MAI-Image-2.5 | Microsoft AI

Create high-quality, photorealistic, and design-ready images from simple text prompts or uploaded images.

Features

MAI-Image-2.5 is built around how people create, with precise control over every edit, whether you’re creating casually or at a professional level.

Photorealism that holds up

Natural lighting and accurate skin tones, rendered the way you envisioned it.

A young woman in profile on a rooftop, blowing soap bubbles against an overcast sky.A young woman in profile on a rooftop, blowing soap bubbles against an overcast sky. She has long straight black hair, windswept slightly, and wears a dark navy double-breasted school uniform jacket with gold buttons and a white collar. She holds a hot pink bubble solution bottle in one hand and a neon lime-green wand to her lips in the other. Five iridescent bubbles of varying sizes float around her.Behind her: low-rise apartment buildings under a flat gray sky, a black metal railing, and weathered concrete underfoot. Film photography aesthetic. Cool, desaturated palette with muted tones, broken by the vivid pink and green of the bubble props. Natural overcast light, slight grain. Mood: nostalgic, youthful, quietly melancholic. Landscape orientation.

Reveal prompt

Precision at every pixel

Fine-grained control means images come out closer to your vision, reducing post-processing.

Edits are sharp and remain coherent in context.

Adapts visuals while preserving layout and composition.

Design-aware generation

Built to perform across branding, product, and commercial design work.

A brown glass candle labeled "ORVA" is lit, with a single flame and soft shadows cast on a neutral surface. The label indicates it is a scented candle, weighing 8.5 oz or 240 g.

Refined text for elevated brand work

Generate high-quality images from text prompts and iterate with ease.

Text rendering is more reliable with each edit.

Image updates can be made and composition remains intact.

Model Family

Four views of a plain, off-white ceramic mug with a handle: front, side, top, and back, displayed against a neutral background. The mug has a simple, minimalist design with a slightly rustic finish.

MAI-Image-2-Efficient

Production-ready quality that’s 22% faster and priced nearly 41% lower than MAI-Image-2.

Try in Playground

A close-up of a pale yellow and brown butterfly perched on the tip of a dry grass stem, with delicate, patterned wings and a soft, blurred background.

MAI-Image-2-Flash

Debuted as the #3 text-to-image model family on the Arena leaderboard.

Try in Playground

Performance

Arena Leaderboard

Ranked third in the text-to-image family.

Featured Partners

The letters "WPP" are formed using a pattern of evenly spaced black dots on a light gray background.

MAI-Image-2 is a genuine game-changer. It’s a platform that not only responds to the intricate nuance of creative direction, but deeply respects the sheer craft involved in generating real-world, campaign-ready images. WPP has some of the best creative talent in the world and MAI-Image-2 is making them even better.

 - Rob Reilly, Global Chief Creative Officer, WPP

The Shutterstock logo in gray, with stylized letters and circular design elements around the "o".

MAI-Image-2-Efficient shows strong progress in prompt fidelity and creative usability across a range of workflows. In our evaluation work, we look closely at how well models translate intent into consistent, production-ready outputs, and this model is trending in the right direction. That level of reliability is what ultimately matters when teams move from experimentation into real-world use.

 – Vanessa Salvo, Principal Product Manager, Shutterstock

Try MAI-Image-2.5

MAI Playground

Experiment with all of our other MAI models.

Try in Playground

Microsoft Foundry

Access model details, documentation, and pricing.

Try in Foundry