Metraipolis › archive › dc_d7ce6545fe4e

OneReel: Efficient Multi-Scene Video Generation with Scene-Structured Attention — arXiv:2611.10594

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.10594
License (as archived): CC0-1.0
Archived: 2026-11-10T18:45:41.577Z
SHA-256 of the archived text: 286d903c2bdbf31433108deaa76c9e4f0838bce88dd92dfbf6d6288d428f5c28
Stable URL of this page: https://metraipolis.com/documento/dc_d7ce6545fe4e

How to cite

OneReel: Efficient Multi-Scene Video Generation with Scene-Structured Attention — arXiv:2611.10594 — arXiv (en), https://arxiv.org/abs/2611.10594 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d7ce6545fe4e (Metraipolis archive dc_d7ce6545fe4e, sha256 286d903c2bdbf31433108deaa76c9e4f0838bce88dd92dfbf6d6288d428f5c28)

BibTeX

@misc{dcd7ce6545fe4e,
  title = {OneReel: Efficient Multi-Scene Video Generation with Scene-Structured Attention — arXiv:2611.10594},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.10594},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d7ce6545fe4e; sha256 286d903c2bdbf31433108deaa76c9e4f0838bce88dd92dfbf6d6288d428f5c28},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10594. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-scene video generation must follow scene-specific prompts while preserving consistency across scenes. Dense joint generation enables cross-scene information exchange but incurs quadratic attention cost, whereas separate generation avoids this cost at the expense of cross-scene consistency. We present OneReel, a training-free system that exploits scene structure to enable efficient multi-scene generation. Our key insight is that multi-scene generation can preserve complete intra-scene attention while restricting cross-scene information exchange to a bounded shared memory. OneReel uses scene prompts and durations to establish scene-specific attention scopes and dynamically selects a bounded set of representative latent frames for cross-scene sharing. This reduces video attention complexity from quadratic to linear in the number of scenes. To translate these savings into execution speedups, OneReel packs scene-local and shared K/V into dense variable-length attention and employs work-balanced multi-GPU partitioning with communication-aware selection between K/V gathering and Ulysses-style parallelism. Our evaluations across four video generation models show that OneReel achieves 1.7-4.9x end-to-end speedup over dense attention and 1.2-2.2x over existing sparse-attention advances, while improving text-following accuracy by 34-37 percentage points and maintaining cross-scene consistency.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.DC, nuovi lavori del giorno).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2611.10594 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-10T18:38:07.439Z dalla pagina https://arxiv.org/list/cs.DC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).