CVAug 12, 2024

CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

Tsinghua
arXiv:2408.06072v31952 citationsh-index: 36Has Code
Originality Highly original
AI Analysis

This addresses the challenge of creating narrative-coherent, high-motion videos from text prompts for applications in content creation and AI-driven media.

The authors tackled the problem of generating long, coherent, and text-aligned videos by introducing CogVideoX, a diffusion transformer model that produces 10-second videos at 16 fps and 768*1360 resolution, achieving state-of-the-art performance in machine and human evaluations.

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.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes