I have been building Burger Window AI, a small product that turns one front-facing photo of a person or a pet into a vertical, roughly 12-second night-window clip.
The scene is fixed on purpose. There is no prompt box. You upload a bright photo, and the clip plays the same beat every time:
- A warm night window.
- A mid-bite freeze.
- A stare into the camera.
- The curtain closes.
That constraint is the product. Short-form feeds (TikTok, Reels, Shorts) reward a recognizable format more than a general video model. A fixed scene also keeps the pipeline simple: one photo in, one MP4 out, about 12 seconds, vertical.
A few things that shaped the build:
- A single camera angle and a short duration are easier to keep consistent than an open-ended generator.
- The photo has to be front-facing and well lit, or the face and the bite do not read in the first second.
- Shipping a scene, not a prompt UI, cuts the instructions down to "upload a photo."
The live product is at https://burgerwindowai.com
If you are building a generative feature, it is worth asking whether a narrow scene will ship better than a blank prompt.
Top comments (0)