Hotel Lobby AI Template
Upload two reference photos and choose an orange or midnight blue stage template to create an original two-person studio performance with a hanging microphone. Updated October 5, 2026.
Which scene is this template designed for?
This template is for a short two-person studio performance, not an accommodation interior. Two authorized reference photos guide the performers; the scene directions place them around a hanging microphone against an orange or midnight-blue background. Friends can request alternating rap-style gestures, couples can request a playful duet-style exchange, and creators can use authorized fictional adult characters for a stage concept.
Use a simple direction that keeps both people visible, such as one performer leading while the other responds with a nod, then switching roles. The template supplies a scene brief rather than a fixed video, motion capture or guaranteed position lock. It does not transfer faces onto an existing performance, provide the original commercial song or synchronize mouths to uploaded lyrics.
The name Hotel Lobby AI refers to this recognizable duo stage format. It does not describe hotel room tours, property showcases, hospitality advertising or travel scenes.
What the template directs
The template supplies scene direction: two performers on opposite sides of a hanging microphone, an orange or midnight blue backdrop, and alternating wide and medium framing. These are instructions for the model; exact positions, colours, timing and camera changes can vary. You supply the two people as reference photos. It does not take a name, a song or a video and copy it, and no original commercial recording is bundled.
Once the scene is set, the model composes a new clip around your references. That is where the variables live — photo quality, lighting and how clearly each subject is separated.
What you still control
- Stage template — orange studio or midnight blue studio
- Duration — 4–15 seconds with MiniMax H3, or 4–30 seconds with Seedance 2.5
- Resolution — 768P or 2K with H3; 480p, 720p or 1080p with Seedance 2.5
- Framing — 9:16 vertical for short-form feeds, 16:9 landscape, or 1:1 square
- Creative direction — free text for staging and movement
Only the model, duration and resolution determine the credit charge. Stage template, framing and creative direction do not add a separate charge. The total is displayed before you submit.
Using it in three steps
You do not need to write a prompt from scratch. The creator starts with a prefilled creative direction for a two-person performance; keep it as it is, or edit it for your staging and movement. You still upload the two photos, choose a template and model, set the output, review the charge and submit.
- Upload one clear reference photo per subject. For people, use consenting adults whose photos you have permission to use.
- Choose a stage template, model and output settings, keep or edit the prefilled creative direction, and review the displayed credit charge.
- Submit. Once the safety check and generation succeed, preview the result in My creations and download the video.
Submitted tasks continue running on the server if you close the page. Return by signing in with Google or email. For an anonymous account, use the same browser session or your saved recovery code.
The default direction requests a trap instrumental with no vocals and no recognisable song. It does not automatically make the subjects sing the original Hotel Lobby song. Audio and visual results can vary. Follow the step-by-step video tutorial to see the upload, settings and preview process, and read the full guide for music and lip-sync limits.
Template or manual prompting
Use the template for a recognisable two-person microphone-stage format. Add scene direction for outfits, movement or tone. Pets and objects are experimental subjects; their upload compatibility does not establish reliable results for those uses.
A working direction keeps the scene and the positions in front, and keeps names out. For example:
Create an original two-person performance in a lit orange studio with one microphone hanging above the center. Keep the first reference subject on the left and the second on the right. Give each performer natural, distinct movements, and let them trade the lead rather than moving in unison.
If a result is weak, check both the references and the direction: clearer faces can help the model recognise subjects, while simpler staging and movement instructions can reduce conflicting requests. Neither change guarantees an exact likeness or performance.
Photos that work, photos that do not
| Works well | Reduces consistency |
|---|---|
| One person, well lit, head fully in frame | A group shot used as a single reference |
| Front-facing or slight three-quarter angle | Heavy side shadow across the face |
| Two separate files, one subject each | Two people inside one photo |
| JPG, PNG or WebP under 10 MB | Screenshots of screenshots |
| Two distinct subjects for the primary duo workflow | A cropped forehead or chin |
What one run costs
MiniMax H3: 10 credits per second at 768P, or 17 at 2K (4–15 seconds). Seedance 2.5: 40 credits per second at 480p, 85 at 720p, or 210 at 1080p (4–30 seconds). The table below shows H3 examples.
| MiniMax H3 output | Credits |
|---|---|
| 5 seconds, 768P | 50 |
| 10 seconds, 768P | 100 |
| 5 seconds, 2K | 85 |
| 10 seconds, 2K | 170 |
One-time packs start with Mini — 100 site credits for US$4.90. The recommended pack is Single video, 400 credits for US$9. Creator offers 1,000 credits for US$28; larger packs and top-ups are also available through Waffo checkout. They are one-time purchases with no subscription and no automatic renewal. The credit quantity, price and any applicable taxes are disclosed at checkout. Rejected prompts are not charged, and a confirmed provider failure returns the credits. See Pricing and credits.
Two things to understand before your first run
- It generates a new scene; it does not swap a face into footage you already have. There is no workflow here for replacing a person in an existing video.
- No specific likeness or performance is guaranteed. Processing times vary with the model and the queue, and results vary with your references.
Reference photos are screened with OpenAI image moderation, and the composed prompt must pass Waffo Pancake’s Content Safety scan-prompt API before generation. A blocked or unavailable check prevents the run. See the Acceptable Use Policy.
Frequently asked questions
Can I make Hotel Lobby AI without writing a prompt?
Yes. Hotel Lobby AI fills in a creative direction that you can keep without writing a prompt from scratch. Upload two reference photos, choose a stage template, model and output settings, review the credit charge, then submit. You can edit the direction if you want different movement or staging.
Does the default template make the people sing the original song?
No. The prefilled creative direction requests a trap instrumental with no vocals and no recognisable song. It describes a two-person performance, not automatic singing of the original Hotel Lobby recording or precise lip-sync to supplied lyrics. Generated audio can vary by model and result.
Do I need the original Hotel Lobby video?
No. Nothing from it is uploaded and no frame of it is used. The generator builds a new scene from your two reference photos.
Can I use two photos of the same person?
You can submit two references of the same consenting adult, but this is experimental. The template requests two distinct performers; duplicated identity, separation and appearance are not guaranteed.
Can I use pets or objects instead of people?
The main use case is two-person studio performances. Pets and objects are experimental subjects, and results for those uses are not established here. Supported files are JPG, PNG or WebP under 10 MB each.
How many credits does one run cost?
Between 40 and 6,300 credits, depending on model, duration and resolution. The exact charge is shown before you submit.
Is the Hotel Lobby AI template free?
There is no free generation allowance at the moment. One-time credit packs are available through Waffo checkout. See Pricing and credits for the current status.