Sampling from diffusion probabilistic models (DPMs) is often expensive for
high-quality image generation and typically requires many steps with a large
model. In this paper, we introduce sampling Trajectory Stitching T-Stitch, a
simple yet efficient technique to improve the sampling efficiency with little
or no generation degradation. Instead of solely using a large DPM for the
entire sampling trajectory, T-Stitch first leverages a smaller DPM in the
initial steps as a cheap drop-in replacement of the larger DPM and switches to
the larger DPM at a later stage. Our key insight is that different diffusion
models learn similar encodings under the same training data distribution and
smaller models are capable of generating good global structures in the early
steps. Extensive experiments demonstrate that T-Stitch is training-free,
generally applicable for different architectures, and complements most existing
fast sampling techniques with flexible speed and quality trade-offs. On DiT-XL,
for example, 40% of the early timesteps can be safely replaced with a 10x
faster DiT-S without performance drop on class-conditional ImageNet generation.
We further show that our method can also be used as a drop-in technique to not
only accelerate the popular pretrained stable diffusion (SD) models but also
improve the prompt alignment of stylized SD models from the public model zoo.
Code is released at this https URL

使用 Trajectory Stitching T-Stitch 技术，通过使用较小的 diffusion probabilistic model（DPM）进行初始步骤，然后在后续阶段转换为更大的 DPM，实现采样效率的提高而无需降低生成质量。该方法是无需训练的，适用于不同结构，能够在速度和质量之间灵活权衡。