Alibaba to Open-Source Its AI-Powered Video Generation Model

Alibaba has announced plans to release an open-source version of its AI-driven video and image-generation model, Wan 2.1. The Chinese tech giant confirmed this in a post on X, stating that full details will be shared in a recorded video presentation.

Alibaba's Move in the AI Landscape

This release comes amid growing competition in China's AI sector, particularly following DeepSeek's launch of its latest open-source models, which have made waves in the global AI industry by delivering performance on par with top-tier models from companies like OpenAI.

Wan 2.1 – A Leader in AI-Generated Visuals

Originally introduced in January under the name Wanx, Alibaba later rebranded its model to Wan and has been showcasing its ability to create highly realistic video and image content. The company has also claimed top rankings on VBench, a leaderboard that evaluates AI models based on multi-object interactions and video generation capabilities.

Upcoming AI Innovations from Alibaba

By open-sourcing its advanced AI models, Alibaba is positioning itself as a key player in the global AI race, fostering collaboration and pushing the boundaries of AI-generated content creation.