阿里 Qwen 团队发布开源权重图像生成模型 Qwen-Image-2.1，仅 7B 参数

Alibaba's open-weight Qwen-Image-2.1 claims to beat closed models in image generation with just 7 billion parameters

AI 导读

阿里 Qwen 团队发布开源权重图像生成与编辑模型 Qwen-Image-2.1，视觉生成部分仅 7B 参数，团队称在其自建基准上超过多数闭源模型，独立基准尚待验证，可在 RTX 3090 等消费级 GPU 上运行。

正文 · 原文

Alibaba's Qwen AI team has released Qwen-Image-2.1, an open-weight model for image generation and editing. Its visual generation component has just 7 billion parameters yet beats most closed models on Qwen's own benchmark, the team claims, though independent benchmarks are still pending. It runs on capable consumer GPUs like a 3090.

Qwen says this group portrait was assembled from individual photos of each person. | Image: Alibaba / Qwen

The model natively generates and edits transparent images (RGBA), letting users isolate objects or change text on transparent layers. It handles up to ten reference images at once for group portraits, virtual try-ons, or room design, while circles, masks, or painted marks guide local edits. Qwen says architecture changes and KV cache reuse speed up inference, especially with multiple reference images.

Qwen-Image-2.1 is available on Hugging Face, GitHub, and Model Scope, with a Hugging Face demo. Its research license bars commercial use, so business users must apply to Qwen for a separate license.