返回全部动态
Qwen-Image-Edit：高质量高效率的图像编辑模型
原标题：Qwen-Image-Edit: Image Editing with Higher Quality and Efficiency
AI 摘要
阿里巴巴推出Qwen-Image-Edit，基于20B参数的Qwen-Image模型，结合Qwen2.5-VL和VAE编码器，实现语义和外观编辑，支持中英文精确文本编辑。在多个公开基准上达到SOTA性能，已在Qwen Chat上线。该模型可应用于IP创作、物体旋转、风格迁移、背景调整等场景，并通过链式编辑逐步修正图像细节。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
We are excited to introduce Qwen-Image-Edit, the image editing version of Qwen-Image. Built upon our 20B Qwen-Image model, Qwen-Image-Edit successfully extends Qwen-Image’s unique text rendering capabilities to image editing tasks, enabling precise text editing. Furthermore, Qwen-Image-Edit simultaneously feeds the input image into Qwen2.5-VL (for visual semantic control) and the VAE Encoder (for visual appearance control), achieving capabilities in both semantic and appearance editing. To exper
发布时间：2025-08-19 01:30
抓取时间：2026-08-31 00:56
来源机构：Alibaba Qwen