# FreeCompose: Generic Zero-Shot Image Composition with Diffusion Prior

arXiv: https://arxiv.org/abs/2407.04947 · HTML: https://mlsanity.com/paper/2407.04947/

## Key facts

- Cited by 16 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 30 of its 43 references that are in the map.
- First posted on arXiv 6 Jul 2024.

## 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 30)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [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)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Blended Diffusion for Text-driven Editing of Natural Images](https://mlsanity.com/paper/2111.14818/) (2021)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Paint by Example: Exemplar-based Image Editing with Diffusion Models](https://mlsanity.com/paper/2211.13227/) (2022)
- [Blended Latent Diffusion](https://mlsanity.com/paper/2206.02779/) (2022)
- [Learning to Discover Cross-Domain Relations with Generative Adversarial Networks](https://mlsanity.com/paper/1703.05192/) (2017)
- [Diffusion Model-Based Image Editing: A Survey](https://mlsanity.com/paper/2402.17525/) (2024)
- [Delta Denoising Score](https://mlsanity.com/paper/2304.07090/) (2023)
- [Noise-Free Score Distillation](https://mlsanity.com/paper/2310.17590/) (2023)
- [Circumventing Concept Erasure Methods For Text-to-Image Generative Models](https://mlsanity.com/paper/2308.01508/) (2023)
- [SSH: A Self-Supervised Framework for Image Harmonization](https://mlsanity.com/paper/2108.06805/) (2021)
- [Foreground-aware Semantic Representations for Image Harmonization](https://mlsanity.com/paper/2006.00809/) (2020)
- [Learning a Discriminative Model for the Perception of Realism in Composite Images](https://mlsanity.com/paper/1510.00477/) (2015)
- [BargainNet: Background-Guided Domain Translation for Image Harmonization](https://mlsanity.com/paper/2009.09169/) (2020)
- [Transformation Consistency Regularization- A Semi-Supervised Paradigm for Image-to-Image Translation](https://mlsanity.com/paper/2007.07867/) (2020)
- [KV Inversion: KV Embeddings Learning for Text-Conditioned Real Image Action Editing](https://mlsanity.com/paper/2309.16608/) (2023)
- [DE-Net: Dynamic Text-guided Image Editing Adversarial Networks](https://mlsanity.com/paper/2206.01160/) (2022)
- [Deep Image Harmonization in Dual Color Spaces](https://mlsanity.com/paper/2308.02813/) (2023)
- [On-Demand Learning for Deep Image Restoration](https://mlsanity.com/paper/1612.01380/) (2016)

## Built on by (most cited first, 16 of 16)

- [OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting](https://mlsanity.com/paper/2503.08677/) (2025)
- [Does FLUX Already Know How to Perform Physically Plausible Image Composition?](https://mlsanity.com/paper/2509.21278/) (2025)
- [Precise Object and Effect Removal with Adaptive Target-Aware Attention](https://mlsanity.com/paper/2505.22636/) (2025)
- [ORIDa: Object-centric Real-world Image Composition Dataset](https://mlsanity.com/paper/2506.08964/) (2025)
- [AIComposer: Any Style and Content Image Composition via Feature Integration](https://mlsanity.com/paper/2507.20721/) (2025)
- [MagicQuillV2: Precise and Interactive Image Editing with Layered Visual Cues](https://mlsanity.com/paper/2512.03046/) (2025)
- [Over++: Generative Video Compositing for Layer Interaction Effects](https://mlsanity.com/paper/2512.19661/) (2025)
- [PixPerfect: Seamless Latent Diffusion Local Editing with Discriminative Pixel-Space Refinement](https://mlsanity.com/paper/2512.03247/) (2025)
- [CrimEdit: Controllable Editing for Counterfactual Object Removal, Insertion, and Movement](https://mlsanity.com/paper/2509.23708/) (2025)
- [DORS: Dynamic Attention Routing for Diffusion-based Object Removal in Dense Scenes](https://mlsanity.com/paper/2607.16656/) (2026)
- [A Training-Free Approach for Multi-ID Customization via Attention Adjustment and Spatial Control](https://mlsanity.com/paper/2511.20401/) (2025)
- [EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal](https://mlsanity.com/paper/2512.21545/) (2025)
- [OmniVTON++: Training-Free Universal Virtual Try-On with Principal Pose Guidance](https://mlsanity.com/paper/2602.14552/) (2026)
- [PICS: Pairwise Image Compositing with Spatial Interactions](https://mlsanity.com/paper/2603.06873/) (2026)
- [HarmoniDiff-RS: Training-Free Diffusion Harmonization for Satellite Image Composition](https://mlsanity.com/paper/2604.19392/) (2026)
- [Physically Based Rendering in the Latent Space](https://mlsanity.com/paper/2609.21054/) (2026)

## Abstract (arXiv)

We offer a novel approach to image composition, which integrates multiple input images into a single, coherent image. Rather than concentrating on specific use cases such as appearance editing (image harmonization) or semantic editing (semantic image composition), we showcase the potential of utilizing the powerful generative prior inherent in large-scale pre-trained diffusion models to accomplish generic image composition applicable to both scenarios. We observe that the pre-trained diffusion models automatically identify simple copy-paste boundary areas as low-density regions during denoising. Building on this insight, we propose to optimize the composed image towards high-density regions guided by the diffusion prior. In addition, we introduce a novel maskguided loss to further enable flexible semantic image composition. Extensive experiments validate the superiority of our approach in achieving generic zero-shot image composition. Additionally, our approach shows promising potential in various tasks, such as object removal and multiconcept customization.