Hotel Lobby AI: Start with Two Clear Portraits

Bring a pair of portraits into the Hotel Lobby AI format on face in hole. Upload a left image and a right image, prepare their shared frame and describe a small studio action. The workflow animates one combined image; it does not assign faces to a two-person replacement template.

Prepare my duo performance

The two uploads become one side-by-side start image for image-to-video. Preparation does not remove backgrounds or assign independent face identities. Exact choreography, facial consistency, lip synchronization and an original soundtrack are not guaranteed.

Hotel Lobby AI Generator

Loading video models…

PNG or JPG · up to 10 MB each. Keep both faces visible. Each photo fills its half of the duo image.

624/10000
Required Credits—

Add the required reference images to continue.

Hotel Lobby AI reference videos

Watch these collected performances for ideas about the orange studio, duo framing and character styling. These are external references, not results generated on this site or one-click templates.

Classic Hotel Lobby Duo

Collected performance reference for duo framing, studio styling and character movement.

Grandma Rap Duo

Collected performance reference for duo framing, studio styling and character movement.

Pet & Baby Duo

Collected performance reference for duo framing, studio styling and character movement.

Halloween Costume Duo

Collected performance reference for duo framing, studio styling and character movement.

Anime Duo

Collected performance reference for duo framing, studio styling and character movement.

Grandma & Grandson Duo

Collected performance reference for duo framing, studio styling and character movement.

Animal Sidekick Duo

Collected performance reference for duo framing, studio styling and character movement.

Hotel Lobby Performance 1

Collected performance reference for duo framing, studio styling and character movement.

Hotel Lobby Performance 2

Collected performance reference for duo framing, studio styling and character movement.

Hotel Lobby Performance 3

Collected performance reference for duo framing, studio styling and character movement.

Hotel Lobby Performance 4

Collected performance reference for duo framing, studio styling and character movement.

Picture your duo in the studio

Explore these collected visual references, then use your own images for the two upload positions above.

Hotel Lobby AI visual reference image 1
Frame both faces clearly
Hotel Lobby AI visual reference image 2
Keep the microphone visible
Hotel Lobby AI visual reference image 3
Compare outfits and expressions
Hotel Lobby AI visual reference image 4
Give both performers room

Collected visual references; these images are not generated results.

A portrait-led approach to Hotel Lobby AI

The studio format gives two portraits a common visual brief: an orange setting, a microphone and restrained performance movement. face in hole combines your images side by side for image-to-video. The name of the site does not change the inputs into an automatic face-swap system. Collected videos are visual references for framing rather than footage that receives your faces.

How to make a Hotel Lobby AI clip on face in hole

  1. 01

    Select portraits with readable faces

    Place one permitted portrait in Left image and the other in Right image. Each must be a PNG or JPG no larger than 10 MB. Include the head, neck and shoulders, and avoid hands or strong profile angles that hide identifying details.

  2. 02

    Inspect both portrait crops

    Sign in and select Prepare duo image to join and upload the portraits. Preparing the image does not submit a video task or spend generation credits. Check both halves for clipped hair, missing shoulders or unequal face scale. If either portrait needs replacing, prepare the new pair again.

  3. 03

    Animate and check each face

    Choose an available image-to-video model and ask for a small, forward-facing studio action. Review the real output settings and Required Credits, then generate. In Your results, watch both faces from start to finish; the combined image is a starting composition, not two independent face assignments.

Make the portraits do the visual work

Two friends with matching framing

Choose photos at similar camera height with enough space around the faces. A gentle nod can give the pair movement without asking the model to reconstruct a sharply turned or partially hidden face.

A costume pair

Use portraits where the costumes are already visible. Let outfit shapes distinguish the two performers, and keep the action small enough to judge whether those details remain intact.

An original avatar beside a portrait

Pair a permitted portrait with your own avatar. Similar proportions help the composition read, but a mix of photographic and illustrated faces can change during animation. Review the complete result before sharing.

Give both faces a fair starting point

Use more than a face crop

Include the head, neck and shoulders with space above the hair. Each photo fills half of the prepared frame, so a tight face crop can lose identifying features when fitted to the composition.

Avoid hidden facial details

Sunglasses, hands and strong profile angles can make identity harder to preserve. Use clear permitted images and begin with an action that does not cover the face.

Do not infer a replacement from the output

The model interprets one start image. If facial details shift, revise the inputs or reduce the motion; there are no independent left and right face assignments to lock.

A prompt that keeps portraits easy to inspect

The two portrait subjects remain side by side in a warm orange studio with a suspended microphone between them. Small head nods, forward-facing expressions and a fixed medium camera. Keep both faces unobstructed, preserve recognizable clothing and avoid crossing arms over either face.

This suggested prompt is a starting brief for a portrait consistency without a face-swap promise. It is not the original prompt for any collected video. Adapt it to the prepared image and review the actual output; a prompt cannot guarantee identity, seamless backgrounds or synchronized lyrics.

Hotel Lobby AI questions for face in hole

What happens to my two uploaded images?

face in hole prepares one side-by-side landscape image with your left and right photos. That single image is the reference for the selected video model. The page does not independently assign a face identity to each performer in a collected clip.

Is this a two-person face-swap tool?

No. The two upload positions prepare one side-by-side start image for the selected video model. The page does not take a collected performance and independently replace its two faces. Identity preservation remains something you review in the generated clip.

Does choosing a collected video copy its performance?

No. Collected videos are visual inspiration. Selecting one changes what you can watch; it does not import its choreography, replace its performers or submit it as a hidden generation template. Unknown original prompts and models are not claimed.

Do I need credits to prepare or generate?

Browsing references and preparing a joined image do not submit a video generation. Rendering on face in hole requires a signed-in account and enough credits for the current quote. Model and output settings determine the cost; review your balance and pricing before submitting.

Will both performers stay recognizable?

Clear inputs and small movements make your portrait consistency without a face-swap promise easier to evaluate, but consistency is not guaranteed. Check both faces, outfits and left/right positions from beginning to end. Fix a poor crop before generation and reduce movement if details drift.

Does the clip include the original music or exact lip sync?

The image pair contains no music. Audio support follows the selected model and its displayed settings. The page does not guarantee a reference song, precise synchronized lyrics or matching choreography. Check sound separately and use audio you are permitted to publish.

Can the preparation step create a seamless studio background?

It joins the two uploaded images without removing their backgrounds. Use compatible photos and inspect the composition before requesting studio details in your prompt. A seamless scene remains an output to review rather than a guaranteed preparation result.

Can I request a refund for my purchase?

You can request a refund within 10 days of purchase if you have unused credits from that purchase and provide a clear reason, subject to our Refund Policy. If eligible, an unused purchase can be fully refunded; a partly used purchase is refunded in proportion to its remaining unused credits. Fully used purchases and free or promotional credits are not refundable.

Do credits expire or carry over?

Credit validity depends on the pack, subscription or promotion that issued them. Review the purchase terms and expiration dates in Settings > Credits. A renewal or new purchase does not extend older credits. Use credits before their stated expiration; do not assume unused subscription credits roll over indefinitely.

What happens to credits if generation fails?

Credits charged for a task that is confirmed as failed due to a system error are returned automatically. A task that is still processing has not yet been confirmed as failed. Check its status and your credit history before submitting again. If a confirmed failure still shows an unresolved charge, email support@faceinhole.app with the task ID.

Can I get credits back if I do not like the result?

AI results can vary, so a completed result that differs from your expectations is not automatically treated as a technical failure. Eligible completed image tasks can be submitted for credit refund review using the refund option where available; approval is required. For a video or another issue, contact support@faceinhole.app with the task ID and details. A credit refund returns credits, not money to your payment method.

How can I get help with billing or a generation?

Email support@faceinhole.app. For billing, include your account email and order ID; for generation, include the task ID, issue description and relevant screenshots. If you purchased as a guest, keep the original browser data and payment receipt so we can help locate the purchase.

Prepare a pair you can recognize throughout

Inspect both portrait crops, describe restrained movement and check the live credits. Watch each face from beginning to end before deciding whether the clip works for your idea.

Prepare my duo performance

· Updated

What's new on this page

  • — Added an action to restore the existing example prompt without starting a generation.
  • — Updated page copy and content.
  • — Page content published.