Obtaining a desired image can be a long exercise in trial and error. OpenAI

The folly of making art with text‑to‑image generative AI

Visual artists draw from visual references, not words, as they imagine their work. So when language is in the driver’s seat of making art, it erects a barrier between the artist and the canvas.
Mario Klingemann’s ‘Neural Glitch Portrait 153552770’ was created using a generative adversarial network. Mario Klingemann

When the line between machine and artist becomes blurred

Later this month, Christie’s will be auctioning its first piece of AI art – a portrait created via machine learning.
Frederic Bazille’s Studio 9 Rue de la Condamine (left) and Norman Rockwell’s Shuffleton’s Barber Shop (right). The computer was able to detect similarities in the composition of both paintings. Yellow circles indicate similar objects, red lines indicate composition, and the blue square represents similar structural elements.

Computer science can only help – not hurt – art historians

I was the lead of a team of computer scientists at Rutgers that published a paper this past August titled, “Toward Automated Discovery of Artistic Influence.” In that paper we reported on our research…

Contact Ahmed for

  • General
  • Media request
  • Speaking request
  • Consulting / Advising
  • Research collaboration
  • Research supervision