Alibaba Cloud has announced the open-sourcing of its video generation model series Wan2.1, consisting of four models, marking a significant contribution to the global open-source community. This move aims to drive innovation and accessibility in artificial intelligence (AI) technology by making these resources available to academic institutions, researchers, and commercial entities worldwide.
The open-source release includes models with two parameter specifications, 14B and 1.3B: T2V-14B, T2V-1.3B, I2V-14B-720P, and I2V-14B-480P. These models support both text-to-video and image-to-video tasks. Developers globally can access the complete inference code and weights of these models on platforms like GitHub, Hugging Face, and Magic Club community.
