Prepare two portraits for Hotel Lobby
Written by Kadenly · Updated
Prepare two portraits for a Hotel Lobby AI duet. Keep left and right identities distinct, adapt the scene prompt and review faces, clothing and credit costs.
Purpose and limitations
Hotel Lobby is an available beta using two separate photos and an editable prompt to create a new orange-studio duet. A four-second preview has been tested. It does not reproduce the original song or guarantee the original choreography; check current settings and credit cost on the tool page.
Use one person in each image
Choose separate portraits with visible faces, even lighting, and minimal obstruction. Avoid group shots that make character selection ambiguous.
Set the positions deliberately
Place the intended left character in the first input and the right character in the second. Check both thumbnails before generating.
Understand the reference
Review the model capabilities before generating. A two-character scene requires support for multiple character references. Check identity consistency and positioning in the result.
English prompt example
This is the editable default prompt used for the public four-second duet sample. Upload the left performer as @Image1 and the right as @Image2 in Hotel Lobby. Keep the identity assignments and edit the scene or actions to suit your idea; results vary.
Create a 4-second photorealistic musical duet. Use @Image1 only as the identity and clothing reference for the LEFT performer and @Image2 only for the RIGHT performer. Preserve their distinct faces, hair, skin tone, outfits and body proportions throughout. Both performers are adults.
Stage both subjects standing side by side in a seamless matte orange studio, with a single black microphone suspended between them. Show both bodies and feet with a clear gap between them. Keep each identity on its assigned side.
During the first half the LEFT performer delivers a playful rap with natural hand gestures while the RIGHT performer nods and reacts. During the second half the RIGHT performer takes the lead while the LEFT performer reacts. Their gestures are independent, conversational and never mirrored or synchronized. Use natural rhythmic gestures and restrained body movement.
One continuous centered shot with a completely fixed camera, soft even frontal lighting. No cuts, zoom, camera movement, extra people, furniture, overlapping bodies, identity swaps, text or logos. Generate an original upbeat hip-hop backing beat and brief playful vocal phrases synchronized with the performers. Do not recreate an existing song.Input and result checklist
- Prepare a separate, clearly lit photo of each person.
- Avoid group photos, face obstruction, and heavily different viewing angles.
- Record the intended left and right roles; input order alone cannot guarantee final placement.
- Use photos you are entitled to upload and obtain consent where appropriate.
- Check duration, ratio, audio and credit cost on the Hotel Lobby tool before submitting.
Common issues and adjustments
The two people are hard to distinguish
Use separate references with clear faces and distinct appearance. Keep the two photo identities separate in the prompt and reduce overlapping gestures.
The character order changes
Keep @Image1 on the left and @Image2 on the right in the prompt, with space between them. A position instruction is not a guarantee; review both identities and positions in the result.
You need the exact preset performance
This two-photo workflow synthesizes a new performance. Exact motion copying needs a separate compatible reference-video workflow; changing a prompt alone cannot guarantee the original performance.
Sources and related policies
These are original preparation tips and prompt examples from our team. Model capabilities change; check current settings before generating. For input requirements and usage rules, see: