Alibaba Group has made its video and image generation AI model Wan 2.1 publicly available as open source. Reuters reports that four variants of the model are now accessible globally through Alibaba Cloud’s ModelScope and HuggingFace platforms for academic, research, and commercial use. The most powerful variants can process up to 14 billion parameters, enabling more accurate results. This move follows similar action from startup DeepSeek, whose open-source models have shown performance comparable to established competitors like OpenAI. Alibaba introduced the latest version in January, highlighting its ability to generate highly realistic visuals and its top ranking on VBench for video generative models. The company also announced plans to invest at least 380 billion yuan ($52 billion) over the next three years to strengthen its cloud computing and AI infrastructure.