recalculates it before submitting a job. Credit packs are one-time purchases. Watching a reference clip or choosing settings is not a personalized free render. Credits are deducted when a generation starts; a technical failure returns them automatically. A successful but imperfect result is charged. Read the pricing page for current packs and the terms for purchase rules.
One-time credit packs. A 12-second 480p AI rap video uses 11 credits, and packs never expire.
Single
$9.99
one-time
$10.99 / 12s at 480p
Duo Pack
$29
one-time
$6.38 / 12s at 480p
Party Pack
$59
one-time
$3.25 / 12s at 480p
Crew Pack
$99
one-time
$3.11 / 12s at 480p
Studio Pack
$199
one-time
$2.74 / 12s at 480p
Upload one portrait per person and keep Orange Stage selected. The page starts with Wan 3.0, the built-in routine, a 12-second length, and 16:9 framing. Review the selected soundtrack and credit total, confirm permission to use the photos, and generate. Your finished version replaces the reference preview.
This page generates a new video from your photos and a motion reference. It does not install a live camera filter or simply paste faces onto fixed footage. The requested look is the orange studio and suspended microphone, with your two subjects performing the routine. The result can vary in identity detail and movement.
Check the audio choice in the generator. Built-in audio is available when the site enables it; you can also choose no reference audio or upload a permitted MP3 or WAV. The motion reference and soundtrack are separate inputs. Watching a reference does not grant permission to publish its music, and selecting a topic does not change recorded lyrics.
Yes: put the new lead in the left photo slot and their partner in the right slot before generating. Wan follows the lead-and-hype setup, with the right performer responding through gestures. If you want new lines for both subjects, choose original rap instead and review that model’s restrictions on realistic faces.
The portraits can be taken in different places. Use one clear subject per photo, with similar face detail and even lighting. You can experiment with stylized pet portraits, but mouths, paws, and proportions may be inconsistent. The illustrated scene cards are ideas for casting the routine, not tested results for every type of subject.
Yes. Open Video settings and select 9:16 for a phone feed, or keep the default 16:9 to give both performers more space. Lengths are 5, 8, 10, 12, and 15 seconds. Check both sides of a vertical result because the model must fit a wider two-person routine into a narrower canvas.
You can watch the reference and prepare your settings without spending credits. Creating your own version is paid with the amount shown on the button; a subscription is not required. The server checks the quote before submitting. Technical failures return credits automatically; a completed but imperfect video is still a completed, charged job.
Use the MP4 download beside the completed preview, or reopen the job in My videos after signing in. This is an independent tool and is not affiliated with the original artists, COLORS, TikTok, or CapCut. Review your likeness and music permissions before posting. The trend name describes the setup and does not imply endorsement.
Inputs and completed videos are stored privately; they are not automatically added to a public gallery. The initial preview and external posts are references, while scenario illustrations describe ideas. AI may change faces, hands, timing, or sound. Use only photos, footage, and recordings you have permission to use. This independent tool is not affiliated with TikTok, CapCut, the original performers, or template creators. Download a local copy of a result you want to keep, and review it before publishing.
Start from the main studio: bring two portraits together, explore three stages, and choose a reference track or an original rap.
Explore this video
Make a performance for two friends or a couple. Choose who leads, or switch to an original rap and trade lines.
Explore this video