4 papers
Tikhonov-Stabilized Bezier Representation Forecasting for Training-free Diffusion Acceleration
Lei Zhu, Mujie Lin, Ruochong Zheng +5
Diffusion models, particularly Diffusion Transformers, achieve strong image and video generation quality but remain expensive at inference time due to repeated denoiser evaluations…
Three Creates All: You Only Sample 3 Steps
Yuren Cai, Guangyi Wang, Zongqing Li +3
Diffusion models deliver high-fidelity generation but remain slow at inference time due to many sequential network evaluations. We find that standard timestep conditioning becomes…
Diffusion Sampling Correction via Approximately 10 Parameters
Guangyi Wang, Wei Peng, Lijiang Li +3
While powerful for generation, Diffusion Probabilistic Models (DPMs) face slow sampling challenges, for which various distillation-based methods have been proposed. However, they t…
PFDiff: Training-Free Acceleration of Diffusion Models Combining Past and Future Scores
Guangyi Wang, Yuren Cai, Lijiang Li +2
Diffusion Probabilistic Models (DPMs) have shown remarkable potential in image generation, but their sampling efficiency is hindered by the need for numerous denoising steps. Most…