Meta Unveils Media Generation Models Muse Image and Muse Video

AIatMeta · x · 2026-07-08

Meta's Superintelligence Labs has released its first batch of media generation models, Muse Image and Muse Video. Muse Image is their most advanced image generation model to date, capable of precise instruction following, accurate editing, and multi-reference image composition. It leverages Instagram data for social context and introduces agentic tool-calling capabilities for integration with Muse Spark. Users can try it out in the Meta AI app and web version, as well as in Instagram Stories and WhatsApp (initially limited to select countries, with more regions rolling out gradually).

Related event: Meta Launches Muse Image and Muse Video Models(71 posts)→

Original post →

More from Multimodal

Multimodal channel →