Currently, AI based images are often generated from noise or a reference image using a phrase (prompt) to describe what should be visible in the image. Sometimes the positioning of objects in such AI videos seems a bit arbitrary. Beautiful that may be and it may remind of works M. C. Escher but I wonder if anybody has tried to use a semantic segmentation/labeling video tracker before the actual AI processing…
Category: Ideas
When Light Runs Through
New installation idea: What if people were transparent and light could travel through them as if they were made of glass or water?
IDNA (dream)
In a dream, I watched the birth of an organism that could willingly alter its own DNA.