Meta has rolled out Muse Image, its first image generation model from Meta Superintelligence Labs.
Muse Image helps users create high-quality visuals, and enables a number of creative tools across Metaʼs apps.
Whether starting from scratch or working with an existing photo, users can describe what they want in simple, conversational language, and Muse Image will generate it, including rendering text inside the visuals.
Meta AI now includes a presets panel with suggested prompts. These include restoring old photos, checking our hairstyle or reimaging a subject as claymation character or video game hero.
Users can as Meta AI to redesign a room from a picture, using real products from the web or Facebook Marketplace.
Muse Image works with Muse Spark, taking multiple steps behind the scenes, such as planning its layout, looking up real-time web context, and blending multiple visual references at once.
Users are able to @-mention Instagram accounts in the Meta AI app to bring specific Instagram profiles into their images.
Editing is simple: users tap the markup icon to circle, sketch or annotate edits on the photo.