Fast Sampling Through The Reuse Of Attention Maps In Diffusion Models
CoRR(2023)
摘要
Text-to-image diffusion models have demonstrated unprecedented capabilities
for flexible and realistic image synthesis. Nevertheless, these models rely on
a time-consuming sampling procedure, which has motivated attempts to reduce
their latency. When improving efficiency, researchers often use the original
diffusion model to train an additional network designed specifically for fast
image generation. In contrast, our approach seeks to reduce latency directly,
without any retraining, fine-tuning, or knowledge distillation. In particular,
we find the repeated calculation of attention maps to be costly yet redundant,
and instead suggest reusing them during sampling. Our specific reuse strategies
are based on ODE theory, which implies that the later a map is reused, the
smaller the distortion in the final image. We empirically compare these reuse
strategies with few-step sampling procedures of comparable latency, finding
that reuse generates images that are closer to those produced by the original
high-latency diffusion model.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要