Updated 2026-10-08
Hotel Lobby AI Video Generator
Coming soon: new video generation and credit purchases are not open yet. Template previews and existing completed videos remain available. See Pricing for the current status.
The Hotel Lobby AI generator is configured for a two-photo reference workflow: two characters in an orange-booth template with one hanging microphone. New submissions are not yet open. You can preview the template, prepare who starts on each side and review the listed credit costs. The selected reference determines who raps and who dances; the two characters do not automatically take turns singing. The planned submission flow does not require a prompt.
What the generator actually does
Behind the button is a two-photo reference workflow. Each photo becomes a character reference — face, hair, skin tone, outfit and body proportions — and the previewed template is the motion and framing reference. Select 5 or 10 seconds to preview the corresponding template. The model replaces the performers while following that reference, and the finished MP4 retains its soundtrack. Exact motion, timing and likeness can vary; there is no promise of frame-for-frame identity replacement or exact lip-sync.
The booth, camera direction and character roles are supplied in a preset, so you do not need to describe them. Your photos are an important input, but the model can still introduce variations in faces, gestures and staging.
Photos that work
- One person per photo. The generator asks for Photo 1 on the left and Photo 2 on the right. A group photo makes the intended subject ambiguous and can increase the chance of blended identities.
- Front-facing, both eyes visible. A visible face provides more identity detail; profiles can be harder to match.
- Even light, no heavy filters. Ring light or window light is ideal; club lighting is not.
- Show the outfit. Waist-up or full-body photos supply clothing, jewellery and body details; a tight face crop leaves more appearance details unspecified.
- Pet references need extra review. Clear markings help you compare a result, but this site has not verified a successful pet result with the current template.
Planned output and existing completed videos
The configured output choices are 5 or 10 seconds, 480p or 720p, in 9:16, 16:9, 4:3 or 3:4. The default is 5 seconds, 720p and 9:16. When new generation opens, rendering may take several minutes or longer when the provider is busy. Existing completed results can still be played and downloaded as MP4 from Your videos. The workflow retains the template soundtrack heard in the preview. Photos do not automatically change the voices, and exact lip-sync is not guaranteed.
Purchased credits and availability
New accounts receive no generation credits. The product uses one-time credit purchases: 5 seconds at 480p/720p costs 100/200 credits; 10 seconds costs 150/300. Watch template previews for free, then check Pricing for purchase terms and the current checkout status. New generation and credit purchases are currently coming soon. Check task status and your current credit balance before retrying a failed task. A slow or interrupted status request is not proof that generation failed.
Hotel Lobby AI generator vs. templates vs. prompting
An editing template can arrange photos or existing footage; some include additional AI effects. A reference-video workflow generates new imagery guided by supplied inputs. What each tool supports depends on the selected product and template, so compare the inputs and controls rather than assuming that all editing templates only paste a face. The workflow comparison explains the distinction.
This site’s preset supplies the scene reference while your two photos guide the characters. Read the template guide, character replacement guide and step-by-step workflow. If you already have a task, check its status before submitting again; the troubleshooting guide covers roles, likeness and sound. Browse all guides for the background and posting steps.
FAQ
Which photo goes where?
Photo 1 guides the starting left role and Photo 2 the right. Changing their order changes the intended assignment; the generated result can still vary.
Which formats and credit costs are available?
Choose 480p or 720p, 5 or 10 seconds, and 9:16, 16:9, 4:3 or 3:4. Costs are 100/200 credits for 5 seconds at 480p/720p, or 150/300 for 10 seconds. The default is 5 seconds, 720p and 9:16: 200 credits.
Can I upload one group photo?
Use one intended subject per photo. Multiple faces can make the reference ambiguous and increase the chance of blended identities.