T2I Generation

T2I: Text-to-Image

Ask about this topic

Overview

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

CardsList

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

  1. Know, then Draw: A New Learning Paradigm for Visual Generation

    Oct 27, 2026Yucheng Mao, Chongjian Ge, Zhuowen Tu +2T2I GenerationT2I Diffusion Models

    University of California, San Diego · Adobe Research

  2. A First-Step Bias Restores Lost Diversity in Diffusion Model Distillation

    Oct 27, 2026Wenwu Tang, Dong Wang, Yun Cheng +1Diffusion Model DistillationDiffusion Models

    Graz University of Technology · Swiss Data Science Center, Switzerland · Complexity Science Hub, Austria

  3. Haste Makes Waste? Towards Safe Few-Step Text-to-Image Models

    Oct 27, 2026Lior Ziv, Mahmood SharifT2I GenerationSafe T2I Generation

    Tel Aviv University

  4. From Structural Feedback to Prompt Policies: Learning Faithful Text-to-Image Prompt Editors

    Oct 26, 2026Wentao Ye, Yali Ye, Zhiqing Xiao +7Prompt Optimization for T2I GenerationT2I Generation

    Zhejiang University · Tencent AI Lab · China Telecom Artificial Intelligence (Beijing) Co. Ltd

  5. HobbyLM: A Sparse Mixture-of-Experts Model Family on a Hobby Budget

    Oct 25, 2026Harish Santhanalakshmi Ganesan, Hariharan M. S., Prabhurajhan RMixture-of-Experts Language ModelsEfficient Language Model Training

  6. TIE: Training-free CLIP Embedding Guidance for Compositional Text-to-Image Alignment

    Oct 23, 2026Sujung Hong, Tae Eun Choi, Youngjun Jun +2T2I GenerationCompositional T2I Generation

    Yonsei University

  7. PASTA: Prompt-Aware Annealed Diffusion Sampling

    Oct 23, 2026Ren Ajiki, Ryugo Morita, Stanislav Frolov +5T2I GenerationDiffusion-Based Image Generation

    Faculty of Science and Engineering, Hosei University, Tokyo, Japan · RPTU Kaiserslautern-Landau & DFKI GmbH, Kaiserslautern, Germany

  8. T-DIG: Text-Conditioned Diversity for Image Generation

    Oct 21, 2026Simran Khanuja, Rohit Gandikota, Gaurav Parmar +1T2I GenerationControllable Image Generation

    Carnegie Mellon University · Northeastern University

  9. PRIMFLOW: Learning Trajectory Primitives for Few-Step Distillation

    Oct 19, 2026Hongyi Fang, Benjia ZhouDiffusion Model DistillationFew-Step Diffusion Sampling

    Beijing Institute of Technology, Zhuhai, China

  10. Text-to-Image Generative Modeling Without Language Pretraining

    Oct 19, 2026Keshigeyan Chandrasegaran, Yue Zhao, Armin W. Thomas +5T2I GenerationAutoregressive Image Generation

    Stanford University · Radical Numerics

  11. Negation without Confusion: Decomposing Bias and Recomposing Style in Text Embeddings for Negation-aware Image Generation

    Oct 19, 2026Sooyeon Park, Hemraj Singh, Kyunghyun Min +2T2I GenerationT2I Diffusion Models

    ♠Yonsei University · ⋄Seoul National University

  12. Test-Time Scaling of Text-to-Image Flow Matching Models with Noise-Rejuvenated Sequential Monte Carlo

    Oct 18, 2026Wenyi Lian, Zheng Zhao, Thomas B. SchönInference-Time ScalingT2I Generation

    Department of Information Technology Uppsala University, Sweden · Department of Computer and Information Science Linköping University, Sweden

  13. Reflection-Guided Dynamics Rectification for Text-to-Image Generation

    Oct 18, 2026Shuo Xu, Hanrui Ying, Debin Liu +2T2I GenerationT2I Diffusion Models

    Huazhong University of Science and Technology · Sorbonne University · Zhengzhou University

  14. Distribution-Based Regularization for Reward Fine-Tuning Diffusion and Flow Models

    Oct 17, 2026Romeo Passaro, Jeongjae Lee, Jong Chul Ye +4Generative ModelingDiffusion Model Alignment

    University of Oxford · AITHYRA · KAIST +2

  15. LogicVal:A Logic-Formalized Benchmark for Constraint Satisfaction in Text-to-Image Generation

    Oct 16, 2026Savitha Sam Abraham, Marjan Alirezaie, Hossein RahnamaImage Generation EvaluationT2I Generation Evaluation

    City St George’s, University of London · Toronto Metropolitan University · Flybits Labs, Creative AI Hub, Toronto +1

  16. A Language-Informed Loss for Visual Generation

    Oct 16, 2026Suchir Agarwal, Keshigeyan Chandrasegaran, Ziyu Chen +4T2I GenerationVision-Language Models

    Stanford University

  17. Not Just a Subject: Capturing Adaptive Scene-Specific Variance for Visual Storytelling

    Oct 15, 2026SeungJu Cha, Ye-Chan Kim, Kwanyoung Lee +1Visual StorytellingT2I Generation

    Hanyang University, Seoul 04763, South Korea

  18. FeaTok: Feature-Loss Tokenization for Image Generation

    Oct 15, 2026Zhang Xiaofeng, Samuel Lavoie, Nicolas Beltran-Velez +6Image TokenizationImage Generation

    Mila - Québec AI Institute · Université de Montréal · FAIR at Meta +4

  19. Are We Overthinking One-Step Generation?

    Oct 14, 2026Woobin Park, Jaeyeon Kim, Yilun Du +2One-Step Generative ModelingConditional Generative Modeling

    Seoul National University · Harvard University

  20. MiniDog: Dog-Breed Text-to-image Flow Matching from Pretraining to Fine-Tuning on 4 Consumer GPUs

    Oct 13, 2026Reyhaneh Esmailizadeh, Xingjian Leng, Zhanhao Liang +1T2I GenerationT2I Diffusion Models

  21. APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation

    Oct 13, 2026Sirui Zhang, Fangyun Wei, Dong Chen +5T2I GenerationRL for Image Generation

    University of Science and Technology of China · Microsoft Research Asia · University of Sydney +2

  22. Making Language the Low-Rate Code of Vision: Successive Refinement from Words to Pixels

    Oct 12, 2026Ruilin Gong, Hao GongT2I GenerationImage Tokenization

    Henan University of Technology · University of Chinese Academy of Sciences

  23. Getting Space Right: Agentic Rewards for Image Generation

    Oct 10, 2026Xiaofeng Tan, Jiaxin Lin, Haobo Yuan +5T2I GenerationRL for Image Generation

    Southeast University · Tencent HY · UC Merced +1

  24. Japanese Handwriting Generation Based on Human Preference Feedback Using Direct Preference Optimization

    Oct 10, 2026Wakana Kuwata, Ryota Mibayashi, Masanori Tani +1T2I Generation

    University of Hyogo, Hyogo, Japan · Kobe University, Hyogo, Japan · ACADEMIC VISION LLC, Kyoto, Japan

  25. Golden Anchor for Video Generation

    Oct 9, 2026Jinyuan Xu, Shitong Shao, Lichen Bai +4Image-to-Video GenerationT2I Generation

    The Hong Kong University of Science and Technology (Guangzhou) · University of Bristol

  26. A Lightweight Velocity Correction Framework for Improving Instruction Following in Few-Step Text-to-Image Generation

    Oct 9, 2026Yating Gao, Zhenlong Zhu, Wen Zihao +6T2I GenerationCompositional T2I Generation

    The University of Osaka · Alibaba Group · Peking University +1

  27. BudgetPix: Compute-Adaptive Tokenization for Pixel-Space Image Diffusion

    Oct 8, 2026Ozgur Kara, Yujia Chen, Daniel Watson +4Image TokenizationDiffusion Model Inference Acceleration

    University of Illinois Urbana-Champaign · Google

  28. From Prompting to Composing: A Spatial Canvas Interface for Poster Generation

    Oct 8, 2026Yitong Wang, Fangyun Wei, Jinjing Zhao +5Controllable Image GenerationImage Generation

    Fudan University · Microsoft Research · The University of Sydney +3

  29. It's Always 10:10: Reference Images Break a Bias That Prompts Only Dent

    Oct 8, 2026Luca CazzanigaLayout-Guided T2I GenerationT2I Generation

    Independent Researcher, AI-Assisted Visual Production

  30. UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation

    Oct 7, 2026Deyuan Liu, Yihao Hu, Jingxuan Zhang +13Text Rendering in T2I GenerationT2I Generation Evaluation

    Westlake University · Ant Group · Zhejiang University +7