# DreamFuse: Adaptive Image Fusion with Diffusion Transformer

arXiv: https://arxiv.org/abs/2504.08291 · HTML: https://mlsanity.com/paper/2504.08291/

## Key facts

- Cited by 13 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 43 of its 55 references that are in the map.
- First posted on arXiv 11 Apr 2025.

## 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 43)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Paint by Example: Exemplar-based Image Editing with Diffusion Models](https://mlsanity.com/paper/2211.13227/) (2022)
- [InstantID: Zero-shot Identity-Preserving Generation in Seconds](https://mlsanity.com/paper/2401.07519/) (2024)
- [AnyDoor: Zero-shot Object-level Image Customization](https://mlsanity.com/paper/2307.09481/) (2023)
- [OminiControl: Minimal and Universal Control for Diffusion Transformer](https://mlsanity.com/paper/2411.15098/) (2024)
- [SVDiff: Compact Parameter Space for Diffusion Fine-Tuning](https://mlsanity.com/paper/2303.11305/) (2023)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [Improving Video Generation with Human Feedback](https://mlsanity.com/paper/2501.13918/) (2025)
- [CogVLM2: Visual Language Models for Image and Video Understanding](https://mlsanity.com/paper/2408.16500/) (2024)
- [Subject-driven Text-to-Image Generation via Apprenticeship Learning](https://mlsanity.com/paper/2304.00186/) (2023)
- [TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition](https://mlsanity.com/paper/2307.12493/) (2023)
- [In-Context LoRA for Diffusion Transformers](https://mlsanity.com/paper/2410.23775/) (2024)
- [VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation](https://mlsanity.com/paper/2412.21059/) (2024)
- [SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation](https://mlsanity.com/paper/2312.16272/) (2023)
- [Prodigy: An Expeditiously Adaptive Parameter-Free Learner](https://mlsanity.com/paper/2306.06101/) (2023)
- [Aligning Diffusion Models by Optimizing Human Utility](https://mlsanity.com/paper/2404.04465/) (2024)

## Built on by (most cited first, 13 of 13)

- [Does FLUX Already Know How to Perform Physically Plausible Image Composition?](https://mlsanity.com/paper/2509.21278/) (2025)
- [Leveraging Verifier-Based Reinforcement Learning in Image Editing](https://mlsanity.com/paper/2604.27505/) (2026)
- [LaneDiffusion: Improving Centerline Graph Learning via Prior Injected BEV Feature Generation](https://mlsanity.com/paper/2511.06272/) (2025)
- [HiGS: Hierarchical Generative Scene Framework for Multi-Step Associative Semantic Spatial Composition](https://mlsanity.com/paper/2510.27148/) (2025)
- [Insert In Style: A Zero-Shot Generative Framework for Harmonious Cross-Domain Object Composition](https://mlsanity.com/paper/2511.15197/) (2025)
- [RoomEditor++: A Parameter-Sharing Diffusion Architecture for High-Fidelity Furniture Synthesis](https://mlsanity.com/paper/2512.17573/) (2025)
- [Geometric Image Editing via Effects-Sensitive In-Context Inpainting with Diffusion Transformers](https://mlsanity.com/paper/2602.08388/) (2026)
- [DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prior](https://mlsanity.com/paper/2604.17195/) (2026)
- [MAVFusion: Efficient Infrared and Visible Video Fusion via Motion-Aware Sparse Interaction](https://mlsanity.com/paper/2604.01958/) (2026)
- [BFS: Back-to-Front Layered Image Synthesis via Knowledge Transfer](https://mlsanity.com/paper/2605.24894/) (2026)
- [Chameleon: Style-Content Disentangled Framework for Cross-Domain Object Compositing](https://mlsanity.com/paper/2606.01079/) (2026)
- [RefGC-SR2: Reference-guided Super-Resolution and Refinement of AI Generated Content](https://mlsanity.com/paper/2606.15158/) (2026)
- [SpatialDiff: 3D-Aware Object Movement via Implicit Spatial Modeling](https://mlsanity.com/paper/2608.21776/) (2026)

## Abstract (arXiv)

Image fusion seeks to seamlessly integrate foreground objects with background scenes, producing realistic and harmonious fused images. Unlike existing methods that directly insert objects into the background, adaptive and interactive fusion remains a challenging yet appealing task. It requires the foreground to adjust or interact with the background context, enabling more coherent integration. To address this, we propose an iterative human-in-the-loop data generation pipeline, which leverages limited initial data with diverse textual prompts to generate fusion datasets across various scenarios and interactions, including placement, holding, wearing, and style transfer. Building on this, we introduce DreamFuse, a novel approach based on the Diffusion Transformer (DiT) model, to generate consistent and harmonious fused images with both foreground and background information. DreamFuse employs a Positional Affine mechanism to inject the size and position of the foreground into the background, enabling effective foreground-background interaction through shared attention. Furthermore, we apply Localized Direct Preference Optimization guided by human feedback to refine DreamFuse, enhancing background consistency and foreground harmony. DreamFuse achieves harmonious fusion while generalizing to text-driven attribute editing of the fused results. Experimental results demonstrate that our method outperforms state-of-the-art approaches across multiple metrics.