Microsoft AI has just announced its first text-to-image generator, MAI-Image-1, designed and developed in-house. The tech giant, which recently announced its first internal Microsoft AI models, called the new image generator “the next step in our journey.”
Microsoft says it solicited feedback from creative professionals to avoid “repetitive or generically stylized output.” MAI-Image-1 “excels” at photorealistic images like lightning, landscapes and more, the company claims. And it can process requests and produce images faster than “bigger, slower models.” The model has already secured a place in the top 10 of LMArena, the leading AI site where humans compare the results of different systems and vote for the best.
We haven’t had a chance to test Microsoft’s new Image Builder, but once we do, we’ll report back on its security guardrails. The company says it is committed to “ensuring safe and responsible outcomes.”
