Something we could have used to test visual understanding of products and their use.
OpenAI’s latest neural network creates images from written descriptions By Ryan Daws | January 6, 2021 | TechForge Media
Categories: Neural Network, OpenAI, Society,
Editor at TechForge Media. Often sighted at global tech conferences with a coffee in one hand and laptop in the other. If it's geeky, I'm probably into it.
OpenAI has debuted its latest jaw-dropping innovation, an image-generating neural network called DALL·E .... a 12-billion parameter version of GPT-3 which is trained to generate images from text descriptions.
“We find that DALL·E is able to create plausible images for a great variety of sentences that explore the compositional structure of language,“ OpenAI explains. Generated images ca range from drawings, to objects, and even manipulated real-world photos. Here are some examples of each provided by OpenAI: ...
No comments:
Post a Comment