The latest DALL-E model just dropped for business users – and this one is even better at hands
Companies can now sink their creative claws into the latest popular model AI art generator DALL-E as part of their ChatGPT account, developer OpenAI has announced.
“Visually striking” and “sharper” is how the company described the DALL-E 3’s intricately detailed visuals compared to its predecessor. That includes faces (which gen AI is very good at) and hands (which gen AI is shockingly bad at).
The new training model is now available for ChatGPT Plus and ChatGPT Enterprise users, with the AI tool will be available via the API and in Labs later this year.
Get to work
Within an organization the call is always the same. More content. Better content. Faster content. But above all, more content. So that’s where a tool like DALL-E 3 comes in, which quickly generates photorealistic images and graphics for use and iteration through text descriptions.
In its big reveal, OpenAI highlighted AI-powered web design and a logo maker as an example of business use cases. But really, it’s for anyone who needs a steady stream of visual branding assets. Although whether that’s good or bad is up for debate, since the platforms are not without their critics.
DALL-E 3 itself brings a few more upgrades. It is now better at responding to extensive, detailed cues to deliver those seemingly “striking” images. There is support for landscape and portrait aspect ratios. Behind the scenes, the model will now pay more attention to captions created by users. In other words, it should do a better job of what users tell it to do.
The AI research and development company also confirmed that it is working on a digital provenance tool. Early testing shows a 99% hit rate in identifying raw DALL-E generated images. That success rate drops to a respectable 95% when making minor edits to the image, such as cropping or compression.
Users can sign up for DALL-E 3 by clicking here. When our Cameras Editor tried it out, he called it the easiest, beginner-friendly AI art generator out there, but found that it struggled to produce photorealistic images that warranted the artistic touch of a human hand.