Paragraphica – Context to image (AI) camera

Created by Bjørn Karmann, Paragraphica is a camera that utilizes location data and AI to visualize a “photo” of a specific place and moment. The camera exists both as a physical prototype and an online camera that you can try. 

The viewfinder displays a real-time description of your current location, and by pressing the trigger, the camera will create a photographic representation of that description. On the camera, there are three dials that let you control the data and AI parameters to influence the appearance of the photo, similar to how a traditional camera is operated.

The camera operates by collecting data from its location using open APIs. Utilising the address, weather, time of day, and nearby places, Paragraphica creates a paragraph that details a representation of the current place and moment. Using a text-to-image API, the camera converts the paragraph into a unique visualization. The resulting “photo” is not just a snapshot, but a complex and nuanced reflection of the location you are at. 

Inspired by the star-nosed mole, which lives and hunts underground, finds light useless. Consequently, it has evolved to perceive the world through its finger-like antennae, granting it an unusual and intelligent way of “seeing.” Empathizing with the ways other intelligences perceive the world can be nearly impossible to imagine. As AI language models are increasingly becoming conscious, we too will have limited imagination of how they will see the world. The camera offers a way of experiencing the world around us, one that is not limited to visual perception alone. Through location data and AI image synthesis, Paragraphica provides deeper insight into the essence of a moment through the perspective of other intelligences.

Try the camera online

The first dial behaves similarly to the focal length in an optical lens but instead controls the radius (meters) of the area the camera searches for places and data. The second dial is comparable to film grain, as the value between 0.1 and 1 produces a noise seed for the AI image diffusion process. The third dial controls the guidance scale. Increasing guidance makes the AI follow the paragraph more closely. In the analogy of a traditional camera, the higher the value, the “sharper,” and the lower, the “blurrier” the photo, thus representing focus.

Created with Raspberry Pi 4, 15-inch touchscreen, 3D printed housing, custom electronics and using Noodl, python and Stable Diffusion API.

Project Page | Try it here | Bjørn Karmann

For more “Camera” related projects, see here.