Skip to main content

Introducing MAI-Image-1, debuting in the top 10 on LMArena Introducing MAI-Image-1, debuting in the top 10 on LMArena

October 13, 2025
models
A collage featuring nature photos (a frog in water, a rabbit, mountains, fields, sunset, a tree) and food photos (pizza, sushi, a grapefruit slice), arranged in a grid on a light beige background.

Update – November 4, 2025:

We have begun launching MAI-Image-1 into select Microsoft products!

Try it in Bing Image Creator: Available at bing.com/create, in the Bing mobile app, or right from the Bing search bar, Bing Image Creator is built to meet people where they already search and create. MAI-Image-1 is now an option alongside DALL-E 3 and GPT4o in the model menu, enabling you to experiment and pick the model that best matches your creative goals.

Try it in Copilot Audio Expressions: Now, when you select Story Mode, Audio Expressions will use MAI-Image-1 to visualize your story with a unique image.

MAI-Image-1 is currently available in all countries that can access Bing Image Creator and Copilot Labs, excluding the EU at present.

Earlier Announcement – October 13, 2025:

Today, we’re announcing MAI-Image-1, our first image generation model developed entirely in-house, debuting in the top 10 text-to-image models on LMArena.  

At Microsoft AI, we’re creating AI for everyone – a supportive, helpful presence always in the service of humanity. We’ve shared how purpose-built models are essential for this mission, and we announced our first two in-house models in August. MAI-Image-1 marks the next step on our journey and paves the way for more immersive, creative and dynamic experiences inside our products.  

We trained this model with the goal of delivering genuine value for creators, and we put a lot of care into avoiding repetitive or generically-stylized outputs. For example, we prioritized rigorous data selection and nuanced evaluation focused on tasks that closely mirror real-world creative use cases – taking into account feedback from professionals in the creative industries. This model is designed to deliver real flexibility, visual diversity and practical value.

MAI-Image-1 excels at generating photorealistic imagery, like lighting (e.g., bounce light, reflections), landscapes, and much more. This is particularly so when compared to many larger, slower models. Its combination of speed and quality means users can get their ideas on screen faster, iterate through them quickly, and then transfer their work to other tools to continue refining.

A roadrunner with brown and white streaked feathers runs across a sandy desert with sparse shrubs. A flat-topped mesa is visible in the background under a clear blue sky.
“MAI-Image-1” is written in the sand on a beach at sunset, with calm waves and a colorful sky in the background. The sun is low on the horizon, casting a warm glow over the scene.
[1] A roadrunner sprinting across sand [2] MAI-Image-1 written in the sand at sunset over the beach [3] A man crossing a city street
A young man in a coat and jeans walks across a city street at sunset, with buildings, a café, and a blurred cyclist in the background. Warm sunlight creates long shadows on the road.

Build the Future With Us Build the Future With Us

We’re a lean, fast-moving lab made up of some of the world’s most talented minds. We have an exciting roadmap of compute at MAI, with our next-generation GB200 cluster now operational. And we have an ambitious mission we truly believe in. We’re also fortunate to partner with incredible product teams giving our models the chance to reach billions of users and create immense positive impact. If you’re a brilliant, highly-ambitious and low ego individual, you’ll fit right in—come and join us as we work on our next generation of models!

Explore all jobs

Related Stories Related Stories