用短视频训练即可生成高质量长视频，突破生成时内存与时间瓶颈。
PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference
- 分三类管理历史信息：锚点帧、压缩中间帧、近期帧，实现高效上下文控制
- 仅需5秒训练片段，即可生成2分钟16帧率视频，内存稳定在4GB
- 适合追求长视频生成效率与质量的AI视频研究者和开发者
自回归视频扩散模型虽有显著进展，但仍受限于难以处理的线性KV缓存增长、时间重复及生成误差累积问题。为此，我们提出PackForcing框架，通过创新的三段式KV缓存策略高效管理生成历史：（1）保留早期锚点帧全分辨率以维持全局语义；（2）通过双分支网络融合3D卷积与低分辨率VAE重编码，实现32倍时空压缩的中间帧；（3）保持近期帧全分辨率以确保局部时间连贯性。为严格控制内存且不损失质量，引入动态top-k上下文选择机制与连续时间RoPE调整，无缝修复丢帧造成的时序错位，开销极小。该方法可在单张H200 GPU上生成832×480分辨率、16帧率的2分钟视频，仅需4GB KV缓存，并实现24倍时间外推（5秒→120秒），零样本或仅用5秒短片训练即可有效运行。VBench评测显示其达到26.07的时序一致性与56.25的动态度，证明短视频监督足以支持高质量长视频合成。
原文摘要 · Abstract (English)
Autoregressive video diffusion models have demonstrated remarkable progress, yet they remain bottlenecked by intractable linear KV-cache growth, temporal repetition, and compounding errors during long-video generation. To address these challenges, we present PackForcing, a unified framework that efficiently manages the generation history through a novel three-partition KV-cache strategy. Specifically, we categorize the historical context into three distinct types: (1) Sink tokens, which preserve early anchor frames at full resolution to maintain global semantics; (2) Mid tokens, which achieve a massive spatiotemporal compression (32x token reduction) via a dual-branch network fusing progressive 3D convolutions with low-resolution VAE re-encoding; and (3) Recent tokens, kept at full resolution to ensure local temporal coherence. To strictly bound the memory footprint without sacrificing quality, we introduce a dynamic top-$k$ context selection mechanism for the mid tokens, coupled with a continuous Temporal RoPE Adjustment that seamlessly re-aligns position gaps caused by dropped tokens with negligible overhead. Empowered by this principled hierarchical context compression, PackForcing can generate coherent 2-minute, 832x480 videos at 16 FPS on a single H200 GPU. It achieves a bounded KV cache of just 4 GB and enables a remarkable 24x temporal extrapolation (5s to 120s), operating effectively either zero-shot or trained on merely 5-second clips. Extensive results on VBench demonstrate state-of-the-art temporal consistency (26.07) and dynamic degree (56.25), proving that short-video supervision is sufficient for high-quality, long-video synthesis. https://github.com/ShandaAI/PackForcing
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。