Saved in:
Bibliographic Details
Main Authors: Zhang, Zeyu, Chang, Shuning, He, Yuanyu, Han, Yizeng, Tang, Jiasheng, Wang, Fan, Zhuang, Bohan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.22973
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917111384768512
author Zhang, Zeyu
Chang, Shuning
He, Yuanyu
Han, Yizeng
Tang, Jiasheng
Wang, Fan
Zhuang, Bohan
author_facet Zhang, Zeyu
Chang, Shuning
He, Yuanyu
Han, Yizeng
Tang, Jiasheng
Wang, Fan
Zhuang, Bohan
contents Generating minute-long videos is a critical step toward developing world models, providing a foundation for realistic extended scenes and advanced AI simulators. The emerging semi-autoregressive (block diffusion) paradigm integrates the strengths of diffusion and autoregressive models, enabling arbitrary-length video generation and improving inference efficiency through KV caching and parallel sampling. However, it yet faces two enduring challenges: (i) KV-cache-induced long-horizon error accumulation, and (ii) the lack of fine-grained long-video benchmarks and coherence-aware metrics. To overcome these limitations, we propose BlockVid, a novel block diffusion framework equipped with semantic-aware sparse KV cache, an effective training strategy called Block Forcing, and dedicated chunk-wise noise scheduling and shuffling to reduce error propagation and enhance temporal consistency. We further introduce LV-Bench, a fine-grained benchmark for minute-long videos, complete with new metrics evaluating long-range coherence. Extensive experiments on VBench and LV-Bench demonstrate that BlockVid consistently outperforms existing methods in generating high-quality, coherent minute-long videos. In particular, it achieves a 22.2% improvement on VDE Subject and a 19.4% improvement on VDE Clarity in LV-Bench over the state of the art approaches. Project website: https://ziplab.co/BlockVid. Inferix (Code): https://github.com/alibaba-damo-academy/Inferix.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22973
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BlockVid: Block Diffusion for High-Quality and Consistent Minute-Long Video Generation
Zhang, Zeyu
Chang, Shuning
He, Yuanyu
Han, Yizeng
Tang, Jiasheng
Wang, Fan
Zhuang, Bohan
Computer Vision and Pattern Recognition
Generating minute-long videos is a critical step toward developing world models, providing a foundation for realistic extended scenes and advanced AI simulators. The emerging semi-autoregressive (block diffusion) paradigm integrates the strengths of diffusion and autoregressive models, enabling arbitrary-length video generation and improving inference efficiency through KV caching and parallel sampling. However, it yet faces two enduring challenges: (i) KV-cache-induced long-horizon error accumulation, and (ii) the lack of fine-grained long-video benchmarks and coherence-aware metrics. To overcome these limitations, we propose BlockVid, a novel block diffusion framework equipped with semantic-aware sparse KV cache, an effective training strategy called Block Forcing, and dedicated chunk-wise noise scheduling and shuffling to reduce error propagation and enhance temporal consistency. We further introduce LV-Bench, a fine-grained benchmark for minute-long videos, complete with new metrics evaluating long-range coherence. Extensive experiments on VBench and LV-Bench demonstrate that BlockVid consistently outperforms existing methods in generating high-quality, coherent minute-long videos. In particular, it achieves a 22.2% improvement on VDE Subject and a 19.4% improvement on VDE Clarity in LV-Bench over the state of the art approaches. Project website: https://ziplab.co/BlockVid. Inferix (Code): https://github.com/alibaba-damo-academy/Inferix.
title BlockVid: Block Diffusion for High-Quality and Consistent Minute-Long Video Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.22973