Read the affiliate disclosure page to find out how can you help MSPoweruser effortlessly and without spending any money. Read more
Meta, formerly known as Facebook, has unveiled two new generative AI tools that will enable users to quickly create videos and edit images using text prompts. The tools, called Emu Video and Emu Edit, are still in development. Still, they can potentially revolutionize how people create and share content. Meta recently also introduced Meta AI, a new AI assistant that will be available on WhatsApp, Messenger, Instagram, and more.
Emu Video can generate short video clips from text prompts. For example, a user could type “a dog playing fetch,” and the tool would generate a video of a dog playing fetch. Emu Video can also produce high-quality video content from simple text or still image inputs. For example, a user could provide a photo of a cat and ask the tool to turn it into a cartoon.
On the other hand, Emu Edit is an image editing tool that can handle various tasks, such as local and global edits, background removal and addition, color and geometry transformations, detection, and segmentation. The tool can also accurately follow detailed instructions, ensuring that pixels unrelated to the specified tasks in the input image remain unchanged. Here is a video posted by Mark Zuckerberg, CEO of Meta.
The potential applications of Meta’s new generative AI tools could be vast. For example, they could generate animated stickers and GIFs, ideate on new concepts, liven up reels, and share unique birthday greetings.
The tools could significantly reduce back-and-forth time between creative and media teams while freeing up resources for strategic tasks like audience analysis.
It seems that Meta’s new generative AI tools could potentially change how people create and edit video and image content. Still, we’ll have to see how they perform in practice before drawing any firm conclusions.