goal The upcoming AI-based tools will allow you to edit any image in very interesting ways.
The company’s CEO, Mark Zuckerberg, previewed some of the upcoming capabilities of Emu (Expression Media Universe), Basic Meta Image Generation Model revealed in September.
The first tool announced is Emu Edit, which can “precisely alter images based on text input.” For example, you can add a dog to an existing image, remove a person from an image, turn a dog into a panda, or change the image background.
Emu Video can generate “high quality” videos based on text prompts. Zuckerberg’s example shows how an image of a panda can be turned into a video; Other aspects of the image can also be modified, including its style and settings.
Zuckerberg says the company is “working to integrate these creative editing capabilities into videos and photos for Facebook and Instagram.”
The demonstration is impressive, although it is not the first time we have seen artificial intelligence tools with similar capabilities; For example, Google’s magic editorAnnounced in May, it can also alter different aspects of a photo.
in a blog entryMeta explained these upcoming tools in a little more detail. The company claims that one of the advantages of Emu Edit is that it can follow instructions precisely, meaning it can alter a particular part of the image while the rest of the image remains the same. As for Emu Video, the company claims that the approach it uses generates higher quality videos that are more faithful to the text message than other artificial intelligence tools.
The company also noted that Emu Video and Emu Edit “certainly do not replace professional artists and animators,” although it did not go into detail about how it plans to protect these groups from AI invades your territory.