Saved in:
Bibliographic Details
Main Authors: Shi, Huafeng, Liang, Jianzhong, Xie, Rongchang, Wu, Xian, Chen, Cheng, Liu, Chang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.10584
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913841178214400
author Shi, Huafeng
Liang, Jianzhong
Xie, Rongchang
Wu, Xian
Chen, Cheng
Liu, Chang
author_facet Shi, Huafeng
Liang, Jianzhong
Xie, Rongchang
Wu, Xian
Chen, Cheng
Liu, Chang
contents This report introduces Aquarius, a family of industry-level video generation models for marketing scenarios designed for thousands-xPU clusters and models with hundreds of billions of parameters. Leveraging efficient engineering architecture and algorithmic innovation, Aquarius demonstrates exceptional performance in high-fidelity, multi-aspect-ratio, and long-duration video synthesis. By disclosing the framework's design details, we aim to demystify industrial-scale video generation systems and catalyze advancements in the generative video community. The Aquarius framework consists of five components: Distributed Graph and Video Data Processing Pipeline: Manages tens of thousands of CPUs and thousands of xPUs via automated task distribution, enabling efficient video data processing. Additionally, we are about to open-source the entire data processing framework named "Aquarius-Datapipe". Model Architectures for Different Scales: Include a Single-DiT architecture for 2B models and a Multimodal-DiT architecture for 13.4B models, supporting multi-aspect ratios, multi-resolution, and multi-duration video generation. High-Performance infrastructure designed for video generation model training: Incorporating hybrid parallelism and fine-grained memory optimization strategies, this infrastructure achieves 36% MFU at large scale. Multi-xPU Parallel Inference Acceleration: Utilizes diffusion cache and attention optimization to achieve a 2.35x inference speedup. Multiple marketing-scenarios applications: Including image-to-video, text-to-video (avatar), video inpainting and video personalization, among others. More downstream applications and multi-dimensional evaluation metrics will be added in the upcoming version updates.
format Preprint
id arxiv_https___arxiv_org_abs_2505_10584
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Aquarius: A Family of Industry-Level Video Generation Models for Marketing Scenarios
Shi, Huafeng
Liang, Jianzhong
Xie, Rongchang
Wu, Xian
Chen, Cheng
Liu, Chang
Computer Vision and Pattern Recognition
This report introduces Aquarius, a family of industry-level video generation models for marketing scenarios designed for thousands-xPU clusters and models with hundreds of billions of parameters. Leveraging efficient engineering architecture and algorithmic innovation, Aquarius demonstrates exceptional performance in high-fidelity, multi-aspect-ratio, and long-duration video synthesis. By disclosing the framework's design details, we aim to demystify industrial-scale video generation systems and catalyze advancements in the generative video community. The Aquarius framework consists of five components: Distributed Graph and Video Data Processing Pipeline: Manages tens of thousands of CPUs and thousands of xPUs via automated task distribution, enabling efficient video data processing. Additionally, we are about to open-source the entire data processing framework named "Aquarius-Datapipe". Model Architectures for Different Scales: Include a Single-DiT architecture for 2B models and a Multimodal-DiT architecture for 13.4B models, supporting multi-aspect ratios, multi-resolution, and multi-duration video generation. High-Performance infrastructure designed for video generation model training: Incorporating hybrid parallelism and fine-grained memory optimization strategies, this infrastructure achieves 36% MFU at large scale. Multi-xPU Parallel Inference Acceleration: Utilizes diffusion cache and attention optimization to achieve a 2.35x inference speedup. Multiple marketing-scenarios applications: Including image-to-video, text-to-video (avatar), video inpainting and video personalization, among others. More downstream applications and multi-dimensional evaluation metrics will be added in the upcoming version updates.
title Aquarius: A Family of Industry-Level Video Generation Models for Marketing Scenarios
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.10584