Microsoft unveils its first in-house AI image generator MAI-Image-1

Microsoft AI has introduced MAI-Image-1, its first text-to-image generator developed entirely in-house. The launch follows the tech giant’s broader strategy to build proprietary AI technologies and promises more immersive and creative experiences for users in the near future. Microsoft sought input from creative professionals to prevent the generation of repetitive or overly generic styles, while asserting that MAI-Image-1 performs exceptionally well with photorealistic visuals. It also boasts faster processing speeds compared to larger, slower models.

For now, the model is being tested on LMArena, and Microsoft said it plans to roll out MAI-Image-1 to Copilot and its Bing Image Creator "very soon."

The model has already secured a spot in the top 10 on the AI benchmark.

Microsoft, in the last couple of months, made its first break from collaborating with OpenAI when it unveiled its first two in-house trained models, MAI-Voice-1 and MAI-1-preview. At that time, Microsoft AI division leader Mustafa Suleyman said in an interview that the company had "an enormous five-year roadmap that we're investing in quarter after quarter."

The AI model has been trained to deliver “genuine value for creators” by steering clear of repetitive and generic results, the company said in its blog. The team did their data selection carefully and evaluated the tasks while taking continuous feedback from creative professionals.