Image generation

MAI-Image-2.5

by Microsoft

Microsoft's strongest image model yet.
Sharper in‑image text, stylized illustration, and commercial‑grade product and packaging shots.

MAI-Image-2.5

by Microsoft

Key features

Coffee bag label 'Bean Street Roast', kraft paper, soft daylightTry now

Technical specifications

#3

Arena text-to-image leaderboard at launch (May 26, 2026)

Diffusion + flow matching

Diffusion-based text-to-image with flow-matching training, per the MAI-Image-2 model card

May 26, 2026

Preview launch on Arena, rolling to MAI Playground and Microsoft Foundry

MAI-Image-2

Released March 19, 2026; 2.5 ranks ahead of it on the public Arena leaderboard

Use cases

Posters with title text

Campaign and event posters where the headline reads cleanly. Type, hierarchy, and spacing hold together instead of degrading into shapes.

Packaging and label concepts

Bottle, bag, tub, and box mockups for client review. Product name, ingredient copy, and decorative marks stay legible and on-brand.

Brand and commercial photography

Product hero shots with controlled lighting, material truth, and clean negative space. Useful for landing pages, ads, and decks.

Editorial and stylized illustration

Magazine spreads, decorative scenes, and packaging art that need a held style rather than a generic photoreal default.

Concept art and moodboards

Fast directional visuals for design briefs. Lighting, scale, and spatial structure stay coherent across a moodboard set.

Storefront and signage mockups

Retail, café, and event signage with legible wordmarks and accurate scene context for early-stage design exploration.

Prompt examples

Packaging label

Coffee bag label 'Bean Street Roast', kraft paper, soft daylight

Edit prompt

Event poster

Concert poster reading 'Echo Festival 2026', bold serif, deep blue

Edit prompt

Product hero

Glass perfume bottle on marble, soft rim light, premium ad feel

Edit prompt

Editorial illustration

Magazine spread of a botanical garden, hand-drawn ink and gouache

Edit prompt

Storefront sign

Bakery storefront with painted sign 'Aurora Bakehouse', morning light

Edit prompt

Ice cream tub

Ice cream tub labeled 'D'Arcy's', pastel palette, studio product shot

Edit prompt

Overview

MAI-Image-2.5 is Microsoft's text-to-image model from the MAI Superintelligence Team, launched on May 26, 2026. It debuted at No. 3 on the Arena text-to-image leaderboard, behind models from Google and OpenAI, and Microsoft positions it as a step change over MAI-Image-2 with the largest gains in text rendering, stylized illustration, and commercial imagery.

What MAI-Image-2.5 does differently

The headline upgrades are in the places designers feel most. Words on posters, labels, and packaging stay sharp and correctly spelled, layouts hold their structure as copy grows, and commercial product shots land with believable material, lighting, and scale. Stylized illustration carries the same intent end-to-end rather than drifting halfway through the frame.

MAI-Image-2.5 on Morphic

On Morphic, MAI-Image-2.5 sits in the image model picker alongside ChatGPT Images 2.0, Nano Banana, Flux, and the rest of the image catalog. Open Copilot, describe the image, and pick MAI-Image-2.5 when in-image text, packaging polish, or commercial brand work is central to the brief.

Simple pricing

Get started for free today, with the option to upgrade or cancel anytime.

Basic

$9/ month
billed as $0 per year

1100 monthly credits

1 user only

All models

Workflows

Standard

$24/ month
billed as $0 per year

3625 monthly credits

1 user only

All models

Workflows

Pro

$45/ month
billed as $0 per year

6350 shared monthly credits

1 user

+ up to 4 more at extra cost

All models

Workflows

Pro Max

$170/ month
billed as $0 per year

24650 shared monthly credits

1 user

+ up to 9 more at extra cost

All models

Workflows

Enterprise

For higher limits

Custom

pricing and billing terms

High-volume credits
Custom seat limits
All models
Workflows
Pricing Gradient

Free

For playing around

$0

forever free

Up to 20 credits
1 user only
Limited models
Workflows
Compare plan details

FAQs

What is MAI-Image-2.5?
MAI-Image-2.5 is Microsoft's text-to-image model from the MAI Superintelligence Team, launched on May 26, 2026. It debuted at No. 3 on the Arena text-to-image leaderboard and is positioned as a step change over MAI-Image-2 with major improvements in text rendering, stylized illustration, and commercial imagery.
Who built MAI-Image-2.5?
MAI-Image-2.5 was built by the MAI Superintelligence Team inside Microsoft. It continues the in-house MAI-Image series that started with MAI-Image-1 and MAI-Image-2, Microsoft's first-party text-to-image models.
What can MAI-Image-2.5 do?
MAI-Image-2.5 generates images from text prompts across a wide range of styles. It is particularly strong on in-image text rendering for posters, labels, and packaging, on stylized illustration, and on commercial product photography with believable lighting, scale, and spatial structure.
How is MAI-Image-2.5 different from MAI-Image-2?
Microsoft describes 2.5 as a step change in quality over MAI-Image-2, with the largest gains in text rendering, stylized illustration, and commercial imagery. On the public Arena leaderboard, 2.5 sits well ahead of MAI-Image-2 at launch.
Where is MAI-Image-2.5 ranked?
MAI-Image-2.5 launched at No. 3 on the Arena text-to-image leaderboard on May 26, 2026, behind models from Google and OpenAI and ahead of its predecessor MAI-Image-2.
Where can I use MAI-Image-2.5?
At launch, MAI-Image-2.5 is available in preview on Arena, and Microsoft has said it will roll out to the MAI Playground and Microsoft Foundry within two weeks of the May 26, 2026 announcement.
How does MAI-Image-2.5 handle in-image text?
Sharper text rendering is one of the headline upgrades. Words on posters, labels, and packaging keep their spelling and shape, and layouts stay structurally intact as copy gets longer or more decorative.
Is MAI-Image-2.5 good for commercial and brand work?
Yes. Microsoft highlights commercial imagery, product shots, and packaging as the areas where 2.5 improved most, with stronger material truth, lighting, and brand polish suited to landing pages, ads, and client decks.
What architecture does MAI-Image-2.5 use?
The MAI-Image-2 model card describes the family as a diffusion-based text-to-image architecture trained with a flow-matching loss. MAI-Image-2.5 continues that lineage as the latest release in the MAI-Image series.
How does MAI-Image-2.5 compare to ChatGPT Images 2.0 or Nano Banana?
ChatGPT Images 2.0 leads on reasoning-driven generation, multi-image batches with character continuity, and output up to 2K. Nano Banana focuses on fast iteration with strong real-world grounding. MAI-Image-2.5 sits between them, with its largest reported strengths in in-image text rendering, stylized illustration, and commercial product and packaging imagery. Pick MAI-Image-2.5 when text legibility and brand polish are the most important parts of the brief.
How do I use MAI-Image-2.5 on Morphic?
Open Morphic Copilot, describe the image, and pick MAI-Image-2.5 from the image model picker. It sits alongside ChatGPT Images 2.0, Nano Banana, Flux, and the rest of the catalog, so you can switch in one click when text rendering or commercial polish is central to the brief.

Other models

Explore the rest of the Morphic model catalog.

See all models →

ChatGPT Images 2.5

OpenAI

OpenAI's image model, released September 2026. Sharper detail, precise edits, faster.

Lyria 3.5

Google DeepMind

Google's best-sounding music model. Full songs with structure, vocals, and lyrics.

MiniMax H3 Max Turbo

fal.ai

The fast tier of fal's post-trained H3. Twice the speed, nearly the same look.

Inworld TTS 2

Inworld

Ninety-five voices, 100+ languages. Speech that starts in under a second.