The background editor is directed by Ahmad Al-Dahle, Meta's lead for artificial intelligence generative. In an announcement post in Threads, Al-Dahle said the tool allows users to initiate changes to their stories' backgrounds which will open up new and creative possibilities.

"With backdrop, it is possible to alter your background photo in just two taps and the prompt 'chased by dinosaurs' or surrounded with puppies to create a completely new image for your Story. Tap the button for background at the top of a new Story to start,'" Al-Dahle wrote. Users can also create their prompts.

Now, you can test using the Instagram "Try it" stickers

When they are posted to stories the AI-generated backgrounds will feature a "Try It" sticker so that other users can use the same text prompts on their photos.

The new feature builds on Instagram's growing range of AI products, which include innovative tools that are available on Snapchat as well as other Meta platforms, including Messenger as well as WhatsApp. The month before, Meta rolled out a similar AI image generator named Imagine, while Snapchat unveiled paid features enabling users to create fantasy-themed photos.

As AI image generation technology advances, social platforms are rushing to build the capability into their applications. Instagram is hoping features like editing backgrounds can distinguish it from its competitors even though ethical questions about deepfakes remain a topic of discussion regarding AI-powered tools for creativity.

Generative AI refers to an artificial intelligence capable of creating new content by itself instead of just analyzing existing content. The "generative" part refers to the fact that these AI systems can create brand-new images, texts audio, video, and other data that have never been seen before.

Generative AI relies on deep learning algorithms, specifically a subset of AI approaches known as neural networks. To discover patterns and concepts, neural nets are trained using vast datasets - sometimes containing millions or billions of data points. After the machine-learning AI model is sufficiently trained, it can use its knowledge to create new, original creations based on the information it has uncovered in the training data.