无需修改模型结构，让流模型快速生成高质量图像。
Decoupled MeanFlow: Turning Flow Models into Flow Maps for Accelerated Sampling
- 通过条件化末尾模块预测下一时刻平均速度，实现流模型到流图的转换。
- 在1步内实现ImageNet 256x256上FID 2.16，4步时达FID 1.51，接近流模型性能。
- 兼容预训练模型，推理速度提升超100倍，适合高效生成场景。
去噪生成模型如扩散模型和基于流的模型虽能生成高质量样本，但因离散化误差需大量去噪步骤。流图通过估计时间步间的平均速度可缓解此误差，实现更快采样。然而，其训练通常需架构改动，限制与预训练流模型的兼容性。本文提出Decoupled MeanFlow，一种无需架构修改的解码策略，将流模型直接转为流图模型。方法通过让扩散Transformer的最后几层以后续时间步为条件，使预训练流模型可直接复用。结合增强训练技术，该设计可在1至4步内实现高质量生成。值得注意的是，先训练流模型再转换比从头训练流图更高效有效。在ImageNet 256x256和512x512数据集上，模型分别达到1步FID 2.16和2.12，显著优于现有方法；4步时FID分别为1.51和1.68，几乎匹配流模型性能，同时推理速度提升超100倍。
原文摘要 · Abstract (English)
Denoising generative models, such as diffusion and flow-based models, produce high-quality samples but require many denoising steps due to discretization error. Flow maps, which estimate the average velocity between timesteps, mitigate this error and enable faster sampling. However, their training typically demands architectural changes that limit compatibility with pretrained flow models. We introduce Decoupled MeanFlow, a simple decoding strategy that converts flow models into flow map models without architectural modifications. Our method conditions the final blocks of diffusion transformers on the subsequent timestep, allowing pretrained flow models to be directly repurposed as flow maps. Combined with enhanced training techniques, this design enables high-quality generation in as few as 1 to 4 steps. Notably, we find that training flow models and subsequently converting them is more efficient and effective than training flow maps from scratch. On ImageNet 256x256 and 512x512, our models attain 1-step FID of 2.16 and 2.12, respectively, surpassing prior art by a large margin. Furthermore, we achieve FID of 1.51 and 1.68 when increasing the steps to 4, which nearly matches the performance of flow models while delivering over 100x faster inference.
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。