Microsoft has unveiled its latest model for generating images from text prompts, MAI-Image-1, which was introduced in October 2025. Users can experience it through Bing Image Creator or Copilot Audio Expression.
This marks Microsoft's third proprietary model in this domain. Earlier, in August 2025, the company released MAI-Voice-1 for generating natural speech and MAI-1-preview – its first text model.
In Bing Image Creator, MAI-Image-1 is now available alongside DALL‑E 3 and GPT‑4o in the menu. In Copilot Audio Expression, it will be utilized in Story Mode for visual storytelling.
MAI-Image-1 is currently accessible in all countries with access to Bing Image Creator and Copilot Labs, including Ukraine, although it is not yet available in the European Union.
As previously stated by Microsoft, MAI-Image-1 "excels at creating photorealistic images, including lighting effects (such as reflections and glare), landscapes, and more." The model has also ranked in the top 10 for text-based image generation on LMArena.