Meta AI adds Muse Image and Video generation models
By Steven Van ·
Muse Image edits and composes from references and is live in the Meta AI app, WhatsApp, and Instagram Stories in the US; Muse Video is coming soon.
Meta Superintelligence Labs has introduced two new generation models, Muse Image and Muse Video, inside Meta AI.
- Muse Image is described as Meta's most advanced image model yet. It follows instructions closely, edits existing images with precision, and can compose a new image from multiple reference images. It also works agentically: planning a prompt, pulling in web context, and refining its own output before returning a result. It's live now in the Meta AI app, on meta.ai, in WhatsApp, and in Instagram Stories in the US.
- Muse Video, built on the same foundation as Muse Image, generates video with native audio. Meta says it is coming soon.
Details are in the original announcement.
Meta AI
Meta's AI assistant for chat, image generation, and live camera understanding — talk to it on the web or inside WhatsApp, Instagram, Messenger, and Facebook.
View Meta AI →