Microsoft AI announces first image generator created in-house

Microsoft has announced the release of its first in-house text-to-image generator, MAI-Image-1. The new AI model was designed and developed by the tech giant, with input from creative professionals to avoid repetitive or generic outputs. Microsoft claims MAI-Image-1 excels at photorealistic imagery, such as lightning and landscapes, and can process requests and produce images faster than larger, slower models. The model has already secured a spot in the top 10 of LMArena, an AI benchmark site. MAI-Image-1 joins Microsoft's other AI products, including the voice generator MAI-Voice-1 AI and chatbot MAI-1-preview. While Microsoft was an early funder of OpenAI, the company's relationship with the AI research company has become more complex. Microsoft is also making significant investments in training its own AI models, like MAI-Image-1, and using Anthropic's AI models for some features in Microsoft 365. The company says it is committed to ensuring safe and responsible outcomes with its new image generator.