Instagram launches AI-powered background editor

Instagram announced its new AI-generated background editing tool for U.S.-based users. The feature is driven by the generative algorithm allows users to transform backgrounds for their Instagram stories and photos through text-based prompts.

The background editor is directed by Ahmad Al-Dahle, Meta's lead for generative AI. In a blog post at Threads, Al-Dahle explained that this tool allows users to make changes to their stories' backgrounds which will open up new and creative possibilities.

"With backdrop, it is possible to alter the background of your photo with two taps and a prompt like 'chased by dinosaurs' or surrounded by puppies' to create an entirely new image to use in your Story. Click the button to create a backdrop at the top of a new Story to get started" Al-Dahle wrote. Users can also create their prompts.

Now you can try the Instagram "Try this" stickers

Once posted to stories, the AI-generated backgrounds will have a "Try the background" sticker, so that others can try the same text prompts on their images.

This launch is a continuation of Instagram's expanding range of AI offerings, including the ability to create creative images that are already available on Snapchat as well as other Meta platforms like Messenger as well as WhatsApp. Earlier this month, Meta rolled out a similar AI image-making tool called Imagine which, in turn, Snapchat revealed paid features that permit users to create fantasy-themed photos.

As AI technology for image generation advances, social platforms are racing to integrate the functionality into their apps. Instagram hopes features like editing backgrounds can differentiate it, though ethical concerns around deepfakes remain a topic of discussion regarding AI-powered tools for creativity.

Generative AI is an artificial intelligence that can create new content by itself instead of only analyzing existing content. "Generative," as in the "generative" part is the fact that these AI systems can generate brand-new images, texts audio, video, and other data that have never been seen before.

Generative AI relies on deep-learning algorithms, specifically one of the subsets of AI approaches known as neural networks. To learn patterns and concepts, these neural nets are trained using huge amounts of data - often containing millions or billions of data points. After the generative AI model has been adequately taught, it can then use its knowledge to create new and original designs based on the information it has uncovered in the training data.