Microsoft Is Adding an AI Art Generator to Office Suite
The app is called Microsoft Designer, and it’s a drag-and-drop image editor destined to compete with the likes of Canva and Easil. Most Microsoft Word users know the pain of inserting an image only for nearby text to dramatically shift. Designer appears to eliminate this problem by allowing Office users to create illustrative elements in a separate app made to accommodate several moving parts.
Designer contains templates, text editing, motion graphics, and millions of stock images and videos. The star of the show, however, is DALL-E 2, an increasingly popular text-to-image AI art generator made by OpenAI. Most people are familiar with DALL-E Mini, a similar but less powerful tool by AI artist Boris Dayma, since the public version of DALL-E 2 is technically still in beta and requires a waitlist sign-up to gain access. (The original DALL-E became available to everyone last month.) With Designer, Microsoft Office users will get to test the full power of DALL-E 2 and use its creations in banners, flyers, and more.
AI art generators like DALL-E 2 are easy to use, requiring only a text prompt to create a new image seemingly out of nowhere. Not only can users tell the AI what to make (like Microsoft’s “grumpy koala wearing a robe” example above) but they can say how to make it, whether in a watercolor style or in a way that imitates an ancient Roman painting. Users can also input locations, lighting descriptions, and perspectives (i.e. “from a distance”) to further customize their images.
Despite introducing AI as impressive as DALL-E 2 to a suite as popular as Microsoft Office, it’s unlikely that graphic designers will be out of a job anytime soon. Many AI-generated images are a little bit…off. Human subjects have smeared or disproportionate facial features; shadows don’t quite fall in the right place (or at all); elements of a prompt can be scrambled if the AI fails to understand the user’s intentions. DALL-E does allow users to essentially cut and commingle elements of different images to create an ideal result, but that’s more work than simply typing a description and waiting a few seconds, and it’s unlikely that the average Office user will have the artistic dexterity or the patience to do that.
Designer’s DALL-E 2 component isn’t the only AI element Microsoft is adding to its existing products. The company briefly mentioned that Bing will soon get its own AI text-to-image generator called Image Creator. This will roll out to select geographical regions as Microsoft monitors real-life performance and tailors Image Creator’s full release accordingly.
Continue reading
OpenAI’s ‘DALL-E’ Generates Images From Text Descriptions
All you need to do is give DALL-E some instructions, and it can draw an image for you. Sometimes the renderings are little better than fingerpainting, but other times they're startlingly accurate portrayals.
What to Expect From Intel’s 11th Generation Rocket Lake
There's a lot of leaks concerning Rocket Lake these days. Here's what we expect from Intel's next-generation desktop CPU.
Epic’s New MetaHuman Creator Generates Digital Characters that Avoid the Uncanny Valley
The company's new MetaHuman engine promises to deliver photorealistic digital characters in a snap, and you can check out a demo right now.
Intel Unleashes 3rd Generation Xeon CPUs Based on Ice Lake SP
Intel's 3rd Gen Xeon Scalable chips are out and offer real performance uplifts compared with previous Cascade Lake parts, but they aren't enough to win Intel overall performance leadership in the segment.