EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagation

TL;DR

EasyAnimate is a high-performance video generation framework that combines hybrid window attention and reward backpropagation to improve quality and efficiency, achieving state-of-the-art results.

Contribution

The paper introduces Hybrid Window Attention and reward backpropagation, along with training strategies and multimodal text encoding, to enhance video generation speed and quality.

Findings

Achieves state-of-the-art performance on VBench and human evaluations.

Significantly improves computational efficiency and video quality.

Introduces novel attention and training methods for video diffusion models.

Abstract

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.