AIAny
Icon for item

JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion

Performs real-time, instruction-guided video-to-video editing on streaming input using a 16B autoregressive diffusion model that preserves subject identity and long-term temporal coherence; achieves end-to-end 720p at ≈30 FPS on a single Nvidia B200 GPU. Key features include chunk-wise autoregressive adaptation, Source-Anchored Distribution Matching Distillation (SA-DMD) that reduces diffusion to a two-step generator, and Long-Horizon Autoregressive Distillation to mitigate temporal drift.

Introduction

Why this matters

Real-time, open-ended video editing under streaming conditions is challenging because deployed systems cannot access future frames, must run with bounded compute and low latency, and must avoid accumulating temporal drift that breaks identity or motion consistency. The core insight of this paper is that combining causal, chunk-wise autoregressive inference with targeted distillation and long-horizon supervision can close the quality gap between streaming editors and stronger offline systems while enabling practical, single-GPU throughput.

Key Findings
  • Real-time streaming quality: a 16B-parameter autoregressive diffusion editor delivers instruction-guided video-to-video edits while operating causally on incoming frames, achieving an end-to-end throughput of ~30.19 FPS at 720×1280 on a single Nvidia B200 GPU. This demonstrates that high-quality editing can be practical under strict latency and memory constraints.
  • Few-step distilled generator: Source-Anchored Distribution Matching Distillation (SA-DMD) distills iterative diffusion denoising into a two-step generator that retains source fidelity by anchoring distillation to temporally aligned source chunks, enabling low-latency inference without large quality loss.
  • Robustness to autoregressive errors: chunk-wise autoregressive adaptation (sliding temporal window with bounded KV cache) plus Long-Horizon Autoregressive Distillation expose the model to model-generated history and directly supervise states affected by accumulated errors, reducing drift across long streams.
  • Empirical competitiveness: across automatic and human evaluations and a long-video benchmark (LongV2VBench), the method substantially outperforms prior streaming editors and is competitive with strong offline editors on both local and global editing tasks.
Who it’s for and tradeoffs

Great fit if you need: low-latency, instruction-driven editing on live or streaming video where future frames are unavailable; a system that must preserve subject identity and complex temporal dynamics across long durations; research into practical real-time generative video models.

Look elsewhere if: you require ultra-high-resolution offline editing without latency constraints (offline diffusion editors may still produce higher-fidelity per-frame results), have strict memory limits that preclude a 16B model, or need an architecture-agnostic plugin—this work is a full-stack model+training+distillation recipe rather than a lightweight client library.

Where it fits

This paper sits at the intersection of generative video modeling and systems-oriented distillation: it narrows the gap between offline iterative diffusion editors and streaming, causal editors by engineering training-time adaptations (clean-history teacher forcing → resampling forcing) and a source-aware distillation target. It is primarily a research/engineering contribution for teams building real-time video editing pipelines.

Method details (concise)
  • Model stack: MLLM-based condition encoder, causal video VAE, and a multimodal diffusion transformer (16B params) trained first bidirectionally, then converted to chunk-wise causal inference.
  • Chunk-wise inference: attention is bidirectional within each chunk and causal across chunks; a sliding window retains recent chunks plus the first chunk as a global sink, bounding temporal memory and per-chunk compute.
  • Distillation & long-horizon supervision: SA-DMD supervises the distillation target along text-conditioning and source-fidelity axes using aligned source chunks; Long-Horizon Autoregressive Distillation performs segmented optimization over extended rollouts to directly correct accumulated autoregressive errors.

Taken together, these design choices yield a practical pipeline that balances editing quality, source fidelity, and real-time constraints while exposing reasonable tradeoffs for deployment on a single inference GPU.

Information

  • Websitearxiv.org
  • OrganizationsJoy Future Academy, JD
  • AuthorsYicheng Xiao, Wenxun Dai, Xinran Qin, Lin Song, Maoquan Zhang, Hang Xu, Yukang Chen, Yitong Li, Guohui Zhang, Yuan Zhang
  • Published date2026/08/04

Categories

More Items

Introduces WorldExam, a diagnostic benchmark that evaluates controllable video world models across four levels from visual quality to inherent world reactivity. Covers 1,474 cases across eight tasks and supports camera-, action-, and language-driven paradigms, measuring scene-conditioned reactions beyond explicit instructions.

Converts text prompts into physically consistent videos by synthesizing executable Blender programs as a process-level chain-of-thought and using a dual-engine pipeline (deterministic simulation draft + draft-conditioned video editor). Ships with a VideoCoCo-3K draft–instruction–target dataset and shows substantial gains in physical-consistency benchmarks.

Real-time streaming multimodal foundation model that uses a codec-native tokenizer (Mage-ViT) to encode motion- and residual-rich regions from video I/P frames, reducing visual token usage by over 75% and enabling up to ~3.5× wall-clock inference speedup after training on ~560M images and 100M video frames.