Microsoft has introduced its first text-to-image generator, named MAI-Image-1, which has been developed in-house. This announcement follows the company’s recent release of its first internally developed AI models. Microsoft describes MAI-Image-1 as a significant advancement in their ongoing AI initiatives.
To enhance its output quality, Microsoft engaged with creative professionals during the development process to address concerns about generating repetitive or generic visuals. The company claims that MAI-Image-1 is particularly adept at producing photorealistic images, including subjects like lightning and landscapes. Additionally, it reportedly processes requests and generates images more quickly than larger, more traditional models. The generator has already achieved a place in the top 10 on LMArena, a benchmark site where users evaluate and vote on the outputs of various AI systems.
While the performance of MAI-Image-1 has not yet been independently tested, Microsoft has emphasized its commitment to implementing safety measures to ensure responsible use of the technology.
Source: https://www.theverge.com/news/798923/microsoft-ai-image-generator-in-house