Venture into the captivating world of AI-driven image generation with our blog series. As we delve into the realm of Generative Adversarial Networks (GANs) and other cutting-edge algorithms, discover how artificial intelligence is reshaping the landscape of visual content creation. From realistic image synthesis to artistic exploration, these articles aim to unravel the transformative impact of AI on pushing the boundaries of creativity and innovation in the field of digital imagery. Whether you are an enthusiast, a creative professional, or simply curious about the future of visual arts, join us in exploring the fascinating synergy between AI and image generation.
By Jess Weatherbed, a news writer focused on creative industries, computing, and internet culture. Jess started her career at TechRadar, covering news and hardware reviews.
Facebook and Instagram are getting some new AI-powered creative tools that will allow users to edit their photographs and produce “high-quality videos” using text descriptions. On Thursday, Meta CEO Mark Zuckerberg announced two new capabilities built on Emu — the company’s foundation model for image generation — that are being integrated into Facebook and Instagram.
The first, dubbed “Emu Edit,” will allow users to “precisely alter images based on text inputs.” The video demonstration for this looks similar to existing tools provided by Adobe, Google, and Canva, providing a way for users to remove or replace objects and people from photographs without any professional image editing experience.
What’s slightly wild is that it doesn’t seem to require that users manually select the section of the image they want to change. The video suggests you can type in something like “turn the dog into a panda,” and Emu Edit will be able to identify the dog within the image. Meta also says that Emu Edit will precisely focus on only making changes that are relevant to the edit request — for example, asking it to add text to a baseball cap won’t change anything else about the cap design.
“Emu Video” is the second tool Meta is working on. According to the blog post Meta released alongside Zuckerberg's teaser, this one can generate video from text prompts, reference images, or a combination of the two inputs. The results seem far from realistic, but they also look like a step up from the rough animations that Meta’s Make-A-Video system was producing last year.
There’s no word yet on when users can expect these new editing capabilities to arrive on Facebook or Instagram, or if this announcement is tied to the AI-powered creator tools that Meta teased last year. We’ve reached out to Meta for clarification and will update this story if we hear back.
Introducing a native AI-based image editing feature to its social media platforms especially seems like a no-brainer here for Meta. There are plenty of similar tools available like the Google Photos Magic Editor and Adobe’s generative fill for Photoshop, but it’s obviously more convenient for Instagram and Facebook users to not have to jump over to a third-party service.
/ Sign up for Verge Deals to get deals on products we’ve tested sent to your inbox daily.
The Verge is a vox media network
© 2024 Vox Media, LLC. All Rights Reserved

source