ArcFlow：通过高精度非线性流蒸馏实现两步文本到图像生成
ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation
AI总结：
ArcFlow通过高精度非线性流蒸馏实现两步文本到图像生成，提升生成速度并保持质量。
摘要：
扩散模型在生成质量上取得了显著成就，但它们由于依赖多个连续去噪步骤而导致显著的推理成本，这促使近期努力将此推理过程蒸馏为几步。然而，现有蒸馏方法通常通过线性捷径近似教师轨迹，这使得难以匹配其不断变化的切向方向，因为速度在时间步长上变化，从而导致质量下降。为了解决这一限制，我们提出了ArcFlow，一个几步蒸馏框架，它明确使用非线性流轨迹来近似预训练的教师轨迹。具体而言，ArcFlow将推理轨迹下的速度场参数化为连续动量过程的混合物。这使ArcFlow能够捕捉速度演变并外推一致的速度以在每个去噪步骤中形成连续的非线性轨迹。重要的是，这种参数化允许对这一非线性轨迹进行解析积分，这避免了数值离散化误差，从而实现了教师轨迹的高精度近似。为了将此参数化训练为几步生成器，我们通过在预训练教师模型上实现轨迹蒸馏，使用轻量级适配器来实现ArcFlow。这种策略确保了快速、稳定的收敛，同时保持生成多样性和质量。基于大规模模型（Qwen-Image-20B和FLUX.1-dev），ArcFlow仅在原始参数的不到5%上进行微调，并在不显著降低质量的情况下，通过2次前向传递（NFE）实现了比原始多步教师模型快40倍的速度提升。在基准测试上的实验表明，ArcFlow在定性和定量上都表现出有效性。
英文摘要：
Diffusion models have achieved remarkable generation quality, but they suffer from significant inference cost due to their reliance on multiple sequential denoising steps, motivating recent efforts to distill this inference process into a few-step regime. However, existing distillation methods typically approximate the teacher trajectory by using linear shortcuts, which makes it difficult to match its constantly changing tangent directions as velocities evolve across timesteps, thereby leading to quality degradation. To address this limitation, we propose ArcFlow, a few-step distillation framework that explicitly employs non-linear flow trajectories to approximate pre-trained teacher trajectories. Concretely, ArcFlow parameterizes the velocity field underlying the inference trajectory as a mixture of continuous momentum processes. This enables ArcFlow to capture velocity evolution and extrapolate coherent velocities to form a continuous non-linear trajectory within each denoising step. Importantly, this parameterization admits an analytical integration of this non-linear trajectory, which circumvents numerical discretization errors and results in high-precision approximation of the teacher trajectory. To train this parameterization into a few-step generator, we implement ArcFlow via trajectory distillation on pre-trained teacher models using lightweight adapters. This strategy ensures fast, stable convergence while preserving generative diversity and quality. Built on large-scale models (Qwen-Image-20B and FLUX.1-dev), ArcFlow only fine-tunes on less than 5% of original parameters and achieves a 40x speedup with 2 NFEs over the original multi-step teachers without significant quality degradation. Experiments on benchmarks show the effectiveness of ArcFlow both qualitatively and quantitatively.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
