Dec, 2023
DeepCache:加速扩散模型的自由之选
DeepCache: Accelerating Diffusion Models for Free
Xinyin Ma, Gongfan Fang, Xinchao Wang
TL;DRDiffusion models have gained attention in image synthesis, and this paper introduces DeepCache, a training-free paradigm that accelerates diffusion models by capitalizing on temporal redundancy in denoising steps and achieving a speedup factor of 2.3x for Stable Diffusion v1.5 and 4.1x for LDM-4-G without significant decline in CLIP Score or FID on ImageNet.