# ReVersion: Diffusion-Based Relation Inversion from Images

arXiv: https://arxiv.org/abs/2303.13495 · HTML: https://mlsanity.com/paper/2303.13495/

## Key facts

- Cited by 82 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 48 of its 76 references that are in the map.
- First posted on arXiv 23 Mar 2023.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 48)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Imagic: Text-Based Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2210.09276/) (2022)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://mlsanity.com/paper/2111.14822/) (2021)
- [End-to-End Learning of Visual Representations from Uncurated Instructional Videos](https://mlsanity.com/paper/1912.06430/) (2019)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)
- [Phenaki: Variable Length Video Generation From Open Domain Textual Description](https://mlsanity.com/paper/2210.02399/) (2022)

## Built on by (most cited first, 30 of 82)

- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence](https://mlsanity.com/paper/2305.14334/) (2023)
- [FreeU: Free Lunch in Diffusion U-Net](https://mlsanity.com/paper/2309.11497/) (2023)
- [Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code](https://mlsanity.com/paper/2310.01506/) (2023)
- [VideoBooth: Diffusion-based Video Generation with Image Prompts](https://mlsanity.com/paper/2312.00777/) (2023)
- [EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers](https://mlsanity.com/paper/2412.20413/) (2024)
- [Domain-Agnostic Tuning-Encoder for Fast Personalization of Text-To-Image Models](https://mlsanity.com/paper/2307.06925/) (2023)
- [Controllable Generation with Text-to-Image Diffusion Models: A Survey](https://mlsanity.com/paper/2403.04279/) (2024)
- [ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models](https://mlsanity.com/paper/2305.16225/) (2023)
- [CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation](https://mlsanity.com/paper/2311.18775/) (2023)
- [Concept Decomposition for Visual Exploration and Inspiration](https://mlsanity.com/paper/2305.18203/) (2023)
- [Video-Bench: Human-Aligned Video Generation Benchmark](https://mlsanity.com/paper/2504.04907/) (2025)
- [LCM-Lookahead for Encoder-based Text-to-Image Personalization](https://mlsanity.com/paper/2404.03620/) (2024)
- [VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2411.13503/) (2024)
- [PALP: Prompt Aligned Personalization of Text-to-Image Models](https://mlsanity.com/paper/2401.06105/) (2024)
- [Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference](https://mlsanity.com/paper/2312.09608/) (2023)
- [Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models](https://mlsanity.com/paper/2404.04243/) (2024)
- [Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction](https://mlsanity.com/paper/2411.14384/) (2024)
- [A Survey on Data Augmentation in Large Model Era](https://mlsanity.com/paper/2401.15422/) (2024)
- [It's All About Your Sketch: Democratising Sketch Control in Diffusion Models](https://mlsanity.com/paper/2403.07234/) (2024)
- [A Survey on Personalized Content Synthesis with Diffusion Models](https://mlsanity.com/paper/2405.05538/) (2024)
- [Visual Instruction Inversion: Image Editing via Visual Prompting](https://mlsanity.com/paper/2307.14331/) (2023)
- [Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation](https://mlsanity.com/paper/2311.15841/) (2023)
- [Magic Clothing: Controllable Garment-Driven Image Synthesis](https://mlsanity.com/paper/2404.09512/) (2024)
- [DreamRelation: Relation-Centric Video Customization](https://mlsanity.com/paper/2503.07602/) (2025)
- [Source Prompt Disentangled Inversion for Boosting Image Editability with Diffusion Models](https://mlsanity.com/paper/2403.11105/) (2024)
- [MotionCrafter: One-Shot Motion Customization of Diffusion Models](https://mlsanity.com/paper/2312.05288/) (2023)
- [SG-Adapter: Enhancing Text-to-Image Generation with Scene Graph Guidance](https://mlsanity.com/paper/2405.15321/) (2024)
- [Personalized Image Generation with Deep Generative Models: A Decade Survey](https://mlsanity.com/paper/2502.13081/) (2025)
- [Lego: Learning to Disentangle and Invert Personalized Concepts Beyond Object Appearance in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2311.13833/) (2023)

## Abstract (arXiv)

Diffusion models gain increasing popularity for their generative capabilities. Recently, there have been surging needs to generate customized images by inverting diffusion models from exemplar images, and existing inversion methods mainly focus on capturing object appearances (i.e., the "look"). However, how to invert object relations, another important pillar in the visual world, remains unexplored. In this work, we propose the Relation Inversion task, which aims to learn a specific relation (represented as "relation prompt") from exemplar images. Specifically, we learn a relation prompt with a frozen pre-trained text-to-image diffusion model. The learned relation prompt can then be applied to generate relation-specific images with new objects, backgrounds, and styles. To tackle the Relation Inversion task, we propose the ReVersion Framework. Specifically, we propose a novel "relation-steering contrastive learning" scheme to steer the relation prompt towards relation-dense regions, and disentangle it away from object appearances. We further devise "relation-focal importance sampling" to emphasize high-level interactions over low-level appearances (e.g., texture, color). To comprehensively evaluate this new task, we contribute the ReVersion Benchmark, which provides various exemplar images with diverse relations. Extensive experiments validate the superiority of our approach over existing methods across a wide range of visual relations. Our proposed task and method could be good inspirations for future research in various domains like generative inversion, few-shot learning, and visual relation detection.