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. When Generative Augmentation Hurts: A Benchmark Study of GAN and Diffusion Models for Bias Correction in AI Classification Systems

    Mar 17, 2026Shesh Narayan Gupta, Nik Bear BrownSynthetic Data AugmentationClass-Imbalanced Learning

    College of Engineering, Northeastern University, Boston, MA 02115, USA

  2. Learning Latent Proxies for Controllable Single-Image Relighting

    Mar 16, 2026Haoze Zheng, Zihao Wang, Xianfeng Wu +5Physics-Informed Diffusion ModelsControllable Image Generation

    HKUST · HKPolyU · CUHK

  3. RSGen: Enhancing Layout-Driven Remote Sensing Image Generation with Diverse Edge Guidance

    Mar 16, 2026Xianbao Hou, Yonghao He, Zeyd Boukhers +4Image GenerationControllable Image Generation

    School of Future Science and Engineering, Soochow University, Suzhou, China · D-Robotics, Beijing, China · Fraunhofer Institute for Applied Information Technology, Sankt Augustin, Germany +2

  4. WiT: Waypoint Diffusion Transformers for Alleviating Trajectory Conflict in Pixel-Space Image Generation

    Mar 16, 2026Hainuo Wang, Mingjia Li, Xiaojie GuoFlow MatchingDiffusion Transformer

    College of Intelligence and Computing, Tianjin University, Tianjin 300350, China

  5. AnyPhoto: Multi-Person Identity Preserving Image Generation with ID Adaptive Modulation on Location Canvas

    Mar 16, 2026Longhui YuanIdentity-Preserving Image GenerationControllable Image Generation

  6. PHAC: Promptable Human Amodal Completion

    Mar 16, 2026Seung Young Noh, Ju Yong ChangControllable Image GenerationDiffusion-Based Image Generation

    Kwangwoon University

  7. Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusion

    Mar 15, 2026Mang Ning, Mingxiao Li, Le Zhang +4Latent Diffusion ModelsDiffusion-Based Image Generation

    Utrecht University · KU Leuven · Mila +1

  8. ChArtist: Generating Pictorial Charts with Unified Spatial and Subject Control

    Mar 15, 2026Shishi Xiao, Tongyu Zhou, David Laidlaw +1Controllable Image GenerationData Visualization

    Brown University · Adobe Research

  9. Sat-JEPA-Diff: Bridging Self-Supervised Learning and Generative Diffusion for Remote Sensing

    Mar 14, 2026Kursat Komurcu, Linas PetkeviciusSpatiotemporal ForecastingDiffusion-Based Image Generation

    Vilnius University, Faculty of Mathematics and Informatics, Institute of Computer Science, Artificial Intelligence Methods Lab, Vilnius, LT-03225, Lithuania

  10. One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformers

    Mar 12, 2026Moayed Haji-Ali, Willi Menapace, Ivan Skorokhodov +6Adaptive Computation for Diffusion ModelsDiffusion Transformer

    Rice University · Snap Inc.

  11. DyWeight: Dynamic Gradient Weighting for Few-Step Diffusion Sampling

    Mar 12, 2026Tong Zhao, Mingkun Lei, Liangyu Yuan +5Diffusion SamplingFew-Step Diffusion Sampling

    Zhejiang University · AGI Lab, Westlake University · TongJi University +1

  12. SERUM: Simple, Efficient, Robust, and Unifying Marking for Diffusion-based Image Generation

    Mar 11, 2026Jan Kociszewski, Hubert Jastrzębski, Tymoteusz Stępkowski +4Diffusion Model WatermarkingAI-Generated Image Watermarking

    CISPA Helmholtz Center for Information Security

  13. High-Fidelity Text-to-Image Generation from Pre-Trained Vision-Language Models via Distribution-Conditioned Diffusion Decoding

    Mar 11, 2026Ji Woo Hong, Hee Suk Yoon, Gwanhyeong Koo +5T2I GenerationDiffusion-Based Image Generation

    Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea · Microsoft Research Asia (MSRA), Beijing, China

  14. BridgeDiff: Bridging Human Observations and Flat-Garment Synthesis for Virtual Try-Off

    Mar 10, 2026Shuang Liu, Ao Yu, Linkang Cheng +5Virtual Try-OnConditional Image Generation

    School of Integrated Circuits, Anhui University, Hefei, China · School of Astronautics, Northwestern Polytechnical University, Xi’an,China · Anhui Provincial High-performance Integrated Circuit Engineering Research Center

  15. Retrieval-Augmented Anatomical Guidance for Text-to-CT Generation

    Mar 9, 2026Daniele Molino, Camillo Maria Caruso, Paolo Soda +1Medical Image SynthesisComputed Tomography

    Unit of Artificial Intelligence and Computer Systems, Department of Engineering, Università Campus Bio-Medico di Roma, Rome, Italy · Department of Diagnostics and Intervention, Biomedical Engineering and Radiation Physics, Umeå University, Umeå, Sweden

  16. CONSTANT: Towards High-Quality One-Shot Handwriting Generation with Patch Contrastive Enhancement and Style-Aware Quantization

    Mar 8, 2026Anh-Duy Le, Van-Linh Pham, Thanh-Nam Vo +2Image GenerationDiffusion-Based Image Generation

    Viettel Artificial Intelligence and Data Services Center, Vietnam · Ho Chi Minh City University of Technology, Vietnam

  17. Image Generation Models: A Technical History

    Mar 8, 2026Rouzbeh ShirvaniImage GenerationDiffusion-Based Image Generation

  18. SODA: Sensitivity-Oriented Dynamic Acceleration for Diffusion Transformer

    Mar 7, 2026Tong Shao, Yusen Fu, Guoying Sun +3Diffusion Model Inference AccelerationDiffusion-Based Image Generation

    Harbin Institute of Technology, Shenzhen

  19. Pinterest Canvas: Large-Scale Image Generation at Pinterest

    Mar 6, 2026Yu Wang, Eric Tzeng, Raymond Shiau +3Image GenerationDiffusion-Based Image Editing

    Pinterest, Inc. San Francisco, CA, USA

  20. DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking

    Mar 6, 2026Akash Haridas, Utkarsh Saxena, Parsa Ashrafi Fashi +3Adaptive TokenizationDiffusion Transformer

    Advanced Micro Devices Inc. (AMD)

  21. Cross-Resolution Distribution Matching for Diffusion Distillation

    Mar 6, 2026Feiyang Chen, Hongpeng Pan, Haonan Xu +3Video Diffusion ModelsDiffusion Model Distillation

    Huawei, Shanghai & Hangzhou, China · Nanjing University of Science and Technology, Nanjing, China

  22. Diffusion-Based sRGB Real Noise Generation via Prompt-Driven Noise Representation Learning

    Mar 5, 2026Jaekyun Ko, Dongjin Kim, Soomin Lee +2Synthetic Data GenerationDiffusion-Based Image Generation

    Department of Computer Science, Hanyang University · Mobile Experience (MX) Division, Samsung Electronics · Department of Computer Science, Toronto Metropolitan University

  23. LAW & ORDER: Adaptive Spatial Weighting for Medical Diffusion and Segmentation

    Mar 5, 2026Anugunj Naman, Ayushman Singh, Gaibo Zhang +1Image SegmentationHealthcare

    Elmore Family School of Electrical and Computer Engineering Purdue University, West Lafayette, USA · Sesame AI, New York, USA · Department of Computer Science Purdue University, West Lafayette, USA +1

  24. DiverseDiT: Towards Diverse Representation Learning in Diffusion Transformers

    Mar 4, 2026Mengping Yang, Zhiyu Tan, Binglei Li +3Diffusion TransformerDiffusion Models

    Fudan University · Shanghai Academy of AI for Science · Shanghai Innovation Institute

  25. AWDiff: An a trous wavelet diffusion model for lung ultrasound image synthesis

    Mar 3, 2026Maryam Heidari, Nantheera Anantrasirichai, Steven Walker +2Medical Image SynthesisSynthetic Data Augmentation

    University of Bristol, UK · Visual Information Lab, University of Bristol, Bristol, UK · Bristol Medical School, University of Bristol, UK +1

  26. MultiShadow: Multi-Object Shadow Generation for Image Compositing via Diffusion Model

    Mar 3, 2026Waqas Ahmed, Dean Diepeveen, Ferdous SohelImage EditingDiffusion-Based Image Generation

    School of Information Technology, Murdoch University, Murdoch, WA 6150, Australia.

  27. Spectral Regularization for Diffusion Models

    Mar 2, 2026Satish Chandran, Nicolas Roque dos Santos, Yunshu Wu +2Diffusion ModelsSpectral Regularization

    Department of Mathematics, University of California Riverside, Riverside, California, USA · Department of Computer Science, University of California Riverside, Riverside, California, USA

  28. A Diffusion-Driven Fine-Grained Nodule Synthesis Framework for Enhanced Lung Nodule Detection from Chest Radiographs

    Mar 2, 2026Aryan Goyal, Shreshtha Singh, Ashish Mittal +3Lung Nodule DetectionSynthetic Data Augmentation

    Qure.ai, India · Indian Institute of Technology, Bombay

  29. Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration

    Mar 2, 2026Jiaqi Han, Juntong Shi, Puheng Li +3Video Diffusion ModelsDiffusion-Based Image Generation

    Stanford University · ByteDance

  30. Ordinal Diffusion Models for Color Fundus Images

    Feb 27, 2026Gustav Schmidt, Philipp Berens, Sarah MüllerDiffusion-Based Image GenerationDiffusion Models

    Hertie Institute for AI in Brain Health, University of Tübingen, Germany