Microsoft AI just announced its first text-to-image generator, MAI-Image-1designed and developed in-house. The tech giant, which recently announced its first proprietary Microsoft AI models, called the up-to-date image generator “the next step in our journey.”
Microsoft says it sought input from inventive professionals to avoid “repetitive or broadly stylized results.” MAI-Image-1 “excellently” handles photorealistic images such as lightning, landscapes and more, the company claims. It can also process requests and generate images faster than “larger, slower models.” The model has already secured a spot in the top 10 on LMArena, an artificial intelligence benchmarking site where people compare results from different systems and vote for the best.
We haven’t had a chance to test Microsoft’s up-to-date image generator, but when we do, we’ll report on its guardrails. The company says it is committed to “delivering safe and responsible results.”