Photos made by robots thanks to artificial intelligence

FRIDA is an eccentric robot. Not because of its hardware, since it’s basically an industrial robotic arm, but because of its software. The artificial intelligence it is endowed with allows it to create images in well-defined artistic styles, responding to requests made to it.

The main people responsible for this initiative are Peter Schaldenbrand, Jean Oh and Jim McCann from the Robotics Institute of Carnegie Mellon University in the United States.

The name FRIDA corresponds to the English abbreviation of the Framework and Robotics Initiative for Developing Arts, but, as Schaldenbrand and his colleagues acknowledged, choosing the acronym FRIDA was an homage to the Mexican painter Frida Kahlo (1907–1954). Is.

Users can instruct FRIDA to paint a representation of it by entering a text description, submitting other artwork to inspire her style, or uploading a photo. The team is also experimenting with other inputs such as audio.

“FRIDA is a robotic painting system, but it is not an artist,” Schaldenbrand warns. “FRIDA does not generate ideas to communicate. FRIDA is a system that an artist can collaborate with. The artist can specify high-level goals for FRIDA and then FRIDA can execute them.”

Frida in action. (Photo: Carnegie Mellon University)

The robot uses an artificial intelligence model similar to tools such as OpenAI’s ChatGPT and DAL-E2, which generate text or an image, respectively, in response to a prompt. FRIDA simulates how you would paint an image with brush strokes, and uses machine learning to assess your progress as you work. (Spring: ncyt d amazing,