The curvature of ODE trajectories in diffusion models hinders their ability to generate high-quality images in a few number of function evaluations (NFE). In this paper, we propose a novel and effective approach to reduce trajectory curvature by utilizing adaptive conditions. By employing a extremely light-weight quantized encoder, our method incurs only an additional 1% of training parameters, eliminates the need for extra regularization terms, yet achieves significantly better sample quality. Our approach accelerates ODE sampling while preserving the downstream task image editing capabilities of SDE techniques. Extensive experiments verify that our method can generate high quality results under extremely limited sampling costs. With only 6 NFE, we achieve 5.14 FID on CIFAR-10, 6.91 FID on FFHQ 64x64 and 3.10 FID on AFHQv2.
Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes
S$^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences(人工智能安全国家重点实验室,计算技术研究所,中国科学院);University of Chinese Academy of Sciences(中国科学院大学);ETH Zürich(苏黎世联邦理工学院)
Sequence-Adaptive Video Prediction in Continuous Streams using Diffusion Noise Optimization
University of Bonn(波恩大学);Toyota Motor Europe(丰田欧洲公司);University of Wuerzburg(乌尔姆大学);Lamarr Institute for Machine Learning and Artificial Intelligence(拉马尔人工智能与机器学习研究所)
Hardware-Friendly Static Quantization Method for Video Diffusion Transformers
Division of the Humanities and Social Sciences(人文与社会科学系);California Institute of Technology(加州理工学院);Device Solutions Research America(设备解决方案研究美国);Samsung Semiconductor Inc.(三星半导体公司)
LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China.(中国人民大学人工智能学院);Beijing Key Laboratory of Research on Large Models(北京大型模型研究关键实验室);Engineering Research Center of Next-Generation Intelligent Search(下一代智能搜索工程研究中心)
All-in-One Medical Image Restoration with Latent Diffusion-Enhanced Vector-Quantized Codebook Prior
School of Biological Science and Medical Engineering(生物科学与医学工程学院);State Key Laboratory of Software Development Environment(软件开发环境国家重点实验室);Key Laboratory of Biomechanics and Mechanobiology of Ministry of Education(教育部生物力学与机械生物学重点实验室);Beijing Advanced Innovation Center for Biomedical Engineering(北京生物医学工程先进创新中心);Beihang University(北京航空航天大学);Department of Biomedical Engineering(生物医学工程系);Tsinghua University(清华大学);ByteDance Inc.(字节跳动公司)
QArtSR: Quantization via Reverse-Module and Timestep-Retraining in One-Step Diffusion based Image Super-Resolution
Shanghai Jiao Tong University(上海交通大学);ETH Zürich(苏黎世联邦理工学院);Singapore Institute of Technology(新加坡理工学院);Chinese University of Hong Kong(香港中文大学);Max Planck Institute for Informatics(马克斯·普朗克信息学研究所)
LightQANet: Quantized and Adaptive Feature Learning for Low-Light Image Enhancement
College of Computer Science and Software Engineering, Shenzhen University(深圳大学计算机科学与软件工程学院);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算机与数据科学学院);Computer Vision Institute, College of Computer Science and Software Engineering, Shenzhen University(深圳大学计算机视觉研究院);School of AI and Advanced Computing, Xi’an Jiaotong-Liverpool University(西安交通大学利物浦大学人工智能与先进计算学院);School of Mathematics and Statistics, Changsha University of Science and Technology(长沙理工大学数学与统计学院);School of Computer Science, Sichuan Normal University(四川师范大学计算机科学学院);Department of Computer Science, University of Nottingham Ningbo China(宁波大学计算机科学系)
QUVA Lab, University of Amsterdam(QUVA实验室,阿姆斯特丹大学);AMLab, Informatics Institute, University of Amsterdam(AMLab,阿姆斯特丹大学信息学院);AI4Science Lab, University of Amsterdam(AI4Science实验室,阿姆斯特丹大学);Korteweg-de Vries Institute for Mathematics, University of Amsterdam(科特韦格 - 德弗里斯数学研究所,阿姆斯特丹大学);Qualcomm AI Research(高通人工智能研究公司);FunAI Lab, University of Technology Nuremberg(FunAI实验室,纽伦堡工业大学)
VQ-DeepISC: Vector Quantized-Enabled Digital Semantic Communication with Channel Adaptive Image Transmission
ZGC Institute of Ubiquitous-X Innovation and Applications(ubiquitous-X创新与应用研究院);State Key Laboratory of Networking and Switching Technology(网络与交换技术国家重点实验室);Beijing University of Posts and Telecommunications(北京邮电大学)
An Adaptive Statistical Non-uniform Quantizer for Detail Wavelet Components in Lossy JPEG2000 Image Compression
Cornell University(康奈尔大学);Indian Institute of Information Technology, Allahabad(阿拉哈巴德印度信息技术学院);Indian Institute of Science Education and Research - Kolkata(加尔各答印度科学教育与研究学院)