Bing Chat users can now access DALL-E 3’s AI image generator

Bing Chat’s AI-powered in-house image generator gets 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’s 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 will get access to DALL-E 3 even before OpenAI’s ChatGPT gets access — which is scheduled to happen this month, but only for paying users. Microsoft will likely be the most popular image creation tool for a while.

DALL-E 3 is of course the third version of OpenAI’s image generation model. The company says it understands prompts much better than before, and can create images that are more creative and realistic. It is also designed to be easier to use; DALL-E 3 is integrated into Bing Chat and ChatGPT rather than running a standalone product, so you can build and improve your image by talking to a chatbot instead of trying to endlessly improve your initial claim.

OpenAI has also built new safety tools into DALL-E 3: it’s designed so you shouldn’t recreate images of public figures, for example, and you shouldn’t recreate hateful or NSFW images either. Within Bing Image Creator, Microsoft also embeds watermarks in each image to identify it as being created by artificial intelligence and has created a special content moderation system. As always, the proof will be in the pictures.

Microsoft plans to use DALL-E technology for more than just Bing, too. It’s working on an AI image creation tool in the Paint app called Paint Cocreator, for example, which will bring the DALL-E model directly to Windows.

Anyone can theoretically use DALL-E 3 now through Bing, although every time I’ve tried so far, it’s been “unable to process new requests” and refused to create my image. Looks like the servers have been overloaded for a while: Microsoft servers Posted by Mikhail Parakhin“We were expecting some strong interest, but we weren’t expecting a lot.”

When you create an image, it will not only create the image you requested, but will also offer suggestions on where you should 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 create these images for me either, since the system was overloaded, but it seemed like a fun way to create alongside the tool.)