Left photo + right photo + motion video
Hotel Lobby AI for Your Next Performance Shot
Develop one Hotel Lobby AI shot at a time on flux3 video. Combine left and right performer images into a shared frame, pair it with your permitted motion reference and review the live generation quote. A controlled first shot makes it easier to decide how the performance belongs in a larger video.
Prepare a performance shotUpload both performer photos, generate a scene image with GPT Image 2, and review it before creating your video with Seedance 2.0. The scene image and video have separate credit quotes.
Classic Hotel Lobby Duo
Two performers, a suspended microphone and a simple orange backdrop.
Hotel Lobby AI references for a shot brief
Watch collected performances to study timing, gesture and framing. They are external visual references rather than flux3 video outputs or ready-made presets. Use your own permitted inputs for the generation.
Classic Hotel Lobby Duo
Two performers, a suspended microphone and a simple orange backdrop.
Grandma Rap Duo
Contrasting outfits and an energetic performance in the same studio setup.
Pet & Baby Duo
A playful pairing with a clear gap between the two subjects.
Halloween Costume Duo
Costume silhouettes make the left and right performers easy to distinguish.
Anime Duo
Illustrated characters bring a different visual treatment to the duo format.
Grandma & Grandson Duo
An intergenerational pairing uses matching staging and contrasting identities.
Animal Sidekick Duo
A character and an animal sidekick share a readable performance space.
Orange Studio Duo
A studio performance with a suspended microphone and a warm orange backdrop.
Plan the opening frame of the performance
Compare character spacing and the microphone location in these collected stills. Decide what the viewer should notice first, then prepare your own scene image with room for that action.

Classic Hotel Lobby Duo
Two performers, a suspended microphone and a simple orange backdrop.

Anime Duo
Illustrated characters bring a different visual treatment to the duo format.

Grandma Rap Duo
Contrasting outfits and an energetic performance in the same studio setup.

Pet & Baby Duo
A playful pairing with a clear gap between the two subjects.
Make a Hotel Lobby AI video with your own performance
Upload both performer portraits and generate a shared orange-studio scene with GPT Image 2. Review the rendered scene before submitting to Seedance 2.0. Both original portraits, the scene image and the motion reference video are supplied together. Identity and scene references guide the result; exact likeness and choreography are not guaranteed.
How to create your Hotel Lobby video
Prepare the opening composition
Upload one left and one right PNG or JPG, up to 10 MB each. Sign in and prepare the combined duo frame. Keep enough visible upper body for the intended gesture and check both portrait crops.
Add a motion reference for the beat
Use a permitted video whose timing and gestures fit your planned scene. Clear faces and restrained movement give you a more useful starting comparison than a crowded or rapidly changing shot.
Review the quote and the complete take
Select an available model and review the actual credit cost and settings. Generate, then watch the complete output in your existing results workflow. Choose the take for its continuity and motion, not only its opening image.
Give the Hotel Lobby AI shot one purpose
A short performance reads more clearly when you know which action carries the beat.
Choose the active performer
Let one character give a modest gesture while the other reacts. This is a prompt direction to evaluate, not a separate control that guarantees each performer follows an assigned action.
Keep the camera predictable
Begin with a fixed medium shot and visible faces. Establish a usable performance before experimenting with stronger camera language.
Fit the motion reference to the duo frame
Movement and composition should support the same visual idea. A reference cannot reliably recover information absent from the starting image.
Avoid movement that hides faces
Hands crossing the face, fast profile turns and overlapping performers can disrupt identity. Choose a clearer motion reference or reduce the complexity of the planned beat.
Keep the subject scale compatible
A close portrait may not support a full-body dance reference. Use an image with the visible body parts needed for the action and inspect the joined frame before rendering.
Review the take before building a sequence
Generation gives you a shot to assess. Editing choices still determine the final story and soundtrack.
Check continuity across the full clip
Watch positions, outfits, facial features and microphone movement at several points. Independently generated shots may not match, so compare them before placing them in an edit.
Make audio an editorial choice
The reference song and exact lip synchronization are not guaranteed. Inspect any output audio and add music you are permitted to use. This page does not automatically deliver a finished music video.
Hotel Lobby AI prompt ideas
Suggested prompts describe the intended look. They are not generated examples or guarantees of the result; motion still comes from the reference video.
A restrained lead and response
Two original performers share a warm orange studio and a suspended microphone. A stable medium shot with both faces visible. The left performer gives a modest gesture while the right performer responds with a small nod; movement is guided by the uploaded reference.
A matched second performance direction
Two original performers with contrasting jackets and matching camera height in the same simple orange-studio brief. Clear subject spacing, soft light and a fixed waist-up frame. Use the permitted motion reference for restrained performance movement.
Hotel Lobby AI questions on flux3 video
How are the left and right photos used?
Upload both performer portraits and generate a shared orange-studio scene with GPT Image 2. Review the rendered scene before submitting to Seedance 2.0. Both original portraits, the scene image and the motion reference video are supplied together. Identity and scene references guide the result; exact likeness and choreography are not guaranteed.
Does the generator assemble several takes into a sequence?
No. Use the output as one shot and assemble your selected clips in a separate editing workflow. Check consistency between takes; independent generations do not guarantee matching wardrobe, faces or scene continuity.
Does choosing a gallery reference generate its exact performance?
No. The collected gallery illustrates framing and styling, and choosing a reference changes what you watch. Use your own permitted images and motion input. Original prompts and generating models are not claimed when they are unknown.
What does the motion reference control?
It supplies movement cues for the selected model to interpret alongside the prepared image. Exact timing, choreography, facial consistency and two independently controlled subjects are not guaranteed. Review the complete generated clip.
Can I browse and prepare the composition without a paid render?
Browsing collected references and preparing the scene image do not submit a video task. Rendering on flux3 video requires a signed-in account and enough credits for the selected model and settings. Review the live quote and your balance before submitting.
Does the result include the source song or synchronized lyrics?
Neither original music nor precise lip synchronization is promised. Audio depends on the actual model and settings. Check the output, then use a soundtrack you are permitted to process and publish.
What should I change if faces or outfits drift?
Begin with clear, compatible portraits and a motion reference that does not hide faces or cause strong overlap. Reduce motion complexity and check the whole clip. The combined start image contains the visible details the model can use; it is not an identity lock.
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@flux3video.dev 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@flux3video.dev 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@flux3video.dev. 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.
Plan your next performance
Build one readable performance shot, inspect its movement from start to finish and decide how it fits your edit. Keep the visual brief when planning another take, while reviewing each new result separately.
Prepare a performance shotflux3video.dev · Updated
See update history
- — Added an action to restore the existing example prompt without starting a generation.
- — Updated page copy and content.
- — Page content published.