Meta has introduced Muse Image, a new artificial intelligence model that generates and edits images from text prompts, the company recently announced. It is the first image-generation system from Meta Superintelligence Labs, the division led by Alexandr Wang.
The model is now available through Meta AI across its dedicated app and website, as well as in Instagram Stories in the United States and on WhatsApp in a limited set of countries. Meta plans to bring Muse Image to Facebook, Messenger, Instagram, and WhatsApp more broadly in the coming weeks. Advertisers will gain access through Advantage+ creative at a later date.
Muse Image functions as what Meta describes as an “agentic” system, meaning it can search the web, write and run code, and refine its own outputs to improve accuracy. Users can type simple prompts to generate images, edit existing photos by sketching directly on them, or combine multiple visual references by tagging Instagram accounts. The model also supports iterative changes, remembering the full conversation context so adjustments can be made without starting over.
Additional features include a panel of preset suggestions for quick creation, a tool to redesign a room by snapping a photo and pulling product listings from Facebook Marketplace, and the ability to produce legible text within images such as infographics or QR codes.
The image model is available in select countries at no cost for everyday use, with additional creation capacity offered through Meta’s subscription plans. Meta also previewed Muse Video, a video generation model built on the same pretraining base, which it said will be released to creators and Meta AI users in the future. No timeline was provided for the video tool.
