By Tom Warren, a senior editor covering Microsoft, PC gaming, console, and tech. He founded WinRumors, a site dedicated to Microsoft news, before joining The Verge in 2012.
Microsoft is adding an AI-powered image creator to its Bing search engine today. The Bing Image Creator will be powered by an “advanced version” of OpenAI’s DALL-E model and will let Bing users create images by simply writing what you want to generate.
“For those in the Bing preview, Bing Image Creator will be fully integrated into the Bing chat experience, rolling out initially in Creative mode,” explains Yusuf Mehdi, Microsoft’s head of consumer marketing. “By typing in a description of an image, providing additional context like location or activity, and choosing an art style, Image Creator will generate an image from your own imagination.”
Microsoft is also bringing this Bing Image Creator to its Edge browser. A new icon will appear in the Edge sidebar that allows you to create images in a text entry prompt. Microsoft is limiting this image creator to its creative mode in Bing and plans to optimize how it works in multi-turn chats. “We will initially only include Image Creator in the creative mode of Bing chat and our intention is to make it available in balanced and precise mode over time,” says Mehdi.
Bing has three modes of responses: creative, balanced, and precise. The creative mode includes responses that are “original and imaginative,” whereas the precise mode favors accuracy and relevancy for more factual and concise answers. Microsoft is clearly being more careful with its image creation feature after Bing’s rude responses made headlines last month.
If you’re not in the new Bing preview, you can access this Bing Image Creator separately at bing.com/create for English text-to-image generation. Microsoft says it will add more language support over time. Bing preview users will be able to access the image creator in the usual chatbot prompt or through Microsoft Edge.
Microsoft’s fast focus on bringing AI-powered text-to-image features to Bing could open the search engine up to generating bad images. Experts have warned about text-to-image systems producing images that could be used for propaganda, harassment, misinformation, and more.
Microsoft says it’s protecting against any misuse. “We have ensured OpenAI’s safeguards, plus additional protections, have been incorporated into Image Creator,” says Mehdi. “For example, we have put controls in place that aim to limit the generation of harmful or unsafe images. When our system detects that a potentially harmful image could be generated by a prompt, it blocks the prompt and warns the user.”
Alongside this new image creator, Microsoft is also bringing its Stories and Knowledge Cards 2.0 features of Bing to all users. Stories offer a snippet of information with images and short videos, while Bing’s latest AI-powered Knowledge Cards highlight key information.
/ Sign up for Verge Deals to get deals on products we’ve tested sent to your inbox daily.
The Verge is a vox media network
© 2023 Vox Media, LLC. All Rights Reserved
source
