mlsanityData to 7 Oct 2026

Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer

arXiv 2312.09008 ↗First posted 11 Dec 2023cs.CVcited by 194

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

Abstract (arXiv)

Despite the impressive generative capabilities of diffusion models, existing diffusion model-based style transfer methods require inference-stage optimization (e.g. fine-tuning or textual inversion of style) which is time-consuming, or fails to leverage the generative ability of large-scale diffusion models. To address these issues, we introduce a novel artistic style transfer method based on a pre-trained large-scale diffusion model without any optimization. Specifically, we manipulate the features of self-attention layers as the way the cross-attention mechanism works; in the generation process, substituting the key and value of content with those of style image. This approach provides several desirable characteristics for style transfer including 1) preservation of content by transferring similar styles into similar image patches and 2) transfer of style based on similarity of local texture (e.g. edge) between content and style images. Furthermore, we introduce query preservation and attention temperature scaling to mitigate the issue of disruption of original content, and initial latent Adaptive Instance Normalization (AdaIN) to deal with the disharmonious color (failure to transfer the colors of style). Our experimental results demonstrate that our proposed method surpasses state-of-the-art methods in both conventional and diffusion-based style transfer baselines.

Key facts. Cited by 194 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 45 of its 55 references that are in the map. First posted on arXiv 11 Dec 2023.

Builds on

45 of 55 references.

Closest ancestors · 13

Same direction, newest first

  1. 2023StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models15 Aug
  2. 2023DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing26 Jun
  3. 2023A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence24 May
  4. 2023Zero-Shot Contrastive Loss for Text-Guided Diffusion Image Style Transfer15 Mar
  5. 2022Inversion-Based Style Transfer with Diffusion Models23 Nov
  6. 2022DiffEdit: Diffusion-based semantic image editing with mask guidance20 Oct
  7. 2022Imagic: Text-Based Real Image Editing with Diffusion Models17 Oct
  8. 2022Diffusion-based Image Translation using Disentangled Style and Content Representation30 Sep
  9. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation25 Aug
  10. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  11. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr
  12. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models20 Dec
1 more
  1. 2021Blended Diffusion for Text-driven Editing of Natural Images29 Nov

Other references · 32

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  6. 2020Denoising Diffusion Implicit Modelscited by 9,655
  7. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  8. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  9. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  10. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  11. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  12. 2022Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translationcited by 897
20 more
  1. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 722
  2. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 452
  3. 2022Diffusion Models already have a Semantic Latent Spacecited by 324
  4. 2023Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translationcited by 253
  5. 2021CLIPstyler: Image Style Transfer with a Single Text Conditioncited by 203
  6. 2018Arbitrary Style Transfer with Style-Attentional Networkscited by 197
  7. 2021StyTr2: Image Style Transfer with Transformerscited by 186
  8. 2023StableVideo: Text-driven Consistency-aware Diffusion Video Editingcited by 182
  9. 2021AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfercited by 178
  10. 2018A Closed-form Solution to Photorealistic Image Stylizationcited by 133
  11. 2022Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalizationcited by 122
  12. 2021ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flowscited by 113
  13. 2022Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learningcited by 93
  14. 2020Arbitrary Style Transfer via Multi-Adaptation Networkcited by 70
  15. 2020HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histogramscited by 64
  16. 2020Collaborative Distillation for Ultra-Resolution Universal Style Transfercited by 52
  17. 2022ArtFID: Quantitative Evaluation of Neural Style Transfercited by 49
  18. 2019A Closed-form Solution to Universal Style Transfercited by 42
  19. 2019Diversified Arbitrary Style Transfer via Deep Feature Perturbationcited by 42
  20. 2023AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networkscited by 34

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 38; 2025: 102; 2026: 54.

194 papers.

Sort:

By area:

  1. 2024CSGO: Content-Style Composition in Text-to-Image Generationcited by 76
  2. 2025Insert Anything: Image Insertion via In-Context Editing in DiTcited by 61
  3. 2024StyleShot: A Snapshot on Any Stylecited by 60
  4. 2024InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generationcited by 51
  5. 2025K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAscited by 48
  6. 2024StyleMaster: Stylize Your Video with Artistic Generation and Translationcited by 47
  7. 2024AeroGen: Enhancing Remote Sensing Object Detection with Diffusion-Driven Data Generationcited by 32
  8. 2025Attention Distillation: A Unified Approach to Visual Characteristics Transfercited by 32
  9. 2025OmniStyle: Filtering High Quality Style Transfer Data at Scalecited by 30
  10. 2024Conditional Image Synthesis with Diffusion Models: A Surveycited by 29
  11. 2024StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elementscited by 26
  12. 2025USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learningcited by 26
38 more
  1. 2024FreeTuner: Any Subject in Any Style with Training-free Diffusioncited by 24
  2. 2025StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfercited by 23
  3. 2024AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoisingcited by 22
  4. 2024ViPer: Visual Personalization of Generative Models via Individual Preference Learningcited by 17
  5. 2025Multi-turn Consistent Image Editingcited by 17
  6. 2024UniVST: A Unified Framework for Training-free Localized Video Style Transfercited by 16
  7. 2025DiffV2IR: Visible-to-Infrared Diffusion Model via Vision-Language Understandingcited by 16
  8. 2025Personalized Vision via Visual In-Context Learningcited by 14
  9. 2025Fine-Tuning Visual Autoregressive Models for Subject-Driven Generationcited by 13
  10. 2025ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translationcited by 13
  11. 2025U-StyDiT: Ultra-high Quality Artistic Style Transfer Using Diffusion Transformerscited by 12
  12. 2025Color Alignment in Diffusioncited by 10
  13. 2025O-DisCo-Edit: Object Distortion Control for Unified Realistic Video Editingcited by 10
  14. 2025ConsisLoRA: Enhancing Content and Style Consistency for LoRA-based Style Transfercited by 9
  15. 2025AttenST: A Training-Free Attention-Driven Style Transfer Framework with Pre-Trained Diffusion Modelscited by 8
  16. 2025Free-Lunch Color-Texture Disentanglement for Stylized Image Generationcited by 8
  17. 2025SA-LUT: Spatial Adaptive 4D Look-Up Table for Photorealistic Style Transfercited by 8
  18. 2024An Efficient and Harmonized Framework for Balanced Cross-Domain Feature Integrationcited by 7
  19. 2024VectorPainter: Advanced Stylized Vector Graphics Synthesis Using Stroke-Style Priorscited by 7
  20. 2024Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Modelscited by 7
  21. 2024DiffArtist: Towards Structure and Appearance Controllable Image Stylizationcited by 6
  22. 2025A Critical Assessment of Modern Generative Models' Ability to Replicate Artistic Stylescited by 6
  23. 2025TF-TI2I: Training-Free Text-and-Image-to-Image Generation via Multi-Modal Implicit-Context Learning in Text-to-Image Modelscited by 6
  24. 2025SITA: Structurally Imperceptible and Transferable Adversarial Attacks for Stylized Image Generationcited by 6
  25. 2025StyleMe3D: Stylization with Disentangled Priors by Multiple Encoders on 3D Gaussianscited by 6
  26. 2025AudioMorphix: Training-free audio editing with diffusion probabilistic modelscited by 6
  27. 2025Style Transfer with Diffusion Models for Synthetic-to-Real Domain Adaptationcited by 6
  28. 2025Targeted Forgetting of Image Subgroups in CLIP Modelscited by 6
  29. 2025GenHSI: Controllable Generation of Human-Scene Interaction Videoscited by 6
  30. 2025Detecting Visual Information Manipulation Attacks in Augmented Reality: A Multimodal Semantic Reasoning Approachcited by 6
  31. 2025FreeViS: Training-free Video Stylization with Inconsistent Referencescited by 6
  32. 2025StyleKeeper: Prevent Content Leakage using Negative Visual Query Guidancecited by 6
  33. 2024G-Style: Stylized Gaussian Splattingcited by 5
  34. 2024Mamba-ST: State Space Model for Efficient Style Transfercited by 5
  35. 2024LineArt: A Knowledge-guided Training-free High-quality Appearance Transfer for Design Drawing with Diffusion Modelcited by 5
  36. 2025Balanced Image Stylization with Style Matching Scorecited by 5
  37. 2025SaMam: Style-aware State Space Model for Arbitrary Image Style Transfercited by 5
  38. 2025DCI: Dual-Conditional Inversion for Boosting Diffusion-Based Image Editingcited by 5

50 most cited of 194 All 194 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024DiffuseST: Unleashing the Capability of the Diffusion Model for Style Transfer
  2. 2023Z^*: Zero-shot Style Transfer via Attention Rearrangement
  3. 2024Harnessing the Latent Diffusion Model for Training-Free Image Style Transfer
  4. 2024Towards Highly Realistic Artistic Style Transfer via Stable Diffusion with Step-aware and Layer-aware Prompt
  5. 2026TRACE: Time-Adaptive Residual Attention Control with Content-Style Decomposition for Training-Free Diffusion Style Transfer
  6. 2024FreeStyle: Free Lunch for Text-guided Style Transfer using Diffusion Models
  7. 2024Z-STAR+: A Zero-shot Style Transfer Method via Adjusting Style Distribution
  8. 2024Tuning-Free Adaptive Style Incorporation for Structure-Consistent Text-Driven Style Transfer