Microsoft has launched MAI-Image-1, its latest model for generating images from textual prompts, which was unveiled in October 2025. Users can explore this technology in Bing Image Creator or Copilot Audio Expression.
This is Microsoft’s third innovation in this domain. In August 2025, the company introduced MAI-Voice-1 for natural speech generation and MAI-1-preview, its first text model.
MAI-Image-1 is now available in Bing Image Creator alongside DALL‑E 3 and GPT‑4o. In Copilot Audio Expression, it will be utilized in Story Mode to visualize narratives.
Currently, MAI-Image-1 is accessible in all countries with Bing Image Creator and Copilot Labs, including Ukraine, but is not yet available in the EU.
According to Microsoft, MAI-Image-1 "excels at creating photorealistic images, including lighting, landscapes, and more." The model has made it into the top 10 in the text-to-image generation category on LMArena.