overview
What is MAI-Image-2.5?
MAI-Image-2.5 is a text-to-image and image-to-image editing tool developed by Microsoft that enables users to generate high-quality, photorealistic outputs and precisely control visual content. It is a key part of Microsoft's broader MAI (Microsoft AI) initiative, developed internally rather than relying on OpenAI's models. The tool's core strengths include photorealism, adherence to complex prompts, and enhanced text rendering within images. MAI-Image-2.5 was officially launched at Microsoft Build 2026 (June 2-3, 2026), introducing two variants: MAI-Image-2.5 for maximum fidelity and professional-grade performance, and MAI-Image-2.5-Flash for faster, more efficient, and lower-cost scalable production workloads. It is currently available to developers through Microsoft Azure AI Foundry and OpenRouter, and is being integrated into Microsoft products such as PowerPoint and OneDrive.