让图像生成自动决定去噪步数，又快又好。
Schedule On the Fly: Diffusion Time Prediction for Faster and Better Image Generation
- 用神经模块实时预测每一步的噪声水平。
- 少用50%步骤，美学分5.44，人偏好评分29.59。
- 适合追求高效高质图像生成的开发者。
扩散模型与流匹配模型在文生图任务中表现卓越，但通常依赖固定的去噪调度。多步逆向去噪过程可视为生成高质量图像的逐步推理链。因此，模型应针对每个输入实例自适应调整最优噪声调度，以兼顾生成质量与采样效率。本文提出时间预测扩散模型（TPDM），引入即插即用的时间预测模块（TPM），基于当前潜在特征预测下一步噪声水平。通过强化学习训练TPM，最大化最终图像质量奖励并惩罚过多去噪步骤。该自适应调度机制使TPDM不仅生成与人类偏好高度一致的高质量图像，还能动态调整扩散时长和去噪步数，提升性能与效率。在Stable Diffusion 3 Medium架构下，TPDM实现美学分5.44、人偏好评分29.59，且仅需约一半的去噪步数即达更优效果。
原文摘要 · Abstract (English)
Diffusion and flow matching models have achieved remarkable success in text-to-image generation. However, these models typically rely on the predetermined denoising schedules for all prompts. The multi-step reverse diffusion process can be regarded as a kind of chain-of-thought for generating high-quality images step by step. Therefore, diffusion models should reason for each instance to adaptively determine the optimal noise schedule, achieving high generation quality with sampling efficiency. In this paper, we introduce the Time Prediction Diffusion Model (TPDM) for this. TPDM employs a plug-and-play Time Prediction Module (TPM) that predicts the next noise level based on current latent features at each denoising step. We train the TPM using reinforcement learning to maximize a reward that encourages high final image quality while penalizing excessive denoising steps. With such an adaptive scheduler, TPDM not only generates high-quality images that are aligned closely with human preferences but also adjusts diffusion time and the number of denoising steps on the fly, enhancing both performance and efficiency. With Stable Diffusion 3 Medium architecture, TPDM achieves an aesthetic score of 5.44 and a human preference score (HPS) of 29.59, while using around 50% fewer denoising steps to achieve better performance.
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。