AI camera uses internet data not light to form image
Paragraphica is a context-to-image camera that uses location data and artificial intelligence to visualize a “photo” of a place and time.
The unit collects data including location and orientation to create a descriptive paragraph which is then converted into an AI-generated “photo”.
Text-to-image by Paragraphica. Source: Bjoern Karmann
The camera operates by collecting data from its location using open APIs. It utilizes the address, weather, time of day, and nearby places. Paragraphica combines the data and composes a paragraph that details a representation of the current place and moment.
Using a text-to-image AI, paragraphica then converts the paragraph into a “photo”.
Paragraphica dataflow. Source: Bjoern Karmann.
Paragraphica controls. Source: Bjoern Karmann.
Three dials are used to control the image generation.
The first dial behaves similarly to the focal length in an optical lens but instead controls the radius in 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” the image and the lower the value the “blurrier” the photo, thus representing focus.
Bjørn Karmann, the developer, describes himself as a senior experience and interaction designer based in Amsterdam, The Netherlands.
Related links and articles:
www.bjoernkarmann.dk/project/paragraphica
News articles:
Intel Labs AI diffusion model generates 3D images from text
Ex-Samsung exec arrested over alleged Chinese copycat fab
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
