Consistency models have recently been introduced to accelerate sampling from diffusion models by directly predicting the solution (i.e., data) of the probability flow ODE (PF ODE) from initial noise. However, the training of consistency models requires learning to map all intermediate points along PF ODE trajectories to their corresponding endpoints. This task is much more challenging than the ultimate objective of one-step generation, which only concerns the PF ODE's noise-to-data mapping. We empirically find that this training paradigm limits the one-step generation performance of consistency models. To address this issue, we generalize consistency training to the truncated time range, which allows the model to ignore denoising tasks at earlier time steps and focus its capacity on generation. We propose a new parameterization of the consistency function and a two-stage training procedure that prevents the truncated-time training from collapsing to a trivial solution. Experiments on CIFAR-10 and ImageNet $64\times64$ datasets show that our method achieves better one-step and two-step FIDs than the state-of-the-art consistency models such as iCT-deep, using more than 2$\times$ smaller networks. Project page: https://truncated-cm.github.io/
Elucidating the Preconditioning in Consistency Distillation
Dept. of Comp. Sci. & Tech., Institute for AI, BNRist Center, THBI Lab(计算机科学与技术系,人工智能研究所,BNRist中心,THBI实验室);Tsinghua-Bosch Joint ML Center, Tsinghua University(清华大学-博世联合机器学习中心,清华大学);Shengshu Technology(盛舒科技);Pazhou Lab (Huangpu), Guangzhou, China(黄埔实验室(广州),中国)
Trajectory Consistency Distillation: Improved Latent Consistency Distillation by Semi-Linear Consistency Function with Trajectory Mapping
South China University of Technology(华南理工大学);Nanyang Technological University(南洋理工大学);Beijing Institute of Technology(北京理工大学);The University of Sydney(悉尼大学)
Marrying Optimal Transport and ODEs for Unified Continuous-Time 4D Reconstruction and Tracking
Macau University of Science and Technology(澳门科技大学);The University of Queensland(昆士兰大学);Great Bay University(大湾区大学);Tsinghua University(清华大学);National University of Singapore(新加坡国立大学);Institute of Automation, Chinese Academy of Sciences (CASIA)(中国科学院自动化研究所)
InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration
Nankai University(南开大学);Mohamed bin Zayed University of AI(穆罕默德·本·扎耶德人工智能大学);Linkoping University(林雪平大学);SB Intuitions, SoftBank(软银SB Intuitions);Nankai International Advanced Research Institute (Shenzhen Futian), Nankai University(南开大学深圳福田国际先进研究院)
Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees
Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);ETH Zurich(苏黎世联邦理工学院);AI Center Tübingen(图宾根人工智能中心);University of Tübingen(图宾根大学);ELLIS Institute Tübingen(图宾根ELLIS研究所);IMPRS-IS(图宾根IMPRS-IS)
School of Electronic Information and Communications, Huazhong University of Science and Technology(华中科技大学电子信息学院);School of Electronic Information(电子信息学院);Communications, Huazhong University of Science(华中科技大学通信学院);School of Science, Wuhan University of Technology(武汉理工大学理学院)
Syndrome-Flow Consistency Model Achieves One-step Denoising Error Correction Codes
Department of Computer Science and Engineering, The Chinese University of Hong Kong(计算机科学与工程系,香港中文大学);Huawei Technologies Co., Ltd.(华为技术有限公司);Theory Lab(理论实验室);Noah’s Ark Lab(诺亚实验室)