Meta drops Muse Image and Muse Video, its first media generation models

Meta Superintelligence Labs 推出 Muse Image 和 Muse Video

Meta's Superintelligence Labs released Muse Image and Muse Video. Muse Image handles precise instruction-following, editing, and multi-reference composition using Instagram social context, plus agentic tool use. Muse Video shares the same pretrained base, outputs video with native audio. Available now in select countries via Meta AI app, web, Instagram Stories, and WhatsApp. The post doesn't disclose model size, latency, or which countries.

Why it matters: Meta's first media generation models, Muse Image and Muse Video, each bring differentiators (social context reading, tool use), but the post lacks details on Muse Spark and actual output quality — 78 for now.