Introducing Qwen-VL

Qwen · 2 years ago

Alibaba released upgraded versions of its Qwen-VL multimodal model, introducing Qwen-VL-Plus and Qwen-VL-Max with improved image reasoning and text recognition capabilities. The new versions support image resolutions above one million pixels and various aspect ratios, addressing generalization limitations in multimodal AI systems. These upgrades enable better performance on tasks requiring detailed image analysis and text extraction from images.