By Muhammad Umar
This most advance camera doesn’t feature lens. Designed by a Dutch engineer Bjørn Karmann, it uses, instead, location data and artificial intelligence to visualize a “photo” of a specific place and moment. The camera exists both as a physical prototype and a virtual camera that you can try. It has strange crimson-hued TV-aerial-like attachment in a spider web shape.
This camera works with the viewfinder and uses real-time description of your current location, and by pressing the trigger, the camera will create a scintigraphic representation of the description. So, it is considered as use of AI in photography.
It is equipped with three physical dials, which let you control the data and AI parameters to influence the appearance of the photo, similar to how a traditional camera is operated.
Body of camera is 3D printed by the Engineer. This needs a paragraph of information containing a brief description of the place, GPS data, and weather, temperature, and date, to generate a real image of the scene in front of the camera.
Above is a screenshot from Noodl, that engineer used to build the web app that communicates between the camera and the multiple APIs to generate the location-based prompt and the image itself.
Hardware: Raspberry Pi 4, 15-inch touchscreen, 3D printed housing, custom electronics.
Software : Noodl, Python code, Stable Diffusion API.