The tech is available in select countries through Bing.
Microsoft Bing has released Image Creator – an AI tool powered by DALL-E 2. It is available in a limited preview to select countries.
Image Creator works like Stable Diffusion and Midjourney: it generates "an image that doesn’t exist" based on a text prompt.
The function is coming to Edge soon, where users will be able to use Image Creator in the sidebar. According to the company, Image Creator works best when you type in a description of something with additional context, like location or the art style you’d like to emulate.
Here are two projects made in the tool: a “dog astronaut launching into space, digital art” and a “crochet goldfish pencil drawing."
Microsoft is working with OpenAI to prevent inappropriate results, so explicit sexual and violent content has been removed from the dataset used for training. Additionally, the company has applied additional technology to address biases found in generative image technology.
"We’ve also adopted a range of mitigations, such as leveraging Microsoft Bing insights on problematic queries, as well as using blocklists and classifiers powered by Azure cognitive services that lower the risk of offensive prompts being issued."