I realized that it is useless for me to try and comment AI art with the help of AI artworks. To me, this answer is a solution to a long dilemma…
Ich habe heute festgestellt, dass es für mich sinnlos ist, KI-Kunst mithilfe von KI-Kunstwerken kommentieren zu wollen. Diese Antwort ist die Lösung eines langen Dilemmas für mich…
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…