OpenAI's text-to-image tool DALL-E 3 now available in Bing Chat
image for illustrative purpose
New Delhi, Oct 05 Microsoft has announced that DALL-E 3, the latest text-to-image model from OpenAI, is now generally available to everyone within Bing Chat and Bing.com/create for free.
It's been available for about a week, first to Bing Enterprise users and then to Bing Image Creator, but it's now available to everyone.
"The DALL-E 3 model from OpenAI delivers enhancements that improve the overall quality and detail of images, along with greater accuracy for human hands, faces, and text in images," Microsoft said in a blogpost.
OpenAI's text-to-image AI model DALL-3, the third version, comes with a number of improvements, including the ability to follow user prompts more accurately and reliably.
The OpenAI model also has new safety features, such as invisible watermarks with time and date stamps to identify AI content, and a moderation system that automatically removes inappropriate or harmful images.
The tech giant said that it has trained the model on its terms of service and community guidelines, and it will automatically avoid images, "that contain nudity, violence, hate speech, or illegal activities."
Meanwhile, Microsoft has started to roll out a new update to its Paint app called Paint Cocreator, a new AI-powered experience powered by DALL-E which will help you create artwork in Paint by describing in a few words what you want to create.
The users will need to optionally select an art style and then click Create. Paint Cocreator will generate three variations of artwork for them to choose from. Select any of them to add to the canvas to start creating.
