Diffusion models have recently emerged as powerful generative frameworks for producing high-quality images. A pivotal component of these models is the noise schedule, which governs the rate of noise injection during the diffusion process. Since the noise schedule substantially influences sampling quality and training quality, understanding its design and implications is crucial. In this discussion, various noise schedules are examined, and their distinguishing features and performance characteristics are highlighted.
Paper
References (33)
Scroll for more · 21 remaining
Similar papers
Improved Noise Schedule for Diffusion TrainingTiankai Hang, Shuyang Gu, Jianmin Bao et al.2025 In Library
On the Importance of Noise Scheduling for Diffusion ModelsTing Chen2023 · arXiv.org · 231 citations In Library