Meta’s AI Chief Alexander Wang Shares Personal Photo Tip After New Image Model Launch

Meta has dropped a new tool dubbed Muse Image, and it is the first image generated by Meta Superintelligence Labs headed by Alexander Wang. The debut of the tool was filled with a mix of research showcase and controversy that followed after. Amid all this, Meta's Chief AI Officer, Alexander Wang, came up with a single pitch to get the most out of the model. In a thread on X, he asked all the users to upload their own photos, mention friends, and pull from what's trending, framing Muse Image as a tool built for everyday sharing. Wang also wrote, asking the users to upload their own photos, tag friends, and hop on to what's currently trending. The focus of the tool will be to move image generation to stories, feeds, and even group chats. Meta says

that the model packs more than 30 AI effects on Instagram Stories and is live in WhatsApp direct chats with Meta AI. As for the availability of the application, it is only available in the United States via the Meta AI app, WhatsApp, and Instagram. It has already been announced that Meta will soon be launching the feature in other countries as well. Apart from that, taking a deep dive into the technical aspect, Wang said he is most excited about three things -Self-refinement: Where the model improves its own output within its chain of thought.Multi-reference composition: which blends multiple images into one coherent generation.Multi-turn editing: which lets you refine the result over several rounds. Meta has already stated that the self-refinement behaviour was not designed, and it emerged during reinforcement learning because it produced better images. That's not it; some controversy also followed in the background as people said that a feature that lets users pull a public Instagram account's photo into a generated image just by tagging the person could be a disaster for those who respect consent.