Bjørn Karmann’s camera, named Paragraphica, uses censors and geolocation data, including weather conditions, to create a stream of text which is then converted into a “photo”, according to his website.
The camera looks like a typical point-and-shoot, but replaces the lens with a red one, described by photography website Digital Camera World as resembling a “TV antenna stuffed where the lens should be. “. Karmann told the evening standard that the bizarre element is simply a sculpture inspired by the star-nosed mole, an animal that is blind but visualizes its surroundings using its snout.
“The viewfinder displays a real-time description of your current location, and pressing the trigger will cause the camera to create a scintigraphic representation of the description,” Karmann wrote on his website.
Presentation – Paragraphica! 📡📷
A camera that takes pictures using location data. It describes where you are, then converts it into an AI-generated “photo”.See more here: https://t.co/Oh2BZuhRcf
or try taking your own photo here: https://t.co/w9UFjckiF2 pic.twitter.com/23kR2QGzpa— Bjorn Karmann (@BjoernKarmann) May 30, 2023
Photographers using the device can control the image outcome with three physical dials on the top of the camera body where the buttons would be located that would normally control things like shutter speed and shutter speed. movie.
The first button, Karmann wrote, functions similarly to the focal length of a traditional camera lens, but is used to limit the radius in which the camera searches for data. A diagram of the dial shows that the distance appears to range from nearly 10 feet to infinite distance.
The second button controls the noise seed for spreading the AI image. In the AI image generation process, the models add Gaussian noise through which the image emerges. Karmann defined noise as “comparable to film grain”.
Courtesy of Bjørn Karmann.
Karmann described the third button as a “guide scale” that provides input on how closely the AI model follows the generated text prompt.
The hardware Karmann used to create the camera included a Raspberry Pi 4, a credit card-sized single board computer, and a 3D-printed enclosure with custom electronics. The software works on Noodl and Python coding with the Stable Diffusion API.
“Honestly, it’s the weirdest, dumbest thing I’ve ever seen, but I’m in awe of its engineering,” wrote Sebastian Oakley in his review for Digital Camera World. “But it’s not photography – or could it be? »
Follow Artnet News on Facebook:
Want to stay one step ahead of the art world? Subscribe to our newsletter to receive breaking news, revealing interviews and incisive reviews that move the conversation forward.
