图像生成 - arXivDaily 专题

2406.14555 2024-06-21 cs.CV 92%

A Survey of Multimodal-Guided Image Editing with Text-to-Image Diffusion Models

Xincheng Shuai, Henghui Ding, Xingjun Ma, Rongcheng Tu, Yu-Gang Jiang, Dacheng Tao

专题命中文生图：text-to-image(title,abstract)；diffusion(title,abstract)；image editing(title,abstract)；分类 cs.CV

Comments Project Page: https://github.com/xinchengshuai/Awesome-Image-Editing

2311.17216 2024-03-29 cs.CV 92%

Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation

Hang Li, Chengzhi Shen, Philip Torr, Volker Tresp, Jindong Gu

专题命中文生图：image generation(title,abstract)；text-to-image(title,abstract)；diffusion(title,abstract)；分类 cs.CV

Comments Accepted to CVPR 2024

2403.06381 2024-03-12 cs.CV 92%

Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models

Yang Zhang, Teoh Tze Tzun, Lim Wei Hern, Tiviatis Sim, Kenji Kawaguchi

专题命中文生图：text-to-image(title,abstract)；diffusion(title,abstract)；image synthesis(title,abstract)；分类 cs.CV

2305.18295 2024-03-12 cs.CV 92%

RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths

Zeyue Xue, Guanglu Song, Qiushan Guo, Boxiao Liu, Zhuofan Zong, Yu Liu, Ping Luo

专题命中文生图：image generation(title,abstract)；text-to-image(title,abstract)；diffusion(title,abstract)；分类 cs.CV

Comments NeurIPS 2023

2403.05121 2024-03-11 cs.CV 92%

CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion

Wendi Zheng, Jiayan Teng, Zhuoyi Yang, Weihan Wang, Jidong Chen, Xiaotao Gu, Yuxiao Dong, Ming Ding, Jie Tang

专题命中文生图：image generation(title,abstract)；text-to-image(title,abstract)；diffusion(title,abstract)；分类 cs.CV

2306.08645 2023-10-27 cs.CV cs.LG eess.IV 92%

Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis

Zhiyu Jin, Xuli Shen, Bin Li, Xiangyang Xue

专题命中文生图：text-to-image(title,abstract)；diffusion(title,abstract)；image synthesis(title,abstract)；分类 cs.CV

Comments Accepted by NeurIPS 2023. 23 pages, 13 figures

2304.03869 2023-04-11 cs.CV 92%

Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis

Qiucheng Wu, Yujian Liu, Handong Zhao, Trung Bui, Zhe Lin, Yang Zhang, Shiyu Chang

专题命中文生图：text-to-image(title,abstract)；diffusion(title,abstract)；image synthesis(title,abstract)；分类 cs.CV

Comments 20 pages, 16 figures

2212.05032 2023-03-02 cs.CV cs.CL 92%

Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis

Weixi Feng, Xuehai He, Tsu-Jui Fu, Varun Jampani, Arjun Akula, Pradyumna Narayana, Sugato Basu, Xin Eric Wang, William Yang Wang

专题命中文生图：text-to-image(title,abstract)；diffusion(title,abstract)；image synthesis(title,abstract)；分类 cs.CV

Comments ICLR 2023 Camera Ready version

2211.07751 2022-11-16 cs.CV eess.IV 92%

Arbitrary Style Guidance for Enhanced Diffusion-Based Text-to-Image Generation

Zhihong Pan, Xin Zhou, Hao Tian

专题命中文生图：image generation(title,abstract)；text-to-image(title,abstract)；diffusion(title,abstract)；分类 cs.CV

Comments To appear at WACV 2023

2209.10948 2022-09-23 cs.CV cs.LG 92%

Implementing and Experimenting with Diffusion Models for Text-to-Image Generation

Robin Zbinden

专题命中文生图：image generation(title,abstract)；text-to-image(title,abstract)；diffusion(title,abstract)；分类 cs.CV

Comments Master's Thesis

2111.14822 2022-03-04 cs.CV cs.LG 92%

Vector Quantized Diffusion Model for Text-to-Image Synthesis

Shuyang Gu, Dong Chen, Jianmin Bao, Fang Wen, Bo Zhang, Dongdong Chen, Lu Yuan, Baining Guo

专题命中文生图：text-to-image(title,abstract)；diffusion(title,abstract)；image synthesis(title)；image generation(abstract)

2408.12692 2025-03-28 cs.AI 91%

Rethinking Training for De-biasing Text-to-Image Generation: Unlocking the Potential of Stable Diffusion

Eunji Kim, Siwon Kim, Minjun Park, Rahim Entezari, Sungroh Yoon

专题命中文生图：image generation(title,abstract)；text-to-image(title,abstract)；diffusion(title,abstract)

Comments 19 pages; First two authors contributed equally; Accepted at CVPR 2025

2405.14828 2025-04-18 cs.CV 91%

Good Seed Makes a Good Crop: Discovering Secret Seeds in Text-to-Image Diffusion Models

Katherine Xu, Lingzhi Zhang, Jianbo Shi

专题命中文生图：text-to-image(title,abstract)；diffusion(title,abstract)；image generation(abstract)；inpainting(abstract)

2411.16164 2024-11-26 cs.CV 91%

Text-to-Image Synthesis: A Decade Survey

Nonghai Zhang, Hao Tang

专题命中文生图：text-to-image(title,abstract)；image synthesis(title,abstract)；image generation(abstract)；diffusion(abstract)

Comments In this survey, we review over 440 recent works on T2I

2401.02015 2024-06-05 cs.CV cs.AI cs.LG 91%

Improving Diffusion-Based Image Synthesis with Context Prediction

Ling Yang, Jingwei Liu, Shenda Hong, Zhilong Zhang, Zhilin Huang, Zheming Cai, Wentao Zhang, Bin Cui

专题命中文生图：diffusion(title,abstract)；image synthesis(title,abstract)；image generation(abstract)；text-to-image(abstract)

Comments Accepted by NeurIPS 2023

2403.12015 2024-03-19 cs.CV 91%

Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation

Axel Sauer, Frederic Boesel, Tim Dockhorn, Andreas Blattmann, Patrick Esser, Robin Rombach

专题命中文生图：diffusion(title,abstract)；image synthesis(title,abstract)；text-to-image(abstract)；image editing(abstract)

2301.00704 2023-01-03 cs.CV cs.AI cs.LG 91%

Muse: Text-To-Image Generation via Masked Generative Transformers

Huiwen Chang, Han Zhang, Jarred Barber, AJ Maschinot, Jose Lezama, Lu Jiang, Ming-Hsuan Yang, Kevin Murphy, William T. Freeman, Michael Rubinstein, Yuanzhen Li, Dilip Krishnan

专题命中文生图：image generation(title,abstract)；text-to-image(title,abstract)；diffusion(abstract)；image editing(abstract)

2304.06720 2025-01-16 cs.CV cs.GR cs.LG 91%

Expressive Text-to-Image Generation with Rich Text

Songwei Ge, Taesung Park, Jun-Yan Zhu, Jia-Bin Huang

专题命中文生图：text-to-image(title,abstract)；image generation(title,abstract)；diffusion(abstract)；image synthesis(abstract)

Comments Project webpage: https://rich-text-to-image.github.io/

2607.26647 2026-07-30 cs.CV 新提交 91%

Anchoring and Steering Diffusion: Enhancing the Faithfulness of Text-to-Image Generation at Inference Time

锚定与引导扩散：在推理时提升文生图生成的忠实度

Xinyi Wang, Yuyang Huang, Yalin Su, Pengcheng Luan, Tao Zhang, Feiming Wei, Wenxian Yu

机构 * Shanghai Jiao Tong University（上海交通大学）

专题命中文生图：text-to-image(title,abstract)；diffusion(title,abstract)；image generation(title)；分类 cs.CV

AI总结提出无训练框架AnchorSteer，通过语义锚定与反射引导组件改进文生图扩散模型的推理，在GenEval等基准上提升文本-图像对齐性能且保持视觉质量。

Comments Accepted by ECCV 2026

2603.20828 2026-03-24 cs.CV 91%

EruDiff: Refactoring Knowledge in Diffusion Models for Advanced Text-to-Image Synthesis

EruDiff：在扩散模型中重构知识以实现高级文本到图像合成

Xiefan Guo, Xinzhu Ma, Haoxiang Ma, Zihao Zhou, Di Huang

机构 * Beihang University（北航大学）； Shanghai AI Laboratory（上海人工智能实验室）

专题命中文生图：text-to-image(title,abstract)；diffusion(title,abstract)；image synthesis(title)；分类 cs.CV

AI总结本文提出EruDiff，通过Diffusion Knowledge Distribution Matching和Negative-Only Reinforcement Learning提升扩散模型处理隐式提示的能力，增强科学和世界知识生成性能。

2511.19965 2025-11-26 cs.CV 91%

HiCoGen: Hierarchical Compositional Text-to-Image Generation in Diffusion Models via Reinforcement Learning

HiCoGen: 通过强化学习在扩散模型中实现层次化组合文本到图像生成

Hongji Yang, Yucheng Zhou, Wencheng Han, Runzhou Tao, Zhongying Qiu, Jianfei Yang, Jianbing Shen

机构 * SKL-IOTSC, CIS, University of Macau（澳门大学SKL-IOTSC、CIS）； Zhejiang ZEEKR Automobile Research & Development Co., Ltd.（浙江浙汽汽车研发有限公司）

专题命中文生图：text-to-image(title,abstract)；diffusion(title,abstract)；image generation(title)；分类 cs.CV

AI总结 HiCoGen通过强化学习和层次化合成框架提升文本到图像生成的组合性和准确性。

Comments 9 pages

2508.03481 2025-08-06 cs.CV cs.AI cs.CL 91%

Draw Your Mind: Personalized Generation via Condition-Level Modeling in Text-to-Image Diffusion Models

Hyungjin Kim, Seokho Ahn, Young-Duk Seo

机构 * Department of Electrical and Computer Engineering, Inha University（电子与计算机工程系，inha大学）

专题命中文生图：diffusion(title,abstract)；personalized generation(title,abstract)；text-to-image(title)；分类 cs.CV

Comments Accepted at ICCV 2025

2411.18936 2025-03-26 cs.CV 91%

Self-Cross Diffusion Guidance for Text-to-Image Synthesis of Similar Subjects

Weimin Qiu, Jieke Wang, Meng Tang

专题命中文生图：diffusion(title,abstract)；image synthesis(title,abstract)；text-to-image(title)；分类 cs.CV

Comments Conference on Computer Vision and Pattern Recognition (CVPR), 2025

2503.15197 2025-03-20 cs.CV 91%

Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization

Feifei Li, Mi Zhang, Yiming Sun, Min Yang

专题命中文生图：text-to-image(title,abstract)；diffusion(title,abstract)；image generation(title)；分类 cs.CV

Comments CVPR25

2409.01327 2025-03-04 cs.CV 91%

SPDiffusion: Semantic Protection Diffusion Models for Multi-concept Text-to-image Generation

Yang Zhang, Rui Zhang, Xuecheng Nie, Haochen Li, Jikun Chen, Yifan Hao, Xin Zhang, Luoqi Liu, Ling Li

专题命中文生图：text-to-image(title,abstract)；diffusion(title,abstract)；image generation(title)；分类 cs.CV

2312.04005 2024-11-26 cs.CV cs.AI 91%

KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis

Youngwan Lee, Kwanyong Park, Yoorhim Cho, Yong-Ju Lee, Sung Ju Hwang

专题命中文生图：text-to-image(title,abstract)；diffusion(title,abstract)；image synthesis(title)；分类 cs.CV

Comments NeurIPS 2024

2407.06079 2024-07-09 cs.CV cs.AI 91%

Layered Diffusion Model for One-Shot High Resolution Text-to-Image Synthesis

Emaad Khwaja, Abdullah Rashwan, Ting Chen, Oliver Wang, Suraj Kothawade, Yeqing Li

专题命中文生图：text-to-image(title,abstract)；diffusion(title,abstract)；image synthesis(title)；分类 cs.CV

2404.02883 2024-04-04 cs.CV cs.AI cs.LG 91%

On the Scalability of Diffusion-based Text-to-Image Generation

Hao Li, Yang Zou, Ying Wang, Orchid Majumder, Yusheng Xie, R. Manmatha, Ashwin Swaminathan, Zhuowen Tu, Stefano Ermon, Stefano Soatto

专题命中文生图：text-to-image(title,abstract)；diffusion(title,abstract)；image generation(title)；分类 cs.CV

Comments CVPR2024

2311.03008 2024-03-18 cs.CV 91%

Exploring the Capability of Text-to-Image Diffusion Models with Structural Edge Guidance for Multi-Spectral Satellite Image Inpainting

Mikolaj Czerkawski, Christos Tachtatzis

专题命中文生图：text-to-image(title,abstract)；inpainting(title,abstract)；diffusion(title)；分类 cs.CV

2305.13921 2023-12-15 cs.CV 91%

Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Models

Ruichen Wang, Zekang Chen, Chen Chen, Jian Ma, Haonan Lu, Xiaodong Lin

专题命中文生图：text-to-image(title,abstract)；diffusion(title,abstract)；image synthesis(title)；分类 cs.CV

Comments accept by AAAI2024

1. 文生图 3472 篇

A Survey of Multimodal-Guided Image Editing with Text-to-Image Diffusion Models

Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation

Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models

RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths

CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion

Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis

Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis

Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis

Arbitrary Style Guidance for Enhanced Diffusion-Based Text-to-Image Generation

Implementing and Experimenting with Diffusion Models for Text-to-Image Generation

Vector Quantized Diffusion Model for Text-to-Image Synthesis

Rethinking Training for De-biasing Text-to-Image Generation: Unlocking the Potential of Stable Diffusion

Good Seed Makes a Good Crop: Discovering Secret Seeds in Text-to-Image Diffusion Models

Text-to-Image Synthesis: A Decade Survey

Improving Diffusion-Based Image Synthesis with Context Prediction

Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation

Muse: Text-To-Image Generation via Masked Generative Transformers

Expressive Text-to-Image Generation with Rich Text

Anchoring and Steering Diffusion: Enhancing the Faithfulness of Text-to-Image Generation at Inference Time

EruDiff: Refactoring Knowledge in Diffusion Models for Advanced Text-to-Image Synthesis

HiCoGen: Hierarchical Compositional Text-to-Image Generation in Diffusion Models via Reinforcement Learning

Draw Your Mind: Personalized Generation via Condition-Level Modeling in Text-to-Image Diffusion Models

Self-Cross Diffusion Guidance for Text-to-Image Synthesis of Similar Subjects

Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization

SPDiffusion: Semantic Protection Diffusion Models for Multi-concept Text-to-image Generation

KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis

Layered Diffusion Model for One-Shot High Resolution Text-to-Image Synthesis

On the Scalability of Diffusion-based Text-to-Image Generation

Exploring the Capability of Text-to-Image Diffusion Models with Structural Edge Guidance for Multi-Spectral Satellite Image Inpainting

Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Models