Inspired by the AI section in the school, I intend to seek a method that generated images. A moving image creates vocal interaction between humans and machinery. Connecting speech recognition software and AI engine( Runway) by processing coding. The voice sent to the vocal recognition software, then the software sent back a string to trigger the AI image data set (AttnGAN)  that eventually generates an image relating to the sentence I said.

 

The work questions the normal logic and working flow of image-making(normally speaking is we frame one specific subject to photography it and the camera process and deliver the picture we pre-selected while we click the shutter), in the meantime, address a possibility to generate an improvisatory photograph by human and machine.