mlsanityData to 7 Oct 2026

UnZipLoRA: Separating Content and Style from a Single Image

arXiv 2412.04465 ↗First posted 5 Dec 2024cs.CVcited by 24

Not on the map. Why?

Abstract (arXiv)

This paper introduces UnZipLoRA, a method for decomposing an image into its constituent subject and style, represented as two distinct LoRAs (Low-Rank Adaptations). Unlike existing personalization techniques that focus on either subject or style in isolation, or require separate training sets for each, UnZipLoRA disentangles these elements from a single image by training both the LoRAs simultaneously. UnZipLoRA ensures that the resulting LoRAs are compatible, i.e., they can be seamlessly combined using direct addition. UnZipLoRA enables independent manipulation and recontextualization of subject and style, including generating variations of each, applying the extracted style to new subjects, and recombining them to reconstruct the original image or create novel variations. To address the challenge of subject and style entanglement, UnZipLoRA employs a novel prompt separation technique, as well as column and block separation strategies to accurately preserve the characteristics of subject and style, and ensure compatibility between the learned LoRAs. Evaluation with human studies and quantitative metrics demonstrates UnZipLoRA's effectiveness compared to other state-of-the-art methods, including DreamBooth-LoRA, Inspiration Tree, and B-LoRA.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 37 of its 45 references that are in the map. First posted on arXiv 5 Dec 2024.

Builds on

37 of 45 references.

References · 37

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  7. 2022Scalable Diffusion Models with Transformerscited by 5,931
  8. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  9. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  10. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  11. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  12. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
25 more
  1. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,099
  2. 2017Universal Style Transfer via Feature Transformscited by 352
  3. 2023SVDiff: Compact Parameter Space for Diffusion Fine-Tuningcited by 338
  4. 2023Break-A-Scene: Extracting Multiple Concepts from a Single Imagecited by 230
  5. 2021Few-shot Image Generation via Cross-domain Correspondencecited by 206
  6. 2018Arbitrary Style Transfer with Style-Attentional Networkscited by 197
  7. 2023StyleDrop: Text-to-Image Generation in Any Stylecited by 197
  8. 2023ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAscited by 194
  9. 2023Cones: Concept Neurons in Diffusion Models for Customized Generationcited by 150
  10. 2024Implicit Style-Content Separation using B-LoRAcited by 135
  11. 2024Measuring Style Similarity in Diffusion Modelscited by 106
  12. 2021Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networkscited by 68
  13. 2023Concept Decomposition for Visual Exploration and Inspirationcited by 61
  14. 2021JoJoGAN: One Shot Face Stylizationcited by 49
  15. 2021BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generationcited by 47
  16. 2024RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Controlcited by 46
  17. 2021One-Shot Generative Domain Adaptationcited by 41
  18. 2022One-Shot Adaptation of GAN in Just One CLIPcited by 31
  19. 2023Lego: Learning to Disentangle and Invert Personalized Concepts Beyond Object Appearance in Text-to-Image Diffusion Modelscited by 19
  20. 2023KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesiscited by 18
  21. 2024ConceptExpress: Harnessing Diffusion Models for Single-image Unsupervised Concept Extractioncited by 16
  22. 2022CtlGAN: Few-shot Artistic Portraits Generation with Contrastive Transfer Learningcited by 10
  23. 2024CusConcept: Customized Visual Concept Decomposition with Diffusion Modelscited by 9
  24. 2024U-VAP: User-specified Visual Appearance Personalization via Decoupled Self Augmentationcited by 7
  25. 2022MultiStyleGAN: Multiple One-shot Image Stylizations using a Single GANcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 12; 2026: 12.

24 papers.

Sort:

By area:

  1. 2025Personalized Image Generation with Deep Generative Models: A Decade Surveycited by 20
  2. 2025Dynamic Concepts Personalization from Single Videoscited by 20
  3. 2025ConsisLoRA: Enhancing Content and Style Consistency for LoRA-based Style Transfercited by 9
  4. 2025QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generationcited by 9
  5. 2025CSD-VAR: Content-Style Decomposition in Visual Autoregressive Modelscited by 6
  6. 2025Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generationcited by 6
  7. 2025SplitFlux: Learning to Decouple Content and Style from a Single Imagecited by 5
  8. 2025StyleProtect: Safeguarding Artistic Identity in Fine-tuned Diffusion Modelscited by 4
  9. 2026CleanStyle: Plug-and-Play Style Conditioning Purification for Text-to-Image Stylizationcited by 3
  10. 2025EmoStyle: Emotion-Driven Image Stylizationcited by 2
  11. 2026Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generationcited by 2
  12. 2025LouvreSAE: Sparse Autoencoders for Interpretable and Controllable Style Transfercited by 1
12 more
  1. 2025A Training-Free Style-Personalization via SVD-Based Feature Decompositioncited by 0
  2. 2025Weed Out, Then Harvest: Dual Low-Rank Adaptation is an Effective Noisy Label Detector for Noise-Robust Learningcited by 0
  3. 2026AD-Relight: Training-Free Banner Relighting via Illumination Translation with Diffusion Priorscited by 0
  4. 2026SEAL: Semantic-aware Single-image Sticker Personalization with a Large-scale Sticker-tag Datasetcited by 0
  5. 2026Structured 3D Latents Are Surprisingly Powerful: Unleashing Generalizable Style with 2D Diffusioncited by 0
  6. 2026When Style Similarity Scores Fail: Diagnosing Raw CSD Cosine in Artist-Style Evaluationcited by 0
  7. 2026Disco-LoRA: Disentangled Composition of Content, Style, and Motion for Multi-concept Video Customizationcited by 0
  8. 2026Histogram-constrained Image Generationcited by 0
  9. 2026AnyStyle: A Single LoRA is Sufficient for Image-Guided Style Transfercited by 0
  10. 2026DeCo: Zero-Shot Industrial Anomaly Generation through Decoupling and Recouplingcited by 0
  11. 2026X-MULTI: VLM-based Imaging Factor Disentanglement for Factor-Aware Image Synthesiscited by 0
  12. 2026RefDiT: Local Attribute Guidance in Reference-Based Image Generationcited by 0