LogIn
Bjørn Karmann presented Paragraphica – a fascinating context-to-image AI camera that uses location data to visualize a photo of a specific place and moment.
The viewfinder of the camera displays a real-time description of your location based on the address, weather, time of day, and nearby places. You can adjust the dials to influence the appearance of the photo and then press the trigger to get a scintigraphic representation of the description.
The first dial controls the radius of the area the camera searches for places and data. The second dial is like film grain: the value between 0.1 and 1 produces a noise seed for the AI image diffusion process. The third dial controls how closely the AI follows the paragraph: the higher the value, the "sharper" the photo.
Even more interesting than the idea is the camera's appearance: it is modeled after a star-nosed mole.
"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." This amazing animal became the perfect metaphor and inspiration for how empathizing with other intelligences and the way they perceive the world can be nearly impossible to imagine from a human perspective. As AI language models are increasingly becoming conscious, we too will have limited imagination of how they will see the world."
Karmann says that Paragraphica "provides deeper insight into the essence of a moment through the perspective of other intelligences."
Hardware used:
- Raspberry Pi 4
- 15-inch touchscreen
- 3D printed housing
- custom electronics
Software used:
- Noodl
- Python code
- Stable Diffusion API
You don't have to assemble your own camera like this, there is an online version of the tool for you to try out.
Find out more about Paragraphica here and don't forget to join our 80 Level Talent platform and our Telegram channel, follow us on Instagram and Twitter, where we share breakdowns, the latest news, awesome artworks, and more.
This pack can help you get that realism that 3D often lacks with various different dirt ad scratches captured from real surfaces.