Meta has launched Muse Image and previewed Muse Video, the first media generation models from Meta Superintelligence Labs. Muse Image is available today across the Meta AI app, on meta.ai, Instagram Stories in the US, and WhatsApp in limited countries, and is coming soon to Facebook. Muse Video is coming soon to creators and Meta AI. Muse Image operates as an agent, invoking search and coding tools to improve accuracy, self-refining its own generations, and improving through scaling test-time compute. It integrates with Muse Spark to share tools and plan jointly. During reinforcement learning, Muse Image learns to write and execute code that produces accurate plots and QR codes, and condition on rendered figures to improve accuracy. It also learns to search the web to ground generated images in factual and real-time information, improving factual accuracy on knowledge-intensive prompts. Self-refinement emerged during RL training, allowing Muse Image to reflect on and improve its work within its chain of thought, such as making local edits or generating new images when larger parts are wrong. Muse Video, built on the same pretraining base, delivers exceptional visual fidelity with native audio support.