Qwen-Image: Crafting with Native Text Rendering

Alibaba releases Qwen-Image, a 20B MMDiT image foundation model with advanced text rendering and image editing capabilities.

From the source
We are thrilled to release Qwen-Image, a 20B MMDiT image foundation model that achieves significant advances in complex text rendering and precise image editing.
qwenlm.github.io

Visit source ↗qwenlm.github.io

Announced: 04 Aug 2025 14:08 UTC
Detected: 03 Aug 2026 21:12 UTC (+364d after)

Other stories

Perplexity · 27 AugDeepSeek V4 Flash 0731New model

Tencent · 27 AugIntroducing Hy4 previewNew model

xAI · 29 AugGrok Bot now works with XCapability change

GitHub · 28 AugGitHub Copilot in Visual Studio — August update

GitHub · 28 Aug

GitHub Copilot weekly releases — August 24

Capability change

Amazon · 28 AugBatch write and discover records in Amazon SageMaker Feature StoreAPI release