Choose length, quality and format before you generate
Pick 4 seconds for a first test, 10 seconds for a longer duet, or 15 seconds for more room to move. Preview requests 480p at 4 credits per second. Standard requests 720p at 12 credits per second; HD requests 1080p at 25 credits per second. The total changes immediately when you change a setting.
For example, a 10-second Preview costs 40 credits, a 10-second Standard costs 120, and a 15-second HD costs 375. All durations support vertical 9:16 and landscape 16:9. Every option requires Google sign-in and sufficient purchased credits. There is no signup grant or free video allowance.
Audio, movement and what to expect
The model creates a new two-person performance from your two photos. Choose a playful duet, freestyle energy or a relaxed session. Video requests include original AI-generated audio; audio quality and movement vary between results.
We do not provide the original Hotel Lobby song, reproduce a specific dance, or clone a singer’s voice. If you want a particular soundtrack, add music you are allowed to use in your editor or the posting platform. Generation time depends on the provider’s queue and the selected model.
Download your MP4 and prepare it for sharing
Your finished video appears in the studio and your private library. Use Download to save the MP4. A 9:16 frame suits phone screens; 16:9 is useful for a wider composition. Review the whole clip for likeness, unexpected movement and audio before publishing.
We do not add a site watermark to the downloaded file, but model-generated visual artifacts can still appear. Obtain permission from both adults for AI transformation and publication, follow your destination platform’s rules, and disclose realistic AI-generated content where required.