Qwen-ImageはMMDiT （Multimodal Diffusion Transformer） という技術を採用。これはイメージとテキストを扱う2つのTransformerが協調しつつ並列動作するもので、Stability AIのStable Diffusion 3に搭載された技術。Qwen-Imageはこれにより、以下のような特徴をもつ。 高精度な画像 ...

In a major step toward AI self-reliance, Microsoft has unveiled MAI-Image-1, its first in-house text-to-image generation model. The move signals a new phase in Microsoft’s artificial intelligence ...

Microsoft has unveiled its first natively built artificial intelligence image generation model, MAI-Image-1 on Monday in a blog post. The model made its public debut on the LMArena forum, entering the ...

Editor's take: This new image generator marks a significant shift in Microsoft's AI development strategy. As the company accelerates its in-house investments, it is simultaneously redefining its ...