Year: 2025
Type: preprint
Abstract: Recent advances in video generation demand increasingly efficient training recipes to mitigate escalating computational costs. In this report, we present ContentV, an 8B-parameter text-to-video model that achieves state-of-the-art performance (85.14 on VBench) after training on 256 x 64GB Neural Processing Units (NPUs) for merely four weeks. ContentV generates diverse, high-quality videos across multiple resolutions and durations from text prompts, enabled by three key innovations: (1) A minimalist architecture that maximizes reuse of pre-trained image generation models for video generation; (2) A systematic multi-stage training strategy leveraging flow matching for enhanced efficiency; and (3) A cost-effective reinforcement learning with human feedback framework that improves generation quality without requiring additional human annotations. All the code and models are available at: https://contentv.github.io.
Source: arXiv (Cornell University)
Authors: Lin, Wenfeng, Chen, Renjie, Liu, Boyuan, Yan, Shiyue, Feng, Ruoyu, Wei, Jiangchuan, Zhang, Yichen, Zhou, Yimeng, Feng, Chao, Ran, Jiao, Wu, Qi, Liu, Zuotao, Guo, Mingyu
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4416139093
Cites:
Cited by:
Related to: