Thanks to an OpenAI model, a new art scene has exploded. Hackers have been modifying an OpenAi model to make image generation tools. To get an ‘artwork’ from these tools, all you have to do is prompt them with a description of the image you want to see, as Vice details:
Listen beautiful relax classics on our Youtube channel.
While the new CLIP-based systems are reminiscent of GPT-3 in their “promptability,” their inner workings are much different. CLIP was designed to be a narrow-scoped tool, albeit an extremely powerful one. It is a general purpose image classifier that can decide how well an image corresponds with a prompt, for example, matching an image of an apple with the word ‘apple.’ But that is all. “It wasn’t obvious that it could be used for generating art,” University of California, Berkeley computer science student Charlie Snell,who has been following the new scene, said in an interview.
But shortly after its release, hackers likeRyan Murdock, a machine learning artist and engineer, figured out how to connect other AIs up to CLIP, creating an image generator. “A couple of days after I started messing around with it, I realized that I could generate images,” Murdock said in an interview.
Image: Mordechai Rorvig