提出PCM模型，让扩散模型生成速度提升近3倍
PCM : Picard Consistency Model for Fast Parallel Sampling of Diffusion Models
- 用皮卡德迭代加一致性训练，直接预测最终输出
- 实测比串行采样快2.71倍，比原方法快1.77倍
- 适合需要快速生成的图像与机器人控制场景
近期扩散模型在视觉、文本和机器人领域取得显著进展，但仍受制于串行去噪过程导致的生成速度慢。为解决此问题，已有基于皮卡德迭代的并行采样方法，能在保证精确收敛的同时减少序列步骤，但其收敛速度无法保证，实际生成仍可能较慢。本文提出新的并行化方案——皮卡德一致性模型（PCM），显著减少皮卡德迭代中的生成步数。受一致性模型启发，PCM 直接训练以预测收敛轨迹中任意阶段的固定点解（即最终输出）。此外，引入模型切换机制，解决PCM局限性并确保精确收敛。大量实验表明，PCM 在图像生成和机器人控制等任务中，相比串行采样实现最高2.71倍加速，相比皮卡德迭代实现1.77倍加速。
原文摘要 · Abstract (English)
Recently, diffusion models have achieved significant advances in vision, text, and robotics. However, they still face slow generation speeds due to sequential denoising processes. To address this, a parallel sampling method based on Picard iteration was introduced, effectively reducing sequential steps while ensuring exact convergence to the original output. Nonetheless, Picard iteration does not guarantee faster convergence, which can still result in slow generation in practice. In this work, we propose a new parallelization scheme, the Picard Consistency Model (PCM), which significantly reduces the number of generation steps in Picard iteration. Inspired by the consistency model, PCM is directly trained to predict the fixed-point solution, or the final output, at any stage of the convergence trajectory. Additionally, we introduce a new concept called model switching, which addresses PCM's limitations and ensures exact convergence. Extensive experiments demonstrate that PCM achieves up to a 2.71x speedup over sequential sampling and a 1.77x speedup over Picard iteration across various tasks, including image generation and robotic control.
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。