类似项目

类似项目 类似项目 Modified February 20, 2024 开源视频扩散Transformer 与 Sora 相似，我们的 Latte 模型也具有 视频扩散Transformer 架构，并对 LDM + DiT 的设计空间进行了深入研究，以用于视频生成 项目： https://maxin cn.github.io/latte project/ 产品编号： https://github.com/Vchitect/Latte Latte: Latent Diffusion Transformer for Video Generation Xin Ma(1,2‡), Yaohui Wang(2†), Gengyun Jia(3), Xinyuan Chen(2), Ziwei Liu(4) Yuan Fang Li(1), Cunjian Chen(1), Yu Qiao(2), (1)Department of Data Science & AI, Faculty of Information Technology, Monash University (2)Shanghai Artificial Intelligence Laboratory (3)Nanjing University of Posts and Telecommunications (4)S Lab, Nanyang Technological University (‡)Work done during internship at Shanghai AI Laboratory (†)Corresponding author Paper arXiv Code Abstract We propose a novel Latent Diffusion Transformer, namely Latte, for video generation. Latte first extracts spatio temporal tokens from input videos and then adopts a series of Transformer blocks to model video distribution in the latent space. In order to model a substantial number of tokens extracted from videos, four efficient variants are introduced from the perspective of decomposing the spatial and temporal dimensions of input videos. To improve the quality of generated videos, we determine the best practices of Latte through rigorous experimental analysis, including video clip patch embedding, model variants, timestep class information injection, temporal positional embedding, and learning strategies. Our comprehensive evaluation demonstrates that Latte achieves state of the art performance across four standard video generation datasets, i.e., FaceForensics, SkyTimelapse, UCF101, and Taichi HD. In addition, we extend Latte to text to video generation (T2V) task, where Latte achieves comparable results compared to recent T2V models. We strongly believe that Latte provides valuable insights for future research on incorporating Transformers into diffusion models for video generation. Sora https://maxin cn.github.io/latte project/ https://github.com/Vchitect/Latte Yaohui Wang Gengyun Jia Xinyuan Chen Ziwei Liu Yuan Fang Li Cunjian Chen Yu Qiao Paper arXiv Code 开源视频扩散Transformer 与 Sora 相似，我们的 Sora Latte 模型也具有 视频扩散Transformer 架构，并对 LDM + DiT 的设计空间进行了深入研究，以用于视频生成 项目： https://maxin cn.github.io/latte project/ 产品编号： https://github.com/Vchitect/Latte https://maxin cn.github.io/latte project/ https://github.com/Vchitect/Latte Latte: Latent Diffusion Transformer for Video Generation Xin Ma(1,2‡), Yaohui Wang(2†), Gengyun Jia(3), Xinyuan Chen(2), Ziwei Liu(4) Yuan Fang Li(1), Cunjian Chen(1), Yu Qiao(2), Xin Ma Yaohui Wang Gengyun Jia Xinyuan Chen Ziwei Liu Yuan Fang Li Cunjian Chen Yu Qiao (1)Department of Data Science & AI, Faculty of Information Technology, Monash University (2)Shanghai Artificial Intelligence Laboratory (3)Nanjing University of Posts and Telecommunications (4)S Lab, Nanyang Technological University (‡)Work done during internship at Shanghai AI Laboratory (†)Corresponding author Paper arXiv Code Paper arXiv Code Abstract We propose a novel Latent Diffusion Transformer, namely Latte, for video generation. Latte first extracts spatio temporal tokens from input videos and then adopts a series of Transformer blocks to model video distribution in the latent space. In order to model a substantial number of tokens extracted from videos, four efficient variants are introduced from the perspective of decomposing the spatial and temporal dimensions of input videos. To improve the quality of generated videos, we determine the best practices of Latte through rigorous experimental analysis, including video clip patch embedding, model variants, timestep class information injection, temporal positional embedding, and learning strategies. Our comprehensive evaluation demonstrates that Latte achieves state of the art performance across four standard video generation datasets, i.e., FaceForensics, SkyTimelapse, UCF101, and Taichi HD. In addition, we extend Latte to text to video generation (T2V) task, where Latte achieves comparable results compared to recent T2V models. We strongly believe that Latte provides valuable insights for future research on incorporating Transformers into diffusion models for video generation.