meituan-longcat/LongCat-Video

We introduce LongCat-Video, a foundational video generation model with 13.6B parameters, delivering strong performance across Text-to-Video, Image-to-Video, and Video-Continuation generation tasks. It particularly excels in efficient and high-quality long video generation, representing our first step toward world models. For more detail, please refer to the comprehensive LongCat-Video Technical Report. Clone the repo: Install dependencies: FlashAttention-2 is enabled in the model config by default; you can also change the model config ("./weights/LongCat-Video/dit/config.json") to use FlashAttention-3 or xformers once installed. Download models using huggingface-cli: 💡 User tips for 1.5 💡 User tips for 1.0 The Text-to-Video MOS evaluation results on our internal benchmark. The Image-to-Video MOS evaluation results on our internal benchmark. Community works are welcome! Please PR or inform us in Issue to add your work. The model weights are released under the MIT License. Any contributions to this repository are licensed under the MIT License, unless otherwise stated. This license…