Microsoft’s Bing AI chatbot can generate images based on text input from the user. Users can provide a description of the image with additional details. Bing uses a version of OpenAI’s Dall-E model for images.

Image generator It’s called Bing Image Creator It’s in Bing chat and in the Edge browser. The image creator currently only works if users start a conversation in creative mode, not in balanced or subtle mode. Users can write a description of the image, provide additional context such as a location or activity, and choose an artistic movement. In order to create a picture in a chat, users have to say something like “draw a picture” or “take a picture.” Bing Image Creator can then create a newsletter or provide inspiration for redesigning a room, Microsoft offers as examples.

The image generator uses an “advanced version” of OpenAI’s Dall-E model, “with added protection.” For example, Microsoft says that Bing Image Creator should create as few harmful or unsafe images as possible. If the generator thinks the user wants to do this, a warning will appear. Microsoft also wants you to indicate with a Bing icon in the lower left corner that an image has been created with Image Creator, to warn others.

Microsoft says Image Creator will only be released to “designated” preview users for now, to bring it to other users later. Bing Image Creator works on both desktop and mobile. In the future, the image generator should also work in Balanced and Fine modes, and with more languages.

Furthermore, Microsoft says it will bring Stories and Knowledge Cards 2.0 to Bing search functionality. Stories are images and short videos that should appear in searches, while Knowledge Cards 2.0 are infographic-like cards that should provide “fun facts and information” in searches. Version 2.0 uses artificial intelligence to display “interactive and dynamic” content such as charts and timelines.

Stories (left) and Knowledge 2.0 cards