OpenAI, an organization that researches artificial intelligence, has presented a tool, ‘DALL E 2, which allows you to create realistic images from text
A few weeks ago, Google unveiled a new artificial intelligence (AI) tool that can transform any text into a photorealistic image. It turns out that Google isn’t the only tech company competing for the AI imager.
Meet OpenAI, a San Francisco-based company that created its first text-to-image system in January 2021. Now, the team has unveiled its latest system, called “DALL · E 2”, which generates multiple images. realistic and accurate with 4x higher resolution.
Both Imagen and DALL · E 2 are tools that use artificial intelligence to transform plain text messages into photorealistic images that never existed before. DALL E 2 can also make realistic changes to existing images, which means you can model famous paintings in different styles or even create a Mohawk on the Mona Lisa.
The artificial intelligence system was created by training a neural network on images and their textual descriptions.
Through deep learning, DALL · E 2 can identify individual objects and understand the relationships between them. OpenAI explains: ‘DALL · E 2 learned the relationship between images and the text used to describe them. It uses a process called ‘diffusion’, which starts with a random dot pattern and gradually transforms it into an image as it recognizes specific aspects of that image. ‘
‘AI benefiting humanity’
OpenAI says its mission is to ensure that artificial intelligence benefits all of humanity. The company says: ‘Our hope is that DALL · E 2 will allow people to express themselves creatively. DALL · E 2 also helps us understand how advanced AI systems see and understand our world, which is central to our mission to create artificial intelligence for the benefit of humanity. ‘
However, despite the company’s intentions, this category of technology is difficult to implement responsibly. With this in mind, OpenAI says it is currently studying the limitations and capabilities of the system with a select group of users.
The company has already removed explicit content from training data to avoid generating violent, hateful or pornographic images. They also say that DALL · E 2 cannot generate photorealistic AI versions of the faces of real individuals.
* Through Designboom
Source: Terra
Benjamin Smith is a fashion journalist and author at Gossipify, known for his coverage of the latest fashion trends and industry insights. He writes about clothing, shoes, accessories, and runway shows, providing in-depth analysis and unique perspectives. He’s respected for his ability to spot emerging designers and trends, and for providing practical fashion advice to readers.
