mlsanityData to 7 Oct 2026

CSGO: Content-Style Composition in Text-to-Image Generation

arXiv 2408.16766 ↗First posted 29 Aug 2024cs.CVcited by 76

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

Abstract (arXiv)

The diffusion model has shown exceptional capabilities in controlled image generation, which has further fueled interest in image style transfer. Existing works mainly focus on training free-based methods (e.g., image inversion) due to the scarcity of specific data. In this study, we present a data construction pipeline for content-style-stylized image triplets that generates and automatically cleanses stylized data triplets. Based on this pipeline, we construct a dataset IMAGStyle, the first large-scale style transfer dataset containing 210k image triplets, available for the community to explore and research. Equipped with IMAGStyle, we propose CSGO, a style transfer model based on end-to-end training, which explicitly decouples content and style features employing independent feature injection. The unified CSGO implements image-driven style transfer, text-driven stylized synthesis, and text editing-driven stylized synthesis. Extensive experiments demonstrate the effectiveness of our approach in enhancing style control capabilities in image generation. Additional visualization and access to the source code can be located on the project page: urlhttps://csgo-gen.github.io/.

Key facts. Cited by 76 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 43 of its 55 references that are in the map. First posted on arXiv 29 Aug 2024.

Builds on

43 of 55 references.

Closest ancestors · 11

Same direction, newest first

  1. 2024Measuring Style Similarity in Diffusion Models1 Apr
  2. 2024DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations11 Mar
  3. 2024InstantID: Zero-shot Identity-Preserving Generation in Seconds15 Jan
  4. 2023Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer11 Dec
  5. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models13 Aug
  6. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models16 Feb
  7. 2023Adding Conditional Control to Text-to-Image Diffusion Models10 Feb
  8. 2022Inversion-Based Style Transfer with Diffusion Models23 Nov
  9. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Models17 Nov
  10. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation25 Aug
  11. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr

Other references · 32

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  6. 2020Denoising Diffusion Implicit Modelscited by 9,655
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  8. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  9. 2022Scalable Diffusion Models with Transformerscited by 5,931
  10. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  11. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  12. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
20 more
  1. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  2. 2019Learning Robust Global Representations by Penalizing Local Predictive Powercited by 1,010
  3. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,010
  4. 2022Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translationcited by 897
  5. 2016A Learned Representation For Artistic Stylecited by 340
  6. 2023Style Aligned Image Generation via Shared Attentioncited by 214
  7. 2017Neural Style Transfer: A Reviewcited by 199
  8. 2023ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAscited by 194
  9. 2021StyTr2: Image Style Transfer with Transformerscited by 186
  10. 2015Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Featurecited by 181
  11. 2024InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generationcited by 166
  12. 2024Implicit Style-Content Separation using B-LoRAcited by 135
  13. 2024IMAGDressing-v1: Customizable Virtual Dressingcited by 100
  14. 2014Salient Object Detection: A Discriminative Regional Feature Integration Approachcited by 89
  15. 2017StyleBank: An Explicit Representation for Neural Image Style Transfercited by 89
  16. 2020Arbitrary Style Transfer via Multi-Adaptation Networkcited by 70
  17. 2024StyleShot: A Snapshot on Any Stylecited by 60
  18. 2024InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generationcited by 51
  19. 2023StyleAdapter: A Unified Stylized Image Generation Modelcited by 39
  20. 2023General Image-to-Image Translation with One-Shot Image Guidancecited by 31

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 9; 2025: 38; 2026: 29.

76 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. 2025K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAscited by 48
  4. 2024StyleMaster: Stylize Your Video with Artistic Generation and Translationcited by 47
  5. 2025Attention Distillation: A Unified Approach to Visual Characteristics Transfercited by 32
  6. 2025OmniStyle: Filtering High Quality Style Transfer Data at Scalecited by 30
  7. 2024StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elementscited by 26
  8. 2025USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learningcited by 26
  9. 2024EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLMcited by 25
  10. 2025UniCombine: Unified Multi-Conditional Combination with Diffusion Transformercited by 25
  11. 2025DiffV2IR: Visible-to-Infrared Diffusion Model via Vision-Language Understandingcited by 16
  12. 2024MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Modelscited by 14
38 more
  1. 2025U-StyDiT: Ultra-high Quality Artistic Style Transfer Using Diffusion Transformerscited by 12
  2. 2025ConsisLoRA: Enhancing Content and Style Consistency for LoRA-based Style Transfercited by 9
  3. 2025Free-Lunch Color-Texture Disentanglement for Stylized Image Generationcited by 8
  4. 2025Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion Modelscited by 7
  5. 2025RepText: Rendering Visual Text via Replicatingcited by 7
  6. 2025CDST: Color Disentangled Style Transfer for Universal Style Reference Customizationcited by 6
  7. 2025FreeViS: Training-free Video Stylization with Inconsistent Referencescited by 6
  8. 2025StyleKeeper: Prevent Content Leakage using Negative Visual Query Guidancecited by 6
  9. 2025iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generationcited by 6
  10. 2026OmniTransfer: All-in-one Framework for Spatio-temporal Video Transfercited by 6
  11. 2025SplitFlux: Learning to Decouple Content and Style from a Single Imagecited by 5
  12. 2026TeleStyle: Content-Preserving Style Transfer in Images and Videoscited by 5
  13. 2024Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalizationcited by 4
  14. 2024ArtNVG: Content-Style Separated Artistic Neighboring-View Gaussian Stylizationcited by 4
  15. 2025ArtCrafter: Text-Image Aligning Style Transfer via Embedding Reframingcited by 4
  16. 2025A Training-Free Style-aligned Image Generation with Scale-wise Autoregressive Modelcited by 4
  17. 2025AIComposer: Any Style and Content Image Composition via Feature Integrationcited by 4
  18. 20253SGen: Unified Subject, Style, and Structure-Driven Image Generation with Adaptive Task-specific Memorycited by 4
  19. 2026TP-Blend: Textual-Prompt Attention Pairing for Precise Object-Style Blending in Diffusion Modelscited by 4
  20. 2026MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mappingcited by 4
  21. 2026OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptationcited by 4
  22. 2026DreamStyle: A Unified Framework for Video Stylizationcited by 3
  23. 2026Tuning-free Visual Effect Transfer across Videoscited by 3
  24. 2026TherA: Thermal-Aware Visual-Language Prompting for Controllable RGB-to-Thermal Infrared Translationcited by 3
  25. 2025Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generationcited by 2
  26. 2026SIGMA: Selective-Interleaved Generation with Multi-Attribute Tokenscited by 2
  27. 2026StyleGallery: Training-free and Semantic-aware Personalized Style Transfer from Arbitrary Image Referencescited by 2
  28. 2026Scale-Separated Conditioning for Style-Encoder-Free Diffusion Stylizationcited by 2
  29. 2024WikiStyle+: A Multimodal Approach to Content-Style Representation Disentanglement for Artistic Image Stylizationcited by 1
  30. 2024Single Trajectory Distillation for Accelerating Image and Video Style Transfercited by 1
  31. 2025Only-Style: Stylistic Consistency in Image Generation without Content Leakagecited by 1
  32. 2025Improved 3D Scene Stylization via Text-Guided Generative Image Editing with Region-Based Controlcited by 1
  33. 2025OmniStyle2: Learning to Stylize by Learning to Destylizecited by 1
  34. 2025Stroke2Sketch: Harnessing Stroke Attributes for Training-Free Sketch Generationcited by 1
  35. 2025A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Spacecited by 1
  36. 2025Insert In Style: A Zero-Shot Generative Framework for Harmonious Cross-Domain Object Compositioncited by 1
  37. 2026Mixture of Style Experts for Diverse Image Stylizationcited by 1
  38. 2026DreamStyle3D: Efficient 3D Stylized Asset Generation via Dual-Attention Disentanglementcited by 1

50 most cited of 76 All 76 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023ControlStyle: Text-Driven Stylized Image Generation Using Diffusion Priors
  2. 2022Arbitrary Style Guidance for Enhanced Diffusion-Based Text-to-Image Generation
  3. 2025Training-free Stylized Text-to-Image Generation with Fast Inference
  4. 2025StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer
  5. 2025FantasyStyle: Controllable Stylized Distillation for 3D Gaussian Splatting
  6. 2024Z-STAR+: A Zero-shot Style Transfer Method via Adjusting Style Distribution
  7. 2024Visual Style Prompting with Swapping Self-Attention
  8. 2025SigStyle: Signature Style Transfer via Personalized Text-to-Image Models