Following Tongyi Qianqian-7B (Qwen-7B), AliCloud has launched Qwen-VL, a large-scale visual language model, and it is directly open-sourced as soon as it goes live. It supports a variety of inputs such as images and text detection frames, and also supports the output of detection frames in addition to text.
Ali big model and open source! Can read the map will recognize things, based on the Tongyi Qianqian 7B build, can be commercialized
Previous: 4G显存低配畅玩AIGC Fooocus小白也能画大片
Next: 女子创建AI男友，却发现它又粘人又烦人