New STMD method speeds diffusion model inference without teacher

Researchers have developed Stochastic Transition-Map Distillation (STMD), a novel framework designed to accelerate the inference process for diffusion models without requiring a pre-trained teacher model. This method distills the full transition map of the sampling stochastic differential equation (SDE), enabling faster, probabilistic sample generation. STMD offers a theoretical foundation with convergence bounds in Wasserstein distance and has been demonstrated on image generation tasks across MNIST, CIFAR-10, and CelebA datasets. AI

影响 Accelerates diffusion model inference, potentially enabling wider use in applications requiring fast, probabilistic generation.

排序理由 Publication of a new academic paper detailing a novel method for accelerating diffusion model inference. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

• CIFAR-10
• George Rapakoulias
• MNIST
• Stochastic Transition-Map Distillation (STMD)
• CelebA
• diffusion models

• 论文
• 模型发布

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →