mlsanityData to 7 Oct 2026

Towards Memorization-Free Diffusion Models

arXiv 2404.00922 ↗First posted 1 Apr 2024cs.CVcited by 49

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Pretrained diffusion models and their outputs are widely accessible due to their exceptional capacity for synthesizing high-quality images and their open-source nature. The users, however, may face litigation risks owing to the models' tendency to memorize and regurgitate training data during inference. To address this, we introduce Anti-Memorization Guidance (AMG), a novel framework employing three targeted guidance strategies for the main causes of memorization: image and caption duplication, and highly specific user prompts. Consequently, AMG ensures memorization-free outputs while maintaining high image quality and text alignment, leveraging the synergy of its guidance methods, each indispensable in its own right. AMG also features an innovative automatic detection system for potential memorization during each step of inference process, allows selective application of guidance strategies, minimally interfering with the original sampling process to preserve output utility. We applied AMG to pretrained Denoising Diffusion Probabilistic Models (DDPM) and Stable Diffusion across various generation tasks. The results demonstrate that AMG is the first approach to successfully eradicates all instances of memorization with no or marginal impacts on image quality and text-alignment, as evidenced by FID and CLIP scores.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 30 of its 39 references that are in the map. First posted on arXiv 1 Apr 2024.

Builds on

30 of 39 references.

Closest ancestors · 8

Same direction, newest first

  1. 2023Understanding and Mitigating Copying in Diffusion Models31 May
  2. 2022Classifier-Free Diffusion Guidance26 Jul
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  4. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  5. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  7. 2020Denoising Diffusion Implicit Models6 Oct
  8. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 22

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  7. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  8. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  9. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  10. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  11. 2016Deep Learning with Differential Privacycited by 2,682
  12. 2015Variational Inference with Normalizing Flowscited by 2,161
10 more
  1. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  2. 2023Extracting Training Data from Diffusion Modelscited by 723
  3. 2021Deduplicating Training Data Makes Language Models Bettercited by 705
  4. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 418
  5. 2023Ablating Concepts in Text-to-Image Diffusion Modelscited by 312
  6. 2022Deduplicating Training Data Mitigates Privacy Risks in Language Modelscited by 309
  7. 2018Differentially Private Generative Adversarial Networkcited by 235
  8. 2022A Self-Supervised Descriptor for Image Copy Detectioncited by 175
  9. 2022Differentially Private Diffusion Modelscited by 118
  10. 2022Dataset Distillation via Factorizationcited by 115

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 16; 2025: 23; 2026: 10.

49 papers.

Sort:

By area:

  1. 2025Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in Trainingcited by 78
  2. 2024A Geometric Framework for Understanding Memorization in Generative Modelscited by 40
  3. 2024Dynamic Negative Guidance of Diffusion Modelscited by 28
  4. 2025Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Modelscited by 24
  5. 2024Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellencycited by 21
  6. 2024Classifier-Free Guidance inside the Attraction Basin May Cause Memorizationcited by 21
  7. 2024Exploring Local Memorization in Diffusion Models via Bright Ending Attentioncited by 19
  8. 2025Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusioncited by 17
  9. 2024Memorized Images in Diffusion Models share a Subspace that can be Located and Deletedcited by 13
  10. 2024Replication in Visual Diffusion Models: A Survey and Outlookcited by 11
  11. 2025Generalization of Diffusion Models Arises with a Balanced Representation Spacecited by 10
  12. 2025A Comprehensive Survey on Concept Erasure in Text-to-Image Diffusion Modelscited by 9
37 more
  1. 2025Demystifying Diffusion Policies: Action Memorization and Simple Lookup Table Alternativescited by 9
  2. 2024SIDE: Surrogate Conditional Data Extraction from Diffusion Modelscited by 7
  3. 2024Understanding and Mitigating Memorization in Diffusion Models for Tabular Datacited by 7
  4. 2025Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Modelscited by 7
  5. 2024An Inversion-based Measure of Memorization for Diffusion Modelscited by 6
  6. 2024Investigating Memorization in Video Diffusion Modelscited by 5
  7. 2024CopyrightShield: Enhancing Diffusion Model Security against Copyright Infringement Attackscited by 5
  8. 2025Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Modelscited by 5
  9. 2025Diffusion models under low-noise regimecited by 5
  10. 2025Deeper Diffusion Models Amplify Biascited by 4
  11. 2024CPSample: Classifier Protected Sampling for Guarding Training Data During Diffusioncited by 3
  12. 2024Dual-Model Defense: Safeguarding Diffusion Models from Membership Inference Attacks through Disjoint Data Splittingcited by 3
  13. 2025Generative AI Training and Copyright Lawcited by 3
  14. 2025SolidMark: Evaluating Image Memorization in Generative Modelscited by 3
  15. 2025Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Studycited by 3
  16. 2025Mitigating data replication in text-to-audio generative diffusion models through anti-memorization guidancecited by 2
  17. 2025A Novel Metric for Detecting Memorization in Generative Models for Brain MRI Synthesiscited by 2
  18. 2026Detecting and Mitigating Memorization in Diffusion Models through Anisotropy of the Log-Probabilitycited by 2
  19. 2024LoyalDiffusion: A Diffusion Model Guarding Against Data Replicationcited by 1
  20. 2025A Closer Look on Memorization in Tabular Diffusion Model: A Data-Centric Perspectivecited by 1
  21. 2026Memorization Control in Diffusion Models from Denoising-centric Perspectivecited by 1
  22. 2026Reducing Memorisation in Generative Models via Riemannian Bayesian Inferencecited by 1
  23. 2026Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformerscited by 1
  24. 2026Progressive Representation Learning for Multimodal Sentiment Analysis with Incomplete Modalitiescited by 1
  25. 2026Towards More General Control of Diffusion Models Using Jeffrey Guidancecited by 1
  26. 2024Opt-In Art: Learning Art Styles Only from Few Examplescited by 0
  27. 2025Redistribute Ensemble Training for Mitigating Memorization in Diffusion Modelscited by 0
  28. 2025GenEAva: Generating Cartoon Avatars with Fine-Grained Facial Expressions from Realistic Diffusion-based Facescited by 0
  29. 2025FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddingscited by 0
  30. 2025Towards Application Aligned Synthetic Surgical Image Synthesiscited by 0
  31. 2025CAPTAIN: Semantic Feature Injection for Memorization Mitigation in Text-to-Image Diffusion Modelscited by 0
  32. 2025Beyond Memorization: Selective Learning for Copyright-Safe Diffusion Model Trainingcited by 0
  33. 2025One-shot synthesis of rare gastrointestinal lesions improves diagnostic accuracy and clinical trainingcited by 0
  34. 2026Memorization In Stable Diffusion Is Unexpectedly Driven by CLIP Embeddingscited by 0
  35. 2026Filtering Memorization from Parameter-Space in Diffusion Modelscited by 0
  36. 2026Adynamical systems view of training generativemodels and the memorization phenomenoncited by 0
  37. 2026Rethinking Memorization Mitigation in Diffusion Models: Reinforcing Text Conditioningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Detecting, Explaining, and Mitigating Memorization in Diffusion Models
  2. 2025How Diffusion Models Memorize
  3. 2024MemControl: Mitigating Memorization in Diffusion Models via Automated Parameter Selection
  4. 2023Semantic Guidance Tuning for Text-To-Image Diffusion Models
  5. 2026Revisiting Classifier-Free Guidance Methods in Latent Diffusion Models
  6. 2026Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Image Diffusion
  7. 2024Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention
  8. 2025Finding DoRI: Discovery of Retained Images in Diffusion Models