Skip to main content
Microsoft Foundry
Microsoft AI

MAI-Image-2.7-Flash

Fast, efficient image generation optimized for low-latency creation and rapid iteration.
Microsoft
Direct from Azure
Version: 2026-11-02

Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:

  • Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.
  • Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all as part of one Microsoft Foundry platform.
  • Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Microsoft Foundry; reducing integration effort.
  • Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.

Learn more about Direct from Azure models .

About this model

MAI-Image-2.7-Flash is a diffusion-based generative model designed for fast, high-quality text-to-image synthesis and controllable image-to-image editing. It operates by progressively transforming random noise into a coherent image that aligns with a given text prompt, combining efficient diffusion inference with strong prompt adherence to deliver responsive image generation and editing.

MAI-Image-2.7-Flash is optimized for speed and efficiency across multimodal editing workflows while maintaining strong visual context understanding and coherence. It reasons across objects, scene structure, lighting, scale, and spatial positioning to produce consistent edits while enabling faster iteration across creative workflows.

The model supports object removal, replacement, attribute changes, inpainting, text updates, and image enhancement while preserving overall composition and layout. It also maintains visual consistency across iterative edits, allowing users to rapidly refine and adapt existing images.

This combination of efficient generation, controllable editing, and visual quality makes MAI-Image-2.7-Flash well suited for rapid creative exploration, design iteration, production editing workflows, and multimodal applications where responsiveness and speed are important.

Key model capabilities

The model excels at precise, surgical edits with consistency — enabling users and developers to make targeted object edits, adapt layouts, update text, clean up artifacts like motion blur, and preserve visual consistency across iterations.

The model is optimized to produce diverse and coherent images across a wide range of creative and design scenarios, making it well suited for tasks such as concept visualization, creative content generation, image editing workflows, and production design.

Quick facts

PublisherMicrosoft
AuthorMicrosoft AI
TypeText to image
LifecyclePreview
Hosted onAzure
Input typetext, image
Output typeimage
Context window32000
Token limits4096 output