mlsanityData to 7 Oct 2026

Measuring Style Similarity in Diffusion Models

arXiv 2404.01292 ↗First posted 1 Apr 2024cs.CV cs.LGcited by 106

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

Generative models are now widely used by graphic designers and artists. Prior works have shown that these models remember and often replicate content from their training data during generation. Hence as their proliferation increases, it has become important to perform a database search to determine whether the properties of the image are attributable to specific training data, every time before a generated image is used for professional purposes. Existing tools for this purpose focus on retrieving images of similar semantic content. Meanwhile, many artists are concerned with style replication in text-to-image models. We present a framework for understanding and extracting style descriptors from images. Our framework comprises a new dataset curated using the insight that style is a subjective property of an image that captures complex yet meaningful interactions of factors including but not limited to colors, textures, shapes, etc. We also propose a method to extract style descriptors that can be used to attribute style of a generated image to the images used in the training dataset of a text-to-image model. We showcase promising results in various style retrieval tasks. We also quantitatively and qualitatively analyze style attribution and matching in the Stable Diffusion model. Code and artifacts are available at https://github.com/learn2phoenix/CSD.

Key facts. Cited by 106 papers in the map (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 36 of its 67 references that are in the map. First posted on arXiv 1 Apr 2024.

Builds on

36 of 67 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Wuerstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models1 Jun
  2. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models7 Dec

Other references · 34

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  7. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  8. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  9. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  10. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  11. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  12. 2021Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrievalcited by 1,175
22 more
  1. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 935
  2. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  3. 2015A Neural Algorithm of Artistic Stylecited by 480
  4. 2016A Learned Representation For Artistic Stylecited by 340
  5. 2023A Cookbook of Self-Supervised Learningcited by 248
  6. 2020Swapping Autoencoder for Deep Image Manipulationcited by 215
  7. 2023Understanding and Mitigating Copying in Diffusion Modelscited by 205
  8. 2015Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Featurecited by 181
  9. 2022A Self-Supervised Descriptor for Image Copy Detectioncited by 175
  10. 2017Deep Photo Style Transfercited by 168
  11. 2018How to Read Paintings: Semantic Art Understanding with Multi-Modal Retrievalcited by 73
  12. 2013Recognizing Image Stylecited by 64
  13. 2022Teaching Matters: Investigating the Role of Supervision in Vision Transformerscited by 45
  14. 2023Evaluating Data Attribution for Text-to-Image Modelscited by 45
  15. 2017BAM! The Behance Artistic Media Dataset for Recognition Beyond Photographycited by 43
  16. 2022How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularizationcited by 40
  17. 2021ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similaritycited by 34
  18. 2021Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generationcited by 30
  19. 2022Fine-Grained Image Style Transfer with Visual Transformerscited by 11
  20. 2018Unsupervised Learning of Artistic Styles with Archetypal Style Analysiscited by 10
  21. 2021Automatic analysis of artistic paintings using information-based measurescited by 4
  22. 2020Art Style Classification with Self-Trained Ensemble of AutoEncoding Transformationscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 26; 2025: 40; 2026: 40.

106 papers.

Sort:

By area:

  1. 2025DreamO: A Unified Framework for Image Customizationcited by 82
  2. 2025OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generationcited by 81
  3. 2024CSGO: Content-Style Composition in Text-to-Image Generationcited by 76
  4. 2025TIIF-Bench: How Does Your T2I Model Follow Your Instructions?cited by 64
  5. 2024ACE: All-round Creator and Editor Following Instructions via Diffusion Transformercited by 56
  6. 2024InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generationcited by 51
  7. 2024StyleMaster: Stylize Your Video with Artistic Generation and Translationcited by 47
  8. 2024RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Controlcited by 46
  9. 2024Alignment of Diffusion Models: Fundamentals, Challenges, and Futurecited by 34
  10. 2025USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learningcited by 26
  11. 2024UnZipLoRA: Separating Content and Style from a Single Imagecited by 24
  12. 2025ICE-Bench: A Unified and Comprehensive Benchmark for Image Creating and Editingcited by 23
38 more
  1. 2024DiffSim: Taming Diffusion Models for Evaluating Visual Similaritycited by 20
  2. 2025Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion Reinforcement Learningcited by 18
  3. 2024Magic Insert: Style-Aware Drag-and-Dropcited by 17
  4. 2024Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Modelscited by 15
  5. 2025CoDe: Blockwise Control for Denoising Diffusion Modelscited by 14
  6. 2025Generative Modeling of Weights: Generalization or Memorization?cited by 12
  7. 2024Replication in Visual Diffusion Models: A Survey and Outlookcited by 11
  8. 2025Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Modelscited by 11
  9. 2025Visual-Aware CoT: Achieving High-Fidelity Visual Consistency in Unified Modelscited by 10
  10. 2026MSVBench: Towards Human-Level Evaluation of Multi-Shot Video Generationcited by 10
  11. 2025EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignmentcited by 8
  12. 2026MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generationcited by 8
  13. 2024Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Modelscited by 7
  14. 2024A LoRA is Worth a Thousand Picturescited by 7
  15. 2025Safe and Reliable Diffusion Models via Subspace Projectioncited by 7
  16. 2025StyleMe3D: Stylization with Disentangled Priors by Multiple Encoders on 3D Gaussianscited by 6
  17. 2025Localizing Knowledge in Diffusion Transformerscited by 6
  18. 2025CDST: Color Disentangled Style Transfer for Universal Style Reference Customizationcited by 6
  19. 2025FreeViS: Training-free Video Stylization with Inconsistent Referencescited by 6
  20. 2026TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Expertscited by 6
  21. 2026OmniTransfer: All-in-one Framework for Spatio-temporal Video Transfercited by 6
  22. 2024Style-Friendly SNR Sampler for Style-Driven Generationcited by 5
  23. 2025SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Modelscited by 5
  24. 2025Learning User Preferences for Image Generation Modelcited by 5
  25. 2025Test-Time Anchoring for Discrete Diffusion Posterior Samplingcited by 5
  26. 2026TeleStyle: Content-Preserving Style Transfer in Images and Videoscited by 5
  27. 2026InnoAds-Composer: Efficient Condition Composition for E-Commerce Poster Generationcited by 5
  28. 2024FreezeAsGuard: Mitigating Illegal Adaptation of Diffusion Models via Selective Tensor Freezingcited by 4
  29. 2024TypeScore: A Text Fidelity Metric for Text-to-Image Generative Modelscited by 4
  30. 2024ArtNVG: Content-Style Separated Artistic Neighboring-View Gaussian Stylizationcited by 4
  31. 2025AIComposer: Any Style and Content Image Composition via Feature Integrationcited by 4
  32. 2025StyleProtect: Safeguarding Artistic Identity in Fine-tuned Diffusion Modelscited by 4
  33. 20253SGen: Unified Subject, Style, and Structure-Driven Image Generation with Adaptive Task-specific Memorycited by 4
  34. 2026QwenStyle: Content-Preserving Style Transfer with Qwen-Image-Editcited by 4
  35. 2026MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mappingcited by 4
  36. 2026OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agentscited by 4
  37. 2024Style-based Clustering of Visual Artworks and the Play of Neural Style-Representationscited by 3
  38. 2024Low-Rank Continual Personalization of Diffusion Modelscited by 3

50 most cited of 106 All 106 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Learning Artistic Signatures: Symmetry Discovery and Style Transfer
  2. 2025StyleBlend: Enhancing Style-Specific Content Creation in Text-to-Image Diffusion Models
  3. 2025Training-free Stylized Text-to-Image Generation with Fast Inference
  4. 2024Z-STAR+: A Zero-shot Style Transfer Method via Adjusting Style Distribution
  5. 2022Language Does More Than Describe: On The Lack Of Figurative Speech in Text-To-Image Models
  6. 2024DiffuseST: Unleashing the Capability of the Diffusion Model for Style Transfer
  7. 2023Not Only Generative Art: Stable Diffusion for Content-Style Disentanglement in Art Analysis
  8. 2023Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer