JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion
This work addresses the need for real-time video editing with bounded resources, providing a practical solution for interactive applications that require low-latency, high-fidelity editing.
JoyAI-Video-Edit introduces a 16B-parameter autoregressive diffusion framework for real-time, open-ended video editing without future frames or predefined duration, achieving 720p editing at ~30 FPS on a single Nvidia B200 GPU while outperforming streaming editors and matching offline systems.
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.