CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910894071480320 |
|---|---|
| author | Yang, Zhuoyi Teng, Jiayan Zheng, Wendi Ding, Ming Huang, Shiyu Xu, Jiazheng Yang, Yuanming Hong, Wenyi Zhang, Xiaohan Feng, Guanyu Yin, Da Zhang, Yuxuan Wang, Weihan Cheng, Yean Xu, Bin Gu, Xiaotao Dong, Yuxiao Tang, Jie |
| author_facet | Yang, Zhuoyi Teng, Jiayan Zheng, Wendi Ding, Ming Huang, Shiyu Xu, Jiazheng Yang, Yuanming Hong, Wenyi Zhang, Xiaohan Feng, Guanyu Yin, Da Zhang, Yuxuan Wang, Weihan Cheng, Yean Xu, Bin Gu, Xiaotao Dong, Yuxiao Tang, Jie |
| contents | We present CogVideoX, a large-scale text-to-video generation model based on diffusion transformer, which can generate 10-second continuous videos aligned with text prompt, with a frame rate of 16 fps and resolution of 768 * 1360 pixels. Previous video generation models often had limited movement and short durations, and is difficult to generate videos with coherent narratives based on text. We propose several designs to address these issues. First, we propose a 3D Variational Autoencoder (VAE) to compress videos along both spatial and temporal dimensions, to improve both compression rate and video fidelity. Second, to improve the text-video alignment, we propose an expert transformer with the expert adaptive LayerNorm to facilitate the deep fusion between the two modalities. Third, by employing a progressive training and multi-resolution frame pack technique, CogVideoX is adept at producing coherent, long-duration, different shape videos characterized by significant motions. In addition, we develop an effective text-video data processing pipeline that includes various data preprocessing strategies and a video captioning method, greatly contributing to the generation quality and semantic alignment. Results show that CogVideoX demonstrates state-of-the-art performance across both multiple machine metrics and human evaluations. The model weight of both 3D Causal VAE, Video caption model and CogVideoX are publicly available at https://github.com/THUDM/CogVideo. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_06072 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer Yang, Zhuoyi Teng, Jiayan Zheng, Wendi Ding, Ming Huang, Shiyu Xu, Jiazheng Yang, Yuanming Hong, Wenyi Zhang, Xiaohan Feng, Guanyu Yin, Da Zhang, Yuxuan Wang, Weihan Cheng, Yean Xu, Bin Gu, Xiaotao Dong, Yuxiao Tang, Jie Computer Vision and Pattern Recognition We present CogVideoX, a large-scale text-to-video generation model based on diffusion transformer, which can generate 10-second continuous videos aligned with text prompt, with a frame rate of 16 fps and resolution of 768 * 1360 pixels. Previous video generation models often had limited movement and short durations, and is difficult to generate videos with coherent narratives based on text. We propose several designs to address these issues. First, we propose a 3D Variational Autoencoder (VAE) to compress videos along both spatial and temporal dimensions, to improve both compression rate and video fidelity. Second, to improve the text-video alignment, we propose an expert transformer with the expert adaptive LayerNorm to facilitate the deep fusion between the two modalities. Third, by employing a progressive training and multi-resolution frame pack technique, CogVideoX is adept at producing coherent, long-duration, different shape videos characterized by significant motions. In addition, we develop an effective text-video data processing pipeline that includes various data preprocessing strategies and a video captioning method, greatly contributing to the generation quality and semantic alignment. Results show that CogVideoX demonstrates state-of-the-art performance across both multiple machine metrics and human evaluations. The model weight of both 3D Causal VAE, Video caption model and CogVideoX are publicly available at https://github.com/THUDM/CogVideo. |
| title | CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.06072 |