Hotel Lobby AI
Two photos, one stage — create your own AI duo performance.
In their words
Hotel Lobby AI is an independent, self-service AI video creation tool for original two-subject studio performances. You supply two separate reference photos you have permission to use, choose a stage and the video settings, and the tool generates a new scene featuring both subjects. It is built for creators who want a duo performance of their own rather than a remix of an existing recording: there is no workflow for swapping faces into footage that already exists, and the project is not affiliated with Migos, Quavo, Takeoff or COLORS and does not bundle any of their recordings. Current duration options are 4-15 seconds on H3 and 4-30 seconds on Seedance, with 768P and 2K output resolutions. Generation runs on AI video models, with image and text moderation applied before anything is submitted for processing.
Fact file
Generator- Web
- Waffo
- OpenAI
- MiniMax H3
- Input limits
- Under 10 MB per photo
- Supported formats
- JPG, PNG, WebP
- Durations
- 4-15 seconds (H3); 4-30 seconds (Seedance)
- Resolutions
- 768P, 2K
What is Hotel Lobby AI?
Two reference photos go in, and an original studio clip comes out. Hotel Lobby AI places both performers on opposite sides of a hanging microphone inside an orange studio backdrop. The fixed format puts one subject on the left and the second on the right while a steady camera maintains a single continuous take. The generator defaults to MiniMax H3 reference-to-video, and tasks continue on the server if the browser tab closes.
Uploads and photo guidelines
Users upload one photo per performer using JPG, PNG or WebP files under 10 MB each. Each reference image must contain a single, clearly visible subject in good light. Group shots, mirrored selfies, blurry faces, and heavily occluded subjects reduce consistency in the output. The tool does not verify identity, age, or consent, so obtaining permission from everyone in the photos remains the responsibility of the person running the generation. Image and text moderation run before any request is forwarded for processing.
Settings and credit costs
Creators choose between 5- or 10-second durations and 768P or 2K resolution, along with vertical 9:16 or wide aspect ratios and custom creative direction. Costs scale by settings: a 5-second 768P video costs 50 credits, a 10-second 768P video costs 100 credits, a 5-second 2K video costs 85 credits, and a 10-second 2K video costs 170 credits. Credits are purchased through Waffo checkout in one-time packs, and a confirmed provider failure restores the credits for that run. Once the safety check and generation succeed, finished clips appear in My creations for download.