T2I Generation

T2I: Text-to-Image

Text-to-image generation studies how models turn natural-language instructions into images, primarily using diffusion and flow-matching models, autoregressive visual-token models, and unified multimodal systems. Researchers improve prompt following through better text and visual representations, spatial planning, reference-image conditioning, and post-training with preference or rubric-based rewards. Benchmarks test compositional alignment, counting, text rendering, world knowledge, and visual quality, while audits examine bias, privacy, and harmful outputs. A central challenge is making generations reliably match complex instructions and real-world constraints without sacrificing diversity, image quality, efficiency, or safety.

Latest papers

302 papers45 papers in the last four weeks, up 88% on the four weeks before. 0.3% of all new papers.

CleanStyle: Plug-and-Play Style Conditioning Purification for Text-to-Image Stylization
Feb 24, 2026Xiaoman Feng, Mingkun Lei, Yang Wang +2Image Style Transfer T2I Diffusion Models
AGI Lab, Westlake University
BBQ-to-Image: Numeric Bounding Box and Qolor Control in Large-Scale Text-to-Image Models
Feb 24, 2026Eliran Kachlon, Alexander Visheratin, Nimrod Sarid +6Geometry-Conditioned Image Generation T2I Generation
BRIA AI
ConceptPrism: Concept Disentanglement in Personalized Diffusion Models via Residual Token Optimization
Feb 23, 2026Minseo Kim, Minchan Kwon, Dongyeun Lee +2T2I Generation Subject-Driven Image Generation
KAIST, South Korea · Hanbat National University, South Korea
SCHEMA for Gemini 3 Pro Image: A Structured Methodology for Controlled AI Image Generation on Google's Native Multimodal Model
Feb 21, 2026Luca CazzanigaPrompt Optimization for T2I Generation Controllable Image Generation
Independent Researcher — AI-Assisted Visual Production
Multi-Level Conditioning by Pairing Localized Text and Sketch for Fashion Image Generation
Feb 20, 2026Ziyue Liu, Davide Talon, Federico Girella +5Image Generation Conditional Image Generation
University of Verona, 37129 Verona, Italy · Polytechnic Institute of Turin, 10129 Turin, Italy · Fondazione Bruno Kessler, 38123 Povo, Italy +1
FIGURA: A Modular Prompt Engineering Method for Artistic Figure Photography in Safety-Filtered Text-to-Image Models
Feb 20, 2026Luca CazzanigaPrompt Optimization for T2I Generation T2I Generation
Independent Researcher, Monza, Italy
Morphological Addressing of Identity Basins in Text-to-Image Diffusion Models
Feb 20, 2026Andrew FraserT2I Generation T2I Diffusion Models
GASS: Geometry-Aware Spherical Sampling for Disentangled Diversity Enhancement in Text-to-Image Generation
Feb 19, 2026Ye Zhu, Kaleb S. Newman, Johannes F. Lutzeyer +3T2I Generation T2I Diffusion Models
Laboratoire d’Informatique (LIX), CNRS, École Polytechnique, IPP, France · Department of Computer Science, Princeton University, USA · FAIR at Meta - Montreal, Canada +3
Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design
Feb 4, 2026Jaemoo Choi, Yuchen Zhu, Wei Guo +6T2I Generation Diffusion Model Fine-Tuning
Georgia Institute of Technology · National University of Singapore · Nanjing university.
Uni-RS: A Spatially Faithful Unified Understanding and Generation Model for Remote Sensing
Jan 25, 2026Weiyu Zhang, Yuan Hu, Yong Li +1Unified Multimodal Models Multimodal Generation
Institute of Remote Sensing and Geographic Information System, School of Earth and Space Sciences, Peking University, Beijing, 100871, China · Department of Civil and Environmental Engineering, The Hong Kong University of Science and Technology, Hong Kong
Unified Text-Image Generation with Weakness-Targeted Post-Training
Jan 7, 2026Jiahui Chen, Philippe Hansen-Estruch, Xiaochuang Han +7Unified Multimodal Models T2I Generation
FAIR at Meta · University of Texas, Austin · Work done at Meta +2
GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models
Dec 17, 2025Bozhou Li, Sihan Yang, Yushuo Guan +6Text Embedding Evaluation T2I Generation
Peking University · Kling Team, Kuaishou Technology · Xi’an Jiaotong University +1
Dynamic Image Prompt Adapter for Scalable Zero-shot Personalized Text-to-Image Generation
Dec 10, 2025Zhizhong Wang, Tianyi Chu, Zeyi Huang +2Subject-Driven Image Generation T2I Generation
Central Media Technology Institute, Huawei
Anchor to Expand: Semantic Anchoring for Personalized Text-to-Image Diffusion Models
Nov 27, 2025Seoyun Yang, Gihoon Kim, Taesup KimSubject-Driven Image Generation T2I Generation
Graduate School of Data Science, Seoul National University
RubricRL: Simple Generalizable Rewards for Text-to-Image Generation
Nov 25, 2025Xuelu Feng, Yunsheng Li, Ziyu Wan +4Reward Modeling T2I Generation
University at Buffalo · Microsoft AI · Nikola Tesla STEM High School
Diversifying Long Prompt Image Generation through Structured Prompt Embedding Space Sampling
Nov 25, 2025Bo-Kai Ruan, Teng-Fang Hsiao, Ling Lo +2T2I Generation Diffusion Models
Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan · Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan
TPSO: Training-Free Diverse Image Generation via Semantic Prompt Embedding Optimization
Nov 25, 2025Debin Meng, Chen Jin, Zheng Gao +3T2I Generation T2I Diffusion Models
Queen Mary University of London · Centre for AI, AstraZeneca, UK · University of Bedfordshire +1
Inference-Time Optimization of Prompt Embeddings in Diffusion Models: A Comparison of sep-CMA-ES and Adam
Nov 5, 2025Domício Pereira Neto, João Correia, Penousal MachadoT2I Generation Diffusion Models
University of Coimbra Coimbra, Portugal
SELECT: Semantic Erasure Boundary Construction with Sibling Exclusive Counterfactuals
Oct 18, 2025Tong Zhang, Ru Zhang, Jianyi Liu +1Concept Erasure T2I Generation
Beijing University of Posts and Telecommunications, School of Cyberspace Security, Beijing, 100876
SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models
Oct 14, 2025Weiyang Jin, Yuwei Niu, Jiaqi Liao +4Unified Multimodal Models T2I Generation
HKU MMLab · The University of Hong Kong · Shenzhen Loop Area Institute +2
Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models
Sep 29, 2025Shuchen Xue, Chongjian Ge, Shilong Zhang +2Score Matching Diffusion Model Alignment
UCAS · Adobe Research · HKU +1
Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance
Sep 28, 2025Ky Dan Nguyen, Hoang Lam Tran, Anh-Dung Dinh +4Visual Autoregressive Models Conditional Image Generation
The University of Sydney, Sydney, New South Wales, Australia · The University of Western Australia, Perth, Western Australia, Australia
Test-time Prompt Refinement for Text-to-Image Models
Jul 22, 2025Mohammad Abdul Hafeez Khan, Yash Jain, Siddhartha Bhattacharyya +1Text-Image Alignment T2I Generation
Florida Institute of Technology, USA · Microsoft Research, USA
AI's Blind Spots: Geographic Knowledge and Diversity Deficit in Generated Urban Scenario
Jun 20, 2025Ciro Beneduce, Massimiliano Luca, Bruno LepriT2I Generation T2I Generation Evaluation
* Bruno Kessler Foundation · **University of Trento
Mitigating Task Objective Conflicts for Continual Learning in Unified Multimodal Models
Jun 4, 2025Jiaxing Zhang, Hao TangTask Interference Unified Multimodal Models
Sichuan University, Chengdu, China · Peking University, Beijing, China
ISAC: Training-Free Instance-to-Semantic Attention Control for Multi-Instance Generation
May 27, 2025Sanghyun Jo, Wooyeol Lee, Ziseok Lee +3Controllable Image Generation T2I Generation
OGQ, Seoul, Korea · Seoul National University, Seoul, Korea
WorldGenBench: A World-Knowledge-Integrated Benchmark for Reasoning-Driven Text-to-Image Generation
May 2, 2025Ruoshi Xu, Daoan Zhang, Che Jiang +7T2I Generation T2I Generation Evaluation
Southern University of Science and Technology · University of Rochester · New York University +2
PixelPonder: Dynamic Patch Adaptation for Enhanced Multi-Conditional Text-to-Image Generation
Mar 9, 2025Yanjie Pan, Qingdong He, Zhengkai Jiang +9T2I Generation Controllable Image Generation
Fudan University · Tencent Youtu Lab · Western University +1
PersGuard: Preventing Malicious Personalization in Text-to-Image Diffusion Models via Model Backdoors
Feb 22, 2025Xinwei Liu, Xiaojun Jia, Yuan Xun +2T2I Generation T2I Diffusion Models
Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing 100049, China · BraneMatrix AI, Shanghai 201203, China +1
Comprehensive Assessment and Analysis for NSFW Content Erasure in Text-to-Image Diffusion Models
Feb 18, 2025Die Chen, Zhiwen Li, Cen Chen +5T2I Generation Concept Erasure
East China Normal University

Feb 24, 2026J/K move · Enter open · S save

CleanStyle: Plug-and-Play Style Conditioning Purification for Text-to-Image Stylization

Xiaoman Feng, Mingkun Lei, Yang Wang, Dingwen Fu+1

AGI Lab, Westlake University

Image Style Transfer T2I Diffusion Models T2I Generation Diffusion Model Guidance

Open paper AskPDF arXiv

Style transfer in diffusion models enables controllable visual generation by injecting the style of a reference image. However, recent encoder-based methods, while efficient and tuning-free, often suffer from content leakage, where semantic elements from the style image undesirably appear in the output, impairing prompt fidelity and stylistic consistency. In this work, we introduce CleanStyle, a plug-and-play framework that filters out content-related noise from the style embedding without retraining. Motivated by empirical analysis, we observe that such leakage predominantly stems from the tail components of the style embedding, which are isolated via Singular Value Decomposition (SVD). To address this, we propose CleanStyleSVD (CS-SVD), which dynamically suppresses tail components using a time-aware exponential schedule, providing clean, style-preserving conditional embeddings throughout the denoising process. Furthermore, we present Style-Specific Classifier-Free Guidance (SS-CFG), which reuses the suppressed tail components to construct style-aware unconditional inputs. Unlike conventional methods that use generic negative embeddings (e.g., zero vectors), SS-CFG introduces targeted negative signals that reflect style-specific but prompt-irrelevant visual elements. This enables the model to effectively suppress these distracting patterns during generation, thereby improving prompt fidelity and enhancing the overall visual quality of stylized outputs. Our approach is lightweight, interpretable, and can be seamlessly integrated into existing encoder-based diffusion models without retraining. Extensive experiments demonstrate that CleanStyle substantially reduces content leakage, improves stylization quality and improves prompt alignment across a wide range of style references and prompts.