Microsoft launches its first in-house AI image generator

Microsoft continues to roll out internal AI models, reducing its reliance on its long-standing partnership with OpenAI. Today, the company introduced MAI-Image-1, the first in-house developed image generation AI model. According to Blog postMAI-Image-1 is particularly useful for creating realistic results, and can create natural lighting and landscapes. Currently, the model is being tested on LMArena, and Microsoft said it plans to roll out MAI-Image-1 to Copilot and Bing Image Creator “very soon.”

Over the summer, Microsoft took its first break from collaborating with OpenAI when unveil The first two internally trained models, MAI-Voice-1 and MAI-1-preview. At the time, Mustafa Suleiman, head of Microsoft’s AI division, said in an interview interview That the company has a “huge five-year roadmap that we’re investing in quarter after quarter.” So far, it’s at least set up a solid pipeline of releases.