Refresh
OpenAI debuts the generation of native images in model 4o
And we go to the races: Sam Altman is calling this one of the most fun advances, and his generation of native images in model 4. He quickly noticed ‘is a great step forward’ and something Openai has been excited to implement for quite some time, for a lot of people.
Altman points out that the best way to explain it is to show it, so we are already in a demonstration. In just a few seconds after the notice, Operai showed an image with which the team said that it has ‘perfect text’. Apparently showing a jump in terms of understanding the warning and creation of the image with clear text, and a single point of view effect.
The live transmission of OpenAi has begun, and in the previous period at the start time of 2pm ET / 11am PT / 6pm GMT, we are being treated with several images. Some of these overlap, but each few seconds are updated and shows all the different styles.
The description of the live broadcast indicates that we will listen to Sam Altman, Gabriel Goh, Prafulla Dhariwal, Lu Liu, Allan Jabri and Mengchao Zhong discussing the generation of images 4th.
Well, the live broadcast title is throwing much more light than to see that we can expect … much more than the image intitally mocked. It is titled “4th Generation in Chatgpt and Sora”, which means that we are probably obtaining improvements in the creation of images within Chatgpt and Sora.
The mention of the latter could mean more general improvements for the generation of text to video as well.
Less than 15 minutes to the end now!
More about artificial intelligence
