Microsoft has officially launched its first in-house AI image generation model, MAI Image 1, now available in Bing Image Creator and Copilot Audio Expressions.
The company first announced the model in October, and Microsoft AI chief Mustafa Suleyman confirmed on X that it will also be coming soon to the European Union.
According to Suleyman, the model performs especially well at creating images of food, nature, and artistic lighting, with impressive photorealistic detail.
In a blog post, Microsoft said MAI Image 1 is designed for speed and visual quality, outperforming many larger, slower AI models. It excels in generating realistic imagery with accurate lighting effects, reflections, and landscapes. The company says this speed allows users to quickly visualize ideas, experiment with variations, and refine them in other creative tools.
MAI Image 1 also integrates with Copilot Audio Expressions, where it generates artwork to accompany AI-created audio stories in “story mode.”
Earlier this year, Microsoft introduced its first in-house AI models — MAI Voice 1, a speech model, and MAI 1 Preview, a text-based model. These developments suggest Microsoft is moving toward more independence from OpenAI, whose models currently power parts of Microsoft’s AI products.
Still, Microsoft continues to use OpenAI’s latest GPT-5 model in its Copilot chatbot, alongside support for Anthropic’s Claude AI.
If this article helped you, please consider supporting our work. Every small contribution keeps Abijita.com independent and running.
MAI Image 1 now appears as one of the three available models in Bing Image Creator, alongside DALL·E 3 and GPT-4o, both from OpenAI.
