Meta has announced the launch of Muse Image, its first image generation model from Meta Superintelligence Labs. The new tool is integrated into the company’s Meta AI assistant and allows you to create and edit visual content using text queries.
Meta has announced the launch of Muse Image, its first image generation model from Meta Superintelligence Labs. The new tool is integrated into the company’s Meta AI assistant and allows you to create and edit visual content using text queries.
As stated in the company's official blog, the model works in conjunction with the Muse Spark text neural network, which allows AI to analyze complex queries and search for information on the Internet in real time. Users can generate images from scratch, remove unwanted objects from ready-made photos, create functional QR codes, and add readable text to images, for example, for infographics.
A separate feature is the ability to redesign rooms: the user can upload a photo of their room, and AI will suggest a new interior using real products from the Internet or Facebook Marketplace. The developers also added an interaction function with Instagram: in Meta AI, you can tag public profiles via @-mention to use their photos to create a shared visual (the option can be disabled in the privacy settings).
The tool is currently rolling out in a limited number of countries. It is available as over 30 AI effects for Instagram Stories and a built-in generator in WhatsApp chats. Basic use of the model is free, but active generation requires a paid subscription. The tool will soon be available on Facebook and Messenger, and will also be available to advertisers.
“Images are just the beginning, we are already developing the Muse Video model,” the company notes.
Meta previously launched the Pocket game coding app , which allows users to create small interactive apps and games using AI prompts.
