无需训练即可让视频扩散模型生成两倍长的连贯视频。
RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers
- 通过降低位置编码的固有频率抑制重复，保持运动一致性。
- 在不训练的情况下实现2倍长度扩展，且视频质量高。
- 微调后可支持3倍长度生成，适合追求高效长视频生成的研究者。
视频生成领域的最新进展已能合成高质量的分钟级视频。然而，生成更长且时间连贯的视频仍是重大挑战，现有长度外推方法常导致时间重复或动作减速。本文系统分析了位置编码中频率成分的作用，识别出主导外推行为的固有频率。基于此，提出RIFLEx——一种极简而有效的无训练方法，通过降低该频率抑制重复并保持运动一致性，无需额外修改。RIFLEx实现了真正的“免费午餐”：在不训练的前提下，使先进视频扩散变压器实现2倍长度外推；通过最小量微调，进一步提升质量并支持3倍长度生成，无需长视频数据。项目页面与代码：https://riflex-video.github.io/。
原文摘要 · Abstract (English)
Recent advancements in video generation have enabled models to synthesize high-quality, minute-long videos. However, generating even longer videos with temporal coherence remains a major challenge and existing length extrapolation methods lead to temporal repetition or motion deceleration. In this work, we systematically analyze the role of frequency components in positional embeddings and identify an intrinsic frequency that primarily governs extrapolation behavior. Based on this insight, we propose RIFLEx, a minimal yet effective approach that reduces the intrinsic frequency to suppress repetition while preserving motion consistency, without requiring any additional modifications. RIFLEx offers a true free lunch--achieving high-quality 2x extrapolation on state-of-the-art video diffusion transformers in a completely training-free manner. Moreover, it enhances quality and enables 3x extrapolation by minimal fine-tuning without long videos. Project page and codes: https://riflex-video.github.io/.
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。