图像生成 - arXivDaily 专题

2406.02540 2025-02-25 cs.CV 83%

ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation

Tianchen Zhao, Tongcheng Fang, Haofeng Huang, Enshu Liu, Rui Wan, Widyadewi Soedarmadji, Shiyao Li, Zinan Lin, Guohao Dai, Shengen Yan, Huazhong Yang, Xuefei Ning, Yu Wang

专题命中效率与蒸馏：diffusion(title,abstract)；text-to-image(abstract)；分类 cs.CV

Comments Accepted at ICLR 2025, Project Page: https://a-suozhang.xyz/viditq.github.io/

2501.15448 2025-01-28 cs.CV cs.AI cs.AR cs.LG 83%

SQ-DM: Accelerating Diffusion Models with Aggressive Quantization and Temporal Sparsity

Zichen Fan, Steve Dai, Rangharajan Venkatesan, Dennis Sylvester, Brucek Khailany

专题命中效率与蒸馏：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

Comments 7 pages, 12 figures, 2 tables

2501.00124 2025-01-03 cs.CV cs.LG 83%

PQD: Post-training Quantization for Efficient Diffusion Models

Jiaojiao Ye, Zhen Wang, Linnan Jiang

专题命中效率与蒸馏：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

Comments 7 pages, 3 figures, uses wacv.sty

2412.14170 2024-12-20 cs.CV cs.AI cs.LG 83%

E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling

Zhihang Yuan, Yuzhang Shang, Hanling Zhang, Tongcheng Fang, Rui Xie, Bingxin Xu, Yan Yan, Shengen Yan, Guohao Dai, Yu Wang

专题命中效率与蒸馏：image generation(title,abstract)；diffusion(abstract)；分类 cs.CV

2412.05926 2024-12-10 cs.CV 83%

BiDM: Pushing the Limit of Quantization for Diffusion Models

Xingyu Zheng, Xianglong Liu, Yichen Bian, Xudong Ma, Yulun Zhang, Jiakai Wang, Jinyang Guo, Haotong Qin

专题命中效率与蒸馏：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

Comments NeurIPS 2024

2410.23274 2024-12-04 cs.LG cs.AI cs.CV 83%

Multi-student Diffusion Distillation for Better One-step Generators

Yanke Song, Jonathan Lorraine, Weili Nie, Karsten Kreis, James Lucas

专题命中效率与蒸馏：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

Comments Project page: https://research.nvidia.com/labs/toronto-ai/MSD/

2406.05768 2024-11-08 cs.CV cs.AI 83%

TLCM: Training-efficient Latent Consistency Model for Image Generation with 2-8 Steps

Qingsong Xie, Zhenyi Liao, Zhijie Deng, Chen chen, Haonan Lu

专题命中效率与蒸馏：image generation(title,abstract)；diffusion(abstract)；分类 cs.CV

2406.11838 2024-11-04 cs.CV 83%

Autoregressive Image Generation without Vector Quantization

Tianhong Li, Yonglong Tian, He Li, Mingyang Deng, Kaiming He

专题命中效率与蒸馏：image generation(title,abstract)；diffusion(abstract)；分类 cs.CV

Comments Neurips 2024 (Spotlight). Code: https://github.com/LTH14/mar

2406.08177 2024-10-25 eess.IV cs.CV 83%

One-Step Effective Diffusion Network for Real-World Image Super-Resolution

Rongyuan Wu, Lingchen Sun, Zhiyuan Ma, Lei Zhang

专题命中效率与蒸馏：diffusion(title,abstract)；text-to-image(abstract)；分类 cs.CV

Comments Accepted by NeurIPS 2024

2410.16794 2024-10-23 cs.CV cs.AI cs.LG 83%

One-Step Diffusion Distillation through Score Implicit Matching

Weijian Luo, Zemin Huang, Zhengyang Geng, J. Zico Kolter, Guo-jun Qi

专题命中效率与蒸馏：diffusion(title,abstract)；text-to-image(abstract)；分类 cs.CV

Comments Accepted by NeurIPS 2024

Journal ref NeurIPS 2024

2405.16005 2024-10-18 cs.CV 83%

PTQ4DiT: Post-training Quantization for Diffusion Transformers

Junyi Wu, Haoxuan Wang, Yuzhang Shang, Mubarak Shah, Yan Yan

专题命中效率与蒸馏：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

Comments NeurIPS 2024. Code is available at https://github.com/adreamwu/PTQ4DiT

2410.04191 2024-10-08 cs.CV cs.AI 83%

Accelerating Diffusion Models with One-to-Many Knowledge Distillation

Linfeng Zhang, Kaisheng Ma

专题命中效率与蒸馏：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

2410.01912 2024-10-04 cs.CV cs.AI cs.CL 83%

A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation

Liang Chen, Sinan Tan, Zefan Cai, Weichu Xie, Haozhe Zhao, Yichi Zhang, Junyang Lin, Jinze Bai, Tianyu Liu, Baobao Chang

专题命中效率与蒸馏：image generation(title,abstract)；diffusion(abstract)；分类 cs.CV

Comments 25 pages, 20 figures, code is open at https://github.com/chenllliang/DnD-Transformer

2409.19128 2024-10-03 cs.CV 83%

Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models

Yize Li, Yihua Zhang, Sijia Liu, Xue Lin

专题命中效率与蒸馏：diffusion(title,abstract)；image synthesis(abstract)；分类 cs.CV

Comments Under Review

2409.19681 2024-10-01 cs.CV 83%

Simple and Fast Distillation of Diffusion Models

Zhenyu Zhou, Defang Chen, Can Wang, Chun Chen, Siwei Lyu

专题命中效率与蒸馏：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

Comments Accepted by NeurIPS 2024

2409.17058 2024-09-26 cs.CV 83%

Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors

Aiping Zhang, Zongsheng Yue, Renjing Pei, Wenqi Ren, Xiaochun Cao

专题命中效率与蒸馏：diffusion(title,abstract)；text-to-image(abstract)；分类 cs.CV

Comments The code is available at https://github.com/ArcticHare105/S3Diff

2408.17131 2024-09-02 cs.CV cs.AI 83%

VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers

Juncan Deng, Shuaiting Li, Zeyu Wang, Hong Gu, Kedong Xu, Kejie Huang

专题命中效率与蒸馏：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

Comments 11 pages, 6 figures

2408.14176 2024-08-28 cs.CV cs.AI 83%

SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teacher

Trung Dao, Thuan Hoang Nguyen, Thanh Le, Duc Vu, Khoi Nguyen, Cuong Pham, Anh Tran

专题命中效率与蒸馏：diffusion(title,abstract)；text-to-image(abstract)；分类 cs.CV

Comments Accepted to ECCV'24

2404.13903 2024-07-23 cs.CV 83%

Accelerating Image Generation with Sub-path Linear Approximation Model

Chen Xu, Tianhui Song, Weixin Feng, Xubin Li, Tiezheng Ge, Bo Zheng, Limin Wang

专题命中效率与蒸馏：image generation(title,abstract)；diffusion(abstract)；分类 cs.CV

2405.20750 2024-06-10 cs.CV 83%

Diffusion Models Are Innate One-Step Generators

Bowen Zheng, Tianming Yang

专题命中效率与蒸馏：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

Comments 9 pages, 4 figures and 4 tables on the main contents

2406.04103 2024-06-07 cs.LG cs.AI cs.CV cs.NE 83%

Multistep Distillation of Diffusion Models via Moment Matching

Tim Salimans, Thomas Mensink, Jonathan Heek, Emiel Hoogeboom

专题命中效率与蒸馏：diffusion(title,abstract)；text-to-image(abstract)；分类 cs.CV

2305.18723 2024-05-01 cs.CV 83%

Towards Accurate Post-training Quantization for Diffusion Models

Changyuan Wang, Ziwei Wang, Xiuwei Xu, Yansong Tang, Jie Zhou, Jiwen Lu

专题命中效率与蒸馏：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

2404.13798 2024-04-23 cs.CV 83%

Enforcing Conditional Independence for Fair Representation Learning and Causal Image Generation

Jensen Hwa, Qingyu Zhao, Aditya Lahiri, Adnan Masood, Babak Salimi, Ehsan Adeli

专题命中效率与蒸馏：image generation(title,abstract)；diffusion(abstract)；分类 cs.CV

Comments To appear at the 2024 IEEE CVPR Workshop on Fair, Data-Efficient, and Trusted Computer Vision

2310.03270 2024-04-16 cs.CV 83%

EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models

Yefei He, Jing Liu, Weijia Wu, Hong Zhou, Bohan Zhuang

专题命中效率与蒸馏：diffusion(title,abstract)；image synthesis(abstract)；分类 cs.CV

Comments Accepted by ICLR 2024

2311.16503 2024-03-12 cs.CV cs.AI cs.LG 83%

TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models

Yushi Huang, Ruihao Gong, Jing Liu, Tianlong Chen, Xianglong Liu

专题命中效率与蒸馏：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

2312.15516 2024-03-06 cs.CV 83%

A-SDM: Accelerating Stable Diffusion through Redundancy Removal and Performance Optimization

Jinchao Zhu, Yuxuan Wang, Xiaobing Tu, Siyuan Pan, Pengfei Wan, Gao Huang

专题命中效率与蒸馏：diffusion(title,abstract)；text-to-image(abstract)；分类 cs.CV

Comments Since the experimental part has not been added, we wish to withdraw the manuscript, and we hope to submit it after the experiment has been verified

2311.17042 2023-11-29 cs.CV 83%

Adversarial Diffusion Distillation

Axel Sauer, Dominik Lorenz, Andreas Blattmann, Robin Rombach

专题命中效率与蒸馏：diffusion(title,abstract)；image synthesis(abstract)；分类 cs.CV

2311.16488 2023-11-29 cs.CV cs.AI 83%

Efficient Multimodal Diffusion Models Using Joint Data Infilling with Partially Shared U-Net

Zizhao Hu, Shaochong Jia, Mohammad Rostami

专题命中效率与蒸馏：diffusion(title,abstract)；inpainting(abstract)；分类 cs.CV

2310.05400 2023-10-10 cs.CV 83%

Efficient-VQGAN: Towards High-Resolution Image Generation with Efficient Vision Transformers

Shiyue Cao, Yueqin Yin, Lianghua Huang, Yu Liu, Xin Zhao, Deli Zhao, Kaiqi Huang

专题命中效率与蒸馏：image generation(title,abstract)；image synthesis(abstract)；分类 cs.CV

Comments This paper is accepted to ICCV2023

2207.02196 2022-12-06 cs.CV 83%

Accelerating Score-based Generative Models with Preconditioned Diffusion Sampling

Hengyuan Ma, Li Zhang, Xiatian Zhu, Jianfeng Feng

专题命中效率与蒸馏：diffusion(title,abstract)；image generation(abstract)；分类 cs.CV

Comments ECCV 2022. Code is available at https://github.com/fudan-zvg/PDS

1. 效率与蒸馏 2536 篇

ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation

SQ-DM: Accelerating Diffusion Models with Aggressive Quantization and Temporal Sparsity

PQD: Post-training Quantization for Efficient Diffusion Models

E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling

BiDM: Pushing the Limit of Quantization for Diffusion Models

Multi-student Diffusion Distillation for Better One-step Generators

TLCM: Training-efficient Latent Consistency Model for Image Generation with 2-8 Steps

Autoregressive Image Generation without Vector Quantization

One-Step Effective Diffusion Network for Real-World Image Super-Resolution

One-Step Diffusion Distillation through Score Implicit Matching

PTQ4DiT: Post-training Quantization for Diffusion Transformers

Accelerating Diffusion Models with One-to-Many Knowledge Distillation

A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation

Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models

Simple and Fast Distillation of Diffusion Models

Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors

VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers

SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teacher

Accelerating Image Generation with Sub-path Linear Approximation Model

Diffusion Models Are Innate One-Step Generators

Multistep Distillation of Diffusion Models via Moment Matching

Towards Accurate Post-training Quantization for Diffusion Models

Enforcing Conditional Independence for Fair Representation Learning and Causal Image Generation

EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models

TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models

A-SDM: Accelerating Stable Diffusion through Redundancy Removal and Performance Optimization

Adversarial Diffusion Distillation

Efficient Multimodal Diffusion Models Using Joint Data Infilling with Partially Shared U-Net

Efficient-VQGAN: Towards High-Resolution Image Generation with Efficient Vision Transformers

Accelerating Score-based Generative Models with Preconditioned Diffusion Sampling