Alibaba’s New AI Image Model Qwen VLo Steps Up Competition Amid Open-Source Push
阿里巴巴推出新 AI 图像模型 Qwen VLo，在开源战略推动下加剧行业竞争
阿里巴巴集团发布了新 AI 模型 Qwen VLo，该模型旨在以类人般的精细度生成和编辑图像，从而加剧了中国多模态 AI 领域的竞争。Qwen Chat 已提供预览版本。阿里巴巴通过开源策略扩大用户基础，力求在 AI 创新竞赛中确立领先地位。
Alibaba Group has launched Qwen VLo, a new AI model designed to generate and edit images with human-like finesse, intensifying competition in China’s multimodal AI landscape. Unveiled on Friday, the model represents a “comprehensive upgrade” from its predecessors like QwenVL and Qwen2.5 VL, boasting enhanced capabilities in understanding inputs, creating precise images, supporting open-ended instructions, and handling multiple languages including Chinese and English. A preview is available on Qwen Chat.
Qwen VLo also stands out with its support for diverse input and output formats, offering users greater flexibility. It is tailored for creating posters, illustrations, web banners, and social media covers. The move comes as Alibaba pursues an open-source strategy to expand its user base, positioning itself as a key player in the race to lead AI innovation.
