DALL-E
Exciting news on the AI front I’ve just been accepted for a DALL-E account, DALL-E is a new AI system that can create realistic images and art from a description in natural language.
OpenAI, the company co-founded by Elon Musk and funded by Microsoft, has reached another milestone with DALL-E, an AI app that can create an image out of nearly any description. For example, if you ask for “a bicycle made of cheese” or a “high quality illustration of a Porsche flying through space,” it will deliver those things, often with startlingly good quality (and sometimes not).
OpenAI’s mission is to ensure that artificial general intelligence (AGI)—by which we mean highly autonomous systems that outperform humans at most economically valuable work—benefits all of humanity.
“Unlike a 3D rendering engine, whose inputs must be specified unambiguously and in complete detail, DALL·E is often able to ‘fill in the blanks’ when the caption implies that the image must contain a certain detail that is not explicitly stated,” according to the OpenAI team.
It can also draw and combine multiple objects and provide different points of view, including cutaways and object interiors. Unlike past text-to-image programs, it even infers details that aren’t mentioned in the description but would be required for a realistic image. For instance, with the description “a painting of a wolf running through a field during the summer,” the agent was able to determine that a shadow was needed.
I’m looking forward to testing out the possibilities with this system hopefully I can create to dope imagery but know me it will end up being nightmare fuel…. I guess we’ll see. Big thanks to the team at DALL-E for accepting me..
