MAI-Image-2.5
Maker: Microsoft · images
A Microsoft AI diffusion model: image generation from text and editing of an uploaded JPEG or PNG. Prompt length up to 32k tokens, one PNG on output, model version 2026-06-02. Aimed at surgical edits: replace an object, update text, remove motion blur, while preserving the rest.
в Microsoft Foundry доступна как публичное превью
Understands
text, images
Produces
images
Contents verified with the vendor: 2026-08-18
Included in subscriptions
No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.