Flex-Forcing：迈向统一的自回归与双向视频扩散模型

摘要

近年来，大规模生成模型的进展显著推动了视频生成技术的发展，但现有方法仍受限于僵化的推理范式。双向扩散模型擅长全局连贯性与视觉保真度，却存在推理速度慢的问题；而自回归模型虽能实现高效且可流式生成的特性，但牺牲了长程一致性与曝光偏差。我们提出Flex-Forcing——一种统一的训练与推理框架，使得视频扩散模型能够在双向生成与自回归生成两种模式下无缝运行。其核心思想是一种在时间轴与去噪步数上联合定义的灵活分块机制。该设计使模型能够：（1）根据不同的设备预算灵活调整分块策略；（2）在分块间进行双向推理以规划全局结构，同时在每个分块内自回归生成帧，实现高效且精细的合成；（3）突破严格的因果约束，支持任意顺序、任意时间步的自回归生成。在多个视频生成基准上的大量实验表明，与采用僵化推理调度的强基线方法相比，Flex-Forcing在视频质量、长视频稳定性上均取得了一致提升，同时推理速度更快。

English

Recent progress in large-scale generative models has substantially advanced video generation, yet existing methods remain constrained by a rigid inference paradigm. Bidirectional diffusion models excel at global coherence and visual fidelity but suffer from slow inference, while autoregressive models offer efficient and streaming generation at the cost of long-range consistency and exposure bias. We introduce Flex-Forcing, a unified training and inference framework that enables a video diffusion model to seamlessly operate under both bidirectional and autoregressive generation regimes. The core idea is a flexible chunking mechanism jointly defined over the temporal axis and denoising steps. This design allows the model to (1) perform flexible chunking according to different device budgets, (2) perform bidirectional inference across chunks for global structure planning, while generating frames autoregressively within each chunk for efficient and fine-grained synthesis, and (3) perform any-order, any-timestep autoregressive generation without the strict causal constraint. Extensive experiments on multiple video generation benchmarks demonstrate that Flex-Forcing achieves consistently better video quality, long-video stability than strong baselines with a rigid inference schedule, while offering faster inference.