<h2 id="introduction">Introduction</h2>We are excited to open-source Qwen-Image-2.1, a unified text-to-image generation and image editing model in the Qwen family. With just 7B parameters in its visual generation component (32 Single-Stream DiT layers), Qwen-Image-2.1 balances generation quality, inference efficiency, and versatility.Four key improvements define this release:<ul><li>Compact and Efficient — A lightweight architecture with mixed-granularity attention and prefix KV cache reuse delivers strong image quality at low computational cost.</li><li>Native Transparency, Unified Creation and Editing — Generate regular or transparent (RGBA) images from text, edit transparent layers, and extract subjects from photographs—all in one model.</li><li>Versatile Editing — Support up to 10 reference images, specify local edits via circles, painted annotations, or separate masks, and preserve identity for people and products.</li><li>Realistic Textures and Refined Aesthetics — Improved typography, portrait lighting, and fine details for more visually compelling results.</li></ul><img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/image2.1/images/example-01.png" width="100%" /><h2 id="showcase">Showcase</h2><img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/image2.1/images/example-04.png" width="30%" /><img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/image2.1/images/example-05.png" width="30%" /><img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/image2.1/images/example-06.png" width="30%" />Native transparent image generation<img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/image2.1/images/example-15.png" width="100%" />Group photograph generated from six portrait references<img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/image2.1/images/example-43.png" width="48%" /><img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/image2.1/images/example-44.png" width="48%" />Text rendering

Qwen_Image_2.1

qwenImage21_bf16.safetensors

bf16

Repost From Huggingface <a target="_blank" rel="ugc" href="https://huggingface.co/Qwen/Qwen-Image-2.1">https://huggingface.co/Qwen/Qwen-Image-2.1</a><h2 id="introduction">Introduction</h2>We are excited to open-source Qwen-Image-2.1, a unified text-to-image generation and image editing model in the Qwen family. With just 7B parameters in its visual generation component (32 Single-Stream DiT layers), Qwen-Image-2.1 balances generation quality, inference efficiency, and versatility.Four key improvements define this release:<ul><li>Compact and Efficient — A lightweight architecture with mixed-granularity attention and prefix KV cache reuse delivers strong image quality at low computational cost.</li><li>Native Transparency, Unified Creation and Editing — Generate regular or transparent (RGBA) images from text, edit transparent layers, and extract subjects from photographs—all in one model.</li><li>Versatile Editing — Support up to 10 reference images, specify local edits via circles, painted annotations, or separate masks, and preserve identity for people and products.</li><li>Realistic Textures and Refined Aesthetics — Improved typography, portrait lighting, and fine details for more visually compelling results.</li></ul>

Files with SHA256: 89f4158d066cc33906a199fca85634f766892dd78f49b6698dabf187ac86c4bc