EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910041222676480 |
|---|---|
| author | Xu, Jiaqi Huang, Kunzhe Zou, Xinyi Chen, Yunkuo Liu, Bo Cheng, MengLi Huang, Jun Shi, Xing |
| author_facet | Xu, Jiaqi Huang, Kunzhe Zou, Xinyi Chen, Yunkuo Liu, Bo Cheng, MengLi Huang, Jun Shi, Xing |
| contents | This paper introduces EasyAnimate, an efficient and high quality video generation framework that leverages diffusion transformers to achieve high-quality video production, encompassing data processing, model training, and end-to-end inference. Despite substantial advancements achieved by video diffusion models, existing video generation models still struggles with slow generation speeds and less-than-ideal video quality. To improve training and inference efficiency without compromising performance, we propose Hybrid Window Attention. We design the multidirectional sliding window attention in Hybrid Window Attention, which provides stronger receptive capabilities in 3D dimensions compared to naive one, while reducing the model's computational complexity as the video sequence length increases. To enhance video generation quality, we optimize EasyAnimate using reward backpropagation to better align with human preferences. As a post-training method, it greatly enhances the model's performance while ensuring efficiency. In addition to the aforementioned improvements, EasyAnimate integrates a series of further refinements that significantly improve both computational efficiency and model performance. We introduce a new training strategy called Training with Token Length to resolve uneven GPU utilization in training videos of varying resolutions and lengths, thereby enhancing efficiency. Additionally, we use a multimodal large language model as the text encoder to improve text comprehension of the model. Experiments demonstrate significant enhancements resulting from the above improvements. The EasyAnimate achieves state-of-the-art performance on both the VBench leaderboard and human evaluation. Code and pre-trained models are available at https://github.com/aigc-apps/EasyAnimate. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_18991 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagation Xu, Jiaqi Huang, Kunzhe Zou, Xinyi Chen, Yunkuo Liu, Bo Cheng, MengLi Huang, Jun Shi, Xing Computer Vision and Pattern Recognition Computation and Language Multimedia This paper introduces EasyAnimate, an efficient and high quality video generation framework that leverages diffusion transformers to achieve high-quality video production, encompassing data processing, model training, and end-to-end inference. Despite substantial advancements achieved by video diffusion models, existing video generation models still struggles with slow generation speeds and less-than-ideal video quality. To improve training and inference efficiency without compromising performance, we propose Hybrid Window Attention. We design the multidirectional sliding window attention in Hybrid Window Attention, which provides stronger receptive capabilities in 3D dimensions compared to naive one, while reducing the model's computational complexity as the video sequence length increases. To enhance video generation quality, we optimize EasyAnimate using reward backpropagation to better align with human preferences. As a post-training method, it greatly enhances the model's performance while ensuring efficiency. In addition to the aforementioned improvements, EasyAnimate integrates a series of further refinements that significantly improve both computational efficiency and model performance. We introduce a new training strategy called Training with Token Length to resolve uneven GPU utilization in training videos of varying resolutions and lengths, thereby enhancing efficiency. Additionally, we use a multimodal large language model as the text encoder to improve text comprehension of the model. Experiments demonstrate significant enhancements resulting from the above improvements. The EasyAnimate achieves state-of-the-art performance on both the VBench leaderboard and human evaluation. Code and pre-trained models are available at https://github.com/aigc-apps/EasyAnimate. |
| title | EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagation |
| topic | Computer Vision and Pattern Recognition Computation and Language Multimedia |
| url | https://arxiv.org/abs/2405.18991 |