The image generator inside the AI-powered Bing Chat is getting a big upgrade today: Microsoft announced that OpenAI’s latest DALL-E 3 model is now available to all Bing Chat and Bing Image Creator users. It has been rolling out over the last week or so, first to Bing Enterprise users and then to Bing Image Creator, but now it’s open to everyone.
Bing is getting DALL-E 3 access even before OpenAI’s own ChatGPT does — that’s scheduled to happen this month, but only for paying users. Microsoft is likely to be the most popular image generating tool for a while.
DALL-E 3 is, of course, the third version of OpenAI’s image generating model. The company says it understands prompts far better than before and can create images that are both more creative and more photorealistic. It’s also designed to be much easier to use; DALL-E 3 is integrated into Bing Chat and ChatGPT rather than powering a standalone product, so you can create and refine your image by conversing with a chatbot rather than trying to endlessly perfect your initial prompt.
OpenAI also built new safety tools into DALL-E 3: it’s designed to not recreate images of public figures, for instance, and should also not create hateful or NSFW images. Within Bing Image Creator, Microsoft is also embedding watermarks in each image to identify them as AI-generated and has created a content moderation system of its own. As ever, though, the proof will be in the images.
Microsoft is planning to use DALL-E tech in more than just Bing, too. It’s working on an AI image creation tool in the Paint app called Paint Cocreator, for instance, which will bring the DALL-E model right into Windows.
Anyone can theoretically use DALL-E 3 now through Bing, though every time I’ve tried so far, it has been “unable to process new requests” and refused to make my image. The servers have apparently been overloaded for a while: Microsoft’s Mikhail Parakhin posted, “We expected some strong interest, but we didn’t expect THAT much.”
When you do make an image, not only will it create the one you asked for but it’ll also offer suggestions on where to go next: “Can you add a rainbow in the background?” “Make it a cat instead of a dog.” “Add some birds around the waterfall.” (Bing Chat wouldn’t make those images for me, either, because the system was overloaded, but it seems like a fun way to create alongside the tool.)