# UnZipLoRA: Separating Content and Style from a Single Image

arXiv: https://arxiv.org/abs/2412.04465 · HTML: https://mlsanity.com/paper/2412.04465/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 45 references that are in the map.
- First posted on arXiv 5 Dec 2024.

## Builds on (most cited first, 30 of 37)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Universal Style Transfer via Feature Transforms](https://mlsanity.com/paper/1705.08086/) (2017)
- [SVDiff: Compact Parameter Space for Diffusion Fine-Tuning](https://mlsanity.com/paper/2303.11305/) (2023)
- [Break-A-Scene: Extracting Multiple Concepts from a Single Image](https://mlsanity.com/paper/2305.16311/) (2023)
- [Few-shot Image Generation via Cross-domain Correspondence](https://mlsanity.com/paper/2104.06820/) (2021)
- [StyleDrop: Text-to-Image Generation in Any Style](https://mlsanity.com/paper/2306.00983/) (2023)
- [Arbitrary Style Transfer with Style-Attentional Networks](https://mlsanity.com/paper/1812.02342/) (2018)
- [ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs](https://mlsanity.com/paper/2311.13600/) (2023)
- [Cones: Concept Neurons in Diffusion Models for Customized Generation](https://mlsanity.com/paper/2303.05125/) (2023)
- [Implicit Style-Content Separation using B-LoRA](https://mlsanity.com/paper/2403.14572/) (2024)
- [Measuring Style Similarity in Diffusion Models](https://mlsanity.com/paper/2404.01292/) (2024)
- [Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks](https://mlsanity.com/paper/2110.08398/) (2021)
- [Concept Decomposition for Visual Exploration and Inspiration](https://mlsanity.com/paper/2305.18203/) (2023)
- [JoJoGAN: One Shot Face Stylization](https://mlsanity.com/paper/2112.11641/) (2021)
- [RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control](https://mlsanity.com/paper/2405.17401/) (2024)
- [BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation](https://mlsanity.com/paper/2110.11728/) (2021)
- [One-Shot Generative Domain Adaptation](https://mlsanity.com/paper/2111.09876/) (2021)
- [One-Shot Adaptation of GAN in Just One CLIP](https://mlsanity.com/paper/2203.09301/) (2022)

## Built on by (most cited first, 24 of 24)

- [Personalized Image Generation with Deep Generative Models: A Decade Survey](https://mlsanity.com/paper/2502.13081/) (2025)
- [Dynamic Concepts Personalization from Single Videos](https://mlsanity.com/paper/2502.14844/) (2025)
- [ConsisLoRA: Enhancing Content and Style Consistency for LoRA-based Style Transfer](https://mlsanity.com/paper/2503.10614/) (2025)
- [QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation](https://mlsanity.com/paper/2507.04599/) (2025)
- [CSD-VAR: Content-Style Decomposition in Visual Autoregressive Models](https://mlsanity.com/paper/2507.13984/) (2025)
- [Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation](https://mlsanity.com/paper/2509.21989/) (2025)
- [SplitFlux: Learning to Decouple Content and Style from a Single Image](https://mlsanity.com/paper/2511.15258/) (2025)
- [StyleProtect: Safeguarding Artistic Identity in Fine-tuned Diffusion Models](https://mlsanity.com/paper/2509.13711/) (2025)
- [EmoStyle: Emotion-Driven Image Stylization](https://mlsanity.com/paper/2512.05478/) (2025)
- [CleanStyle: Plug-and-Play Style Conditioning Purification for Text-to-Image Stylization](https://mlsanity.com/paper/2602.20721/) (2026)
- [Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation](https://mlsanity.com/paper/2603.21884/) (2026)
- [LouvreSAE: Sparse Autoencoders for Interpretable and Controllable Style Transfer](https://mlsanity.com/paper/2512.18930/) (2025)
- [A Training-Free Style-Personalization via SVD-Based Feature Decomposition](https://mlsanity.com/paper/2507.04482/) (2025)
- [Weed Out, Then Harvest: Dual Low-Rank Adaptation is an Effective Noisy Label Detector for Noise-Robust Learning](https://mlsanity.com/paper/2510.10208/) (2025)
- [AD-Relight: Training-Free Banner Relighting via Illumination Translation with Diffusion Priors](https://mlsanity.com/paper/2604.24407/) (2026)
- [SEAL: Semantic-aware Single-image Sticker Personalization with a Large-scale Sticker-tag Dataset](https://mlsanity.com/paper/2604.26883/) (2026)
- [Structured 3D Latents Are Surprisingly Powerful: Unleashing Generalizable Style with 2D Diffusion](https://mlsanity.com/paper/2605.04412/) (2026)
- [When Style Similarity Scores Fail: Diagnosing Raw CSD Cosine in Artist-Style Evaluation](https://mlsanity.com/paper/2605.09030/) (2026)
- [Disco-LoRA: Disentangled Composition of Content, Style, and Motion for Multi-concept Video Customization](https://mlsanity.com/paper/2606.26668/) (2026)
- [Histogram-constrained Image Generation](https://mlsanity.com/paper/2606.31683/) (2026)
- [AnyStyle: A Single LoRA is Sufficient for Image-Guided Style Transfer](https://mlsanity.com/paper/2607.04677/) (2026)
- [DeCo: Zero-Shot Industrial Anomaly Generation through Decoupling and Recoupling](https://mlsanity.com/paper/2608.07904/) (2026)
- [X-MULTI: VLM-based Imaging Factor Disentanglement for Factor-Aware Image Synthesis](https://mlsanity.com/paper/2608.24563/) (2026)
- [RefDiT: Local Attribute Guidance in Reference-Based Image Generation](https://mlsanity.com/paper/2609.04976/) (2026)

## 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.