Alert button
Picture for Qiang Xu

Qiang Xu

Alert button

DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception

Add code
Bookmark button
Alert button
Mar 20, 2024
Yibo Wang, Ruiyuan Gao, Kai Chen, Kaiqiang Zhou, Yingjie Cai, Lanqing Hong, Zhenguo Li, Lihui Jiang, Dit-Yan Yeung, Qiang Xu, Kai Zhang

Figure 1 for DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception
Figure 2 for DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception
Figure 3 for DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception
Figure 4 for DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception
Viaarxiv icon

BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion

Add code
Bookmark button
Alert button
Mar 11, 2024
Xuan Ju, Xian Liu, Xintao Wang, Yuxuan Bian, Ying Shan, Qiang Xu

Figure 1 for BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion
Figure 2 for BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion
Figure 3 for BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion
Figure 4 for BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion
Viaarxiv icon

Evaluating Text-to-Image Generative Models: An Empirical Study on Human Image Synthesis

Add code
Bookmark button
Alert button
Mar 08, 2024
Muxi Chen, Yi Liu, Jian Yi, Changran Xu, Qiuxia Lai, Hongliang Wang, Tsung-Yi Ho, Qiang Xu

Figure 1 for Evaluating Text-to-Image Generative Models: An Empirical Study on Human Image Synthesis
Figure 2 for Evaluating Text-to-Image Generative Models: An Empirical Study on Human Image Synthesis
Figure 3 for Evaluating Text-to-Image Generative Models: An Empirical Study on Human Image Synthesis
Figure 4 for Evaluating Text-to-Image Generative Models: An Empirical Study on Human Image Synthesis
Viaarxiv icon

GuardT2I: Defending Text-to-Image Models from Adversarial Prompts

Add code
Bookmark button
Alert button
Mar 03, 2024
Yijun Yang, Ruiyuan Gao, Xiao Yang, Jianyuan Zhong, Qiang Xu

Figure 1 for GuardT2I: Defending Text-to-Image Models from Adversarial Prompts
Figure 2 for GuardT2I: Defending Text-to-Image Models from Adversarial Prompts
Figure 3 for GuardT2I: Defending Text-to-Image Models from Adversarial Prompts
Figure 4 for GuardT2I: Defending Text-to-Image Models from Adversarial Prompts
Viaarxiv icon

Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning

Add code
Bookmark button
Alert button
Feb 07, 2024
Yuxuan Bian, Xuan Ju, Jiangtong Li, Zhijian Xu, Dawei Cheng, Qiang Xu

Figure 1 for Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning
Figure 2 for Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning
Figure 3 for Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning
Figure 4 for Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning
Viaarxiv icon

Text Image Inpainting via Global Structure-Guided Diffusion Models

Add code
Bookmark button
Alert button
Feb 02, 2024
Shipeng Zhu, Pengfei Fang, Chenjie Zhu, Zuoyan Zhao, Qiang Xu, Hui Xue

Viaarxiv icon

Non-Cross Diffusion for Semantic Consistency

Add code
Bookmark button
Alert button
Nov 30, 2023
Ziyang Zheng, Ruiyuan Gao, Qiang Xu

Viaarxiv icon

MMA-Diffusion: MultiModal Attack on Diffusion Models

Add code
Bookmark button
Alert button
Nov 29, 2023
Yijun Yang, Ruiyuan Gao, Xiaosen Wang, Nan Xu, Qiang Xu

Viaarxiv icon

Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code

Add code
Bookmark button
Alert button
Oct 19, 2023
Xuan Ju, Ailing Zeng, Yuxuan Bian, Shaoteng Liu, Qiang Xu

Figure 1 for Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code
Figure 2 for Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code
Figure 3 for Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code
Figure 4 for Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code
Viaarxiv icon

MagicDrive: Street View Generation with Diverse 3D Geometry Control

Add code
Bookmark button
Alert button
Oct 13, 2023
Ruiyuan Gao, Kai Chen, Enze Xie, Lanqing Hong, Zhenguo Li, Dit-Yan Yeung, Qiang Xu

Figure 1 for MagicDrive: Street View Generation with Diverse 3D Geometry Control
Figure 2 for MagicDrive: Street View Generation with Diverse 3D Geometry Control
Figure 3 for MagicDrive: Street View Generation with Diverse 3D Geometry Control
Figure 4 for MagicDrive: Street View Generation with Diverse 3D Geometry Control
Viaarxiv icon