16B参数模型实现30帧实时视频编辑，支持任意长度自由修改。
JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion
- 分块自回归生成+源帧锚定蒸馏，解决实时编辑中的一致性问题
- 单卡B200实现720p视频30帧每秒流畅编辑，长视频无累积误差
- 适合需要快速迭代的视频创作、直播剪辑等实时场景
实时视频编辑需在有限算力下实现低延迟因果生成，同时保持源内容保真与长期时间一致性。我们提出JoyAI-Video-Edit，一个160亿参数的自回归扩散框架，可在不访问未来帧或预设视频时长的情况下实现实时、开放式的视频编辑。该方法结合分块自回归适配、源帧锚定分布匹配蒸馏（SA-DMD）和长时序自回归蒸馏，有效降低训练-推理差异，保障两阶段生成中的源内容保真，并缓解时间漂移积累。大量自动与人工评估表明，该系统显著优于现有流式编辑器，在短片与长视频上均保持与强离线系统相当的性能。完整系统在单张Nvidia B200 GPU上实现端到端720p视频编辑约30帧每秒。代码已开源：https://github.com/jd-opensource/JoyAI-Video-Edit。
原文摘要 · Abstract (English)
Real-time video editing requires low-latency causal generation with bounded computational resources while preserving source fidelity and long-term temporal consistency. We present JoyAI-Video-Edit, a 16B-parameter autoregressive diffusion framework for real-time, open-ended video editing without access to future frames or a predefined video duration. Our method combines chunk-wise autoregressive adaptation, Source-Anchored Distribution Matching Distillation (SA-DMD), and Long-Horizon Autoregressive Distillation to reduce train--inference mismatch, preserve source fidelity during two-step generation, and mitigate accumulated temporal drift. Extensive automatic and human evaluations show that JoyAI-Video-Edit substantially outperforms existing streaming editors and remains competitive with strong offline systems on both short and long videos. The complete system achieves end-to-end 720p video editing at approximately 30 FPS on a single Nvidia B200 GPU. Code is available at https://github.com/jd-opensource/JoyAI-Video-Edit.
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。