Metraipolis › archive › dc_ef76a3bd714c
Diff-VF: Training-free High-quality Long Video Generation via Diffusion Model — arXiv:2608.05976
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.05976
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T10:36:26.113Z
- SHA-256 of the archived text
4246ef98e273a98bde378ba05a3ffc375888031420a66845482d78215967d0a9- Stable URL of this page
https://metraipolis.com/documento/dc_ef76a3bd714c
How to cite
Diff-VF: Training-free High-quality Long Video Generation via Diffusion Model — arXiv:2608.05976 — arXiv (en), https://arxiv.org/abs/2608.05976 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ef76a3bd714c (Metraipolis archive dc_ef76a3bd714c, sha256 4246ef98e273a98bde378ba05a3ffc375888031420a66845482d78215967d0a9)
BibTeX
@misc{dcef76a3bd714c,
title = {Diff-VF: Training-free High-quality Long Video Generation via Diffusion Model — arXiv:2608.05976},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.05976},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ef76a3bd714c; sha256 4246ef98e273a98bde378ba05a3ffc375888031420a66845482d78215967d0a9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05976. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recently, diffusion models have made great progress in video generation. However, most existing video diffusion models are trained with short videos, and degrade when extrapolated to long videos, struggling to maintain long-range temporal coherence while retaining diverse motions. To generate consistent, high-quality and dynamic long videos, we propose Diff-VF, a training-free, plug-and-play and model-agnostic framework that converts existing short-video diffusion backbones into long-video generators without modifying or fine-tuning the base model. Diff-VF couples three complementary strategies: Hybrid Noise Initialization (HNI) to constrain global semantics, Weighted Window Sampling (WWS) to remove inter-window discontinuities, and Temporal Extended Sampling (TES) to establish long-range dependencies with a timestep-varying fusion. We further extend Diff-VF to long-video enhancement via Skip Residual Guidance that balances fidelity and realism through timestep-dependent guidance. VBench-Long evaluation results show that Diff-VF achieves a more favorable balance between temporal coherence and motion diversity than base models and recent training-free long video generation baselines, including FreeNoise, FreeLong, and RIFLEx, while maintaining competitive frame-wise quality. Experiments on two base models demonstrate the applicability to video diffusion models with different spatial-temporal modeling strategies. Extensive ablations validate the contribution of each component and hyperparameters. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.05976 — 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 2026-10-31T10:23:31.040Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).