├── transformer_i2v  
│   ├── 1000  
│   │   └── mp_rank_00_model_states.pt  
│   └── latest  
└── transformer_t2v  
    ├── 1000  
    │   └── mp_rank_00_model_states.pt  
    └── latest  

└── vae  
    └── 3d-vae.pt  

├── t5-v1_1-xxl  
   ├── added_tokens.json  
   ├── config.json  
   ├── model-00001-of-00002.safetensors  
   ├── model-00002-of-00002.safetensors  
   ├── model.safetensors.index.json  
   ├── special_tokens_map.json  
   ├── spiece.model  
   └── tokenizer_config.json  


0 directories, 8 files  

@article{yang2024cogvideox,
  title={CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer},
  author={Yang, Zhuoyi and Teng, Jiayan and Zheng, Wendi and Ding, Ming and Huang, Shiyu and Xu, Jiazheng and Yang, Yuanming and Hong, Wenyi and Zhang, Xiaohan and Feng, Guanyu and others},
  journal={arXiv preprint arXiv:2408.06072},
  year={2024}
}