Tabla de Contenidos: :: Library Catalog

Guardado en:

Detalles Bibliográficos
Autores principales:	FSVideo Team, Chen, Qingyu, Fang, Zhiyuan, Huang, Haibin, Huang, Xinwei, Jin, Tong, Lin, Minxuan, Liu, Bo, Liu, Celong, Ma, Chongyang, Mei, Xing, Shen, Xiaohui, Shen, Yaojie, Tan, Fuwen, Wang, Angtian, Yang, Xiao, Yang, Yiding, Yuan, Jiamin, Zhang, Lingxi, Zhang, Yuxin
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	https://arxiv.org/abs/2602.02092
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Tabla de Contenidos:

We introduce FSVideo, a fast speed transformer-based image-to-video (I2V) diffusion framework. We build our framework on the following key components: 1.) a new video autoencoder with highly-compressed latent space ($64\times64\times4$ spatial-temporal downsampling ratio), achieving competitive reconstruction quality; 2.) a diffusion transformer (DIT) architecture with a new layer memory design to enhance inter-layer information flow and context reuse within DIT, and 3.) a multi-resolution generation strategy via a few-step DIT upsampler to increase video fidelity. Our final model, which contains a 14B DIT base model and a 14B DIT upsampler, achieves competitive performance against other popular open-source models, while being an order of magnitude faster. We discuss our model design as well as training strategies in this report.

Ejemplares similares