Diffusion-Based Image Generation

Ask about this topic

Overview

Diffusion models learn to turn noise into images through a sequence of denoising steps, often guided by text, labels, sketches, layouts, or reference images. Work spans pixel-space and latent-space models, U-Net and Transformer architectures, and related flow-matching methods, with efforts to improve training objectives, representations, and controllability. Researchers evaluate quality and prompt or spatial alignment on benchmarks such as ImageNet and COCO, and apply the models to editing, medical imaging, remote sensing, and synthetic data generation. A central challenge is balancing image quality, diversity, precise control, and reliability against the computation required for training and sampling; synthetic images also need validation for downstream usefulness and safety.

Latest papers

CardsList

328 papers46 papers in the last four weeks, up 171% 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. ALADDIN: Adversarial Latent Diffusion Distillation for One-Step Identity Swapping

    Oct 27, 2026Ivan Shchekotov, Timofei Gritsaev, Viacheslav Pirogov +1Image GenerationDiffusion Model Distillation

    Constructor University, Bremen, Germany · Sumsub, Berlin, Germany

  3. VaLoP: Value Gradient Lookahead and Pullback for Reward-Guided Diffusion

    Oct 26, 2026Kwanyoung KimDiffusion Model GuidanceDiffusion Guidance

  4. UltraFlash: Accelerating Megapixel Visual Synthesis

    Oct 24, 2026Phuc Lai, Anh Nguyen, Phong Nguyen +1Diffusion Model Inference AccelerationDiffusion-Based Image Generation

    Qualcomm AI Research†

  5. Rethinking Microscopy Generation: Co-Designed Diffusion for Biologically Interpretable Single-Cell Synthesis

    Oct 24, 2026Shumpei Takezaki, Duway Nicolas Lesmes-Leon, Ryoma Bise +4Image GenerationControllable Image Generation

    Kyushu University, Fukuoka, Japan · University of Kaiserslautern-Landau (RPTU), Kaiserslautern, Germany · German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany +1

  6. Fast and Useful: Adapting Distilled Generators for Visual Learning

    Oct 23, 2026Patryk Bartkowiak, Dominik Michels, Sören Pirk +1Diffusion Model AdaptationSynthetic Data Augmentation

    Adam Mickiewicz University · GreenMatterAI · KAUST +1

  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. Squaring-the-Sphere: Distortion-Free and Seamless Panorama Generation via CubeAtlas

    Oct 22, 2026Xuhui Zuo, Chenjie Cao, Tengfei Wang +3Image GenerationDiffusion-Based Image Generation

    Tencent

  9. AdvFidelity: Unifying Preference Alignment and Few-Step Image Generation within Reinforcement Learning

    Oct 21, 2026Sicong Kang, Fangao Zeng, Yuhan Li +6RL for Image GenerationDiffusion-Based Image Generation

    Taobao & Tmall group of Alibaba · Shanghai Jiao Tong University

  10. DualHeads: Reward-tilted few-step diffusion made simple

    Oct 20, 2026Yuanzhi Zhu, Eleftherios Tsonis, Simo Alami Chehboune +3Diffusion-Based Image GenerationDiffusion Model Fine-Tuning

    LIX, École Polytechnique, CNRS, IPP · Inria at Univ. Grenoble Alpes, CNRS, LJK

  11. MoDDiT: Simple Token Routing in Diffusion Transformers

    Oct 20, 2026Jarek Liesen, Matthew T. Jackson, Benjamin Ellis +2Diffusion TransformerAdaptive Computation for Diffusion Models

    British Open-ended Learning and Discovery

  12. Dancing Diffusion: Learning Continuous Programs for Image Generation and Editing

    Oct 20, 2026Cui Enhe, Jinyue Yang, Bojian Yin +1Diffusion-Based Image GenerationDiffusion-Based Image Editing

    Renmin University of China · Institute of Automation, Chinese Academy of Sciences

  13. RoAR-VAE: Improving Latent Diffusability through Robust Prediction

    Oct 19, 2026Yang Yue, Fangyun Wei, Yitong Wang +4Image TokenizationVariational Autoencoders

    Tsinghua University · Microsoft Research

  14. Rethinking the design space of Vanilla Pixel Diffusion Transformers

    Oct 16, 2026Soumik Mukhopadhyay, Long Mai, Abhinav Shrivastava +1Diffusion-Based Image GenerationDiffusion Models

    University of Maryland, College Park · Adobe Research

  15. SCALE: Improving Guidance-Free Visual Generation via Self-Contrastive Alignment for Likelihood Estimation

    Oct 16, 2026Jiwan Hur, Dong-Jae Lee, Dongyeun Lee +2Image GenerationDiffusion Model Guidance

    KAIST, South Korea

  16. Learning to Be Guided: Shaping Latent Geometry for Classifier-Free Guidance

    Oct 16, 2026Haoming Liu, Junhao Zhu, Shaoyi Zheng +4Latent Space GeometryDiffusion-Based Image Generation

    New York University · New York University Shanghai · Georgia Institute of Technology

  17. ManiFusion: Unlocking the High-Throughput Generation via Superposition in Manifold Space

    Oct 15, 2026Minkyu Kim, Baekseung Kim, Junhoo Lee +2Diffusion Model Inference AccelerationDiffusion-Based Image Generation

    Seoul National University · Kookmin University

  18. Intern Lumina U2: A Multi-Codebook Diffusion Large Language Model for Omni-Visual Understanding and Image Generation

    Oct 14, 2026Qian Yu, Zongyang Qiu, Juncheng Yan +40Unified Multimodal ModelsDiffusion Language Models

  19. Purify Before You Align: Improving Representation Alignment for Diffusion Models

    Oct 14, 2026Yingheng Wang, Yaoqiang Li, Yaqin Wu +4Diffusion Model AlignmentDiffusion-Based Image Generation

    Cornell University · Independent researcher. · University of Pennsylvania

  20. Representation Conditioning for Generation

    Oct 14, 2026Saeed Razavi, Xingjian Leng, Liang ZhengDiffusion-Based Image GenerationDiffusion Transformer

    Australian National University

  21. Generative Representation Learning for Scalable Latent Tokenization

    Oct 14, 2026Alan Baade, Kyle Sargent, Vincent Sitzmann +4Representation LearningImage Tokenization

    Stanford University · Massachusetts Institute of Technology · University of Michigan

  22. No Way To Steal My Face: Proactive Defense Against Identity-Preserving Personalized Generation

    Oct 14, 2026Lizhi Xiong, Jun Li, Ziqiang Li +2Identity-Preserving Image GenerationDiffusion-Based Image Generation

    Nanjing University of Information Science and Technology

  23. PixelMoE: Scaling Pixel-Space Diffusion with LLM-Style Mixture-of-Experts

    Oct 13, 2026Ruixiao Dong, Jianmin Bao, Bozhi Luan +6Diffusion-Based Image GenerationPixel-Space Diffusion Models

    University of Science and Technology of China · KlingAI Research · Peking University

  24. LayerCanvas: Infographic Generation in AI Learning Assistants via Hybrid Layer-Set Diffusion

    Oct 13, 2026Keshav Gupta, Jeremy Owen, Christopher Lloyd +2Vector Graphics GenerationDiffusion-Based Image Generation

    University of California, San Diego · LinkedIn Inc.

  25. Omni-RS: Unifying Multi-Task Understanding and Generation in Remote Sensing

    Oct 13, 2026Pan Yin, Shuai Yang, Yuanhao Liu +7Image GenerationUnified Multimodal Models

    Xi’an Jiaotong University

  26. LoopREG: Representation Supervision Enables Test-Time Recurrent Depth in Diffusion Transformers

    Oct 13, 2026Zipeng Wang, Anping Xiong, Jing Zhang +17Diffusion-Based Image GenerationDiffusion Transformer

    Chongqing University of Posts and Telecommunications · China United Network Communications Group Co., Ltd. · University of Electronic Science and Technology of China +1

  27. AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers

    Oct 12, 2026Javad Rajabi, Koorosh Roohi, David B. Lindell +1Diffusion TransformerDiffusion-Based Image Generation

    University of Toronto · Vector Institute

  28. Image Tokenizers Should Be Trained Between Images

    Oct 12, 2026Ole Beißwenger, Jan-Niklas Dihlmann, Hendrik LenschImage TokenizationLatent Diffusion Models

    University of Tübingen

  29. Tikhonov-Stabilized Bezier Representation Forecasting for Training-free Diffusion Acceleration

    Oct 12, 2026Lei Zhu, Mujie Lin, Ruochong Zheng +5Diffusion Model Inference AccelerationDiffusion Model Caching

    School of Electronic and Computer Engineering, Peking University · School of Informatics, Xiamen University · Department of Automation and BNRist, Tsinghua University

  30. Regime-Aware Router Learning for Multi-Domain Medical Image Generation with Diffusion Experts

    Oct 12, 2026Yaoshuai Ma, Wei Yao, Yongxiang Liu +5Expert RoutingDiffusion-Based Image Generation

    Peng Cheng Laboratory, Shenzhen, China · Southern University of Science and Technology, Shenzhen, China