# D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples

arXiv: https://arxiv.org/abs/2505.22002 · HTML: https://mlsanity.com/paper/2505.22002/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 41 of its 52 references that are in the map.
- First posted on arXiv 28 May 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)
- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 30 of 41)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://mlsanity.com/paper/2211.09794/) (2022)
- [Imagic: Text-Based Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2210.09276/) (2022)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Improved Techniques for Training Score-Based Generative Models](https://mlsanity.com/paper/2006.09011/) (2020)
- [Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation](https://mlsanity.com/paper/2211.12572/) (2022)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Diffusion Autoencoders: Toward a Meaningful and Decodable Representation](https://mlsanity.com/paper/2111.15640/) (2021)
- [Directly Fine-Tuning Diffusion Models on Differentiable Rewards](https://mlsanity.com/paper/2309.17400/) (2023)
- [Aligning Text-to-Image Models using Human Feedback](https://mlsanity.com/paper/2302.12192/) (2023)
- [RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback](https://mlsanity.com/paper/2312.00849/) (2023)
- [Fine-Grained Human Feedback Gives Better Rewards for Language Model Training](https://mlsanity.com/paper/2306.01693/) (2023)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [Visual Relationship Detection with Language Priors](https://mlsanity.com/paper/1608.00187/) (2016)
- [DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing](https://mlsanity.com/paper/2306.14435/) (2023)
- [LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation](https://mlsanity.com/paper/2303.17189/) (2023)

## Built on by (most cited first, 14 of 14)

- [DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models](https://mlsanity.com/paper/2506.03517/) (2025)
- [Reinforcement Learning for Large Model: A Survey](https://mlsanity.com/paper/2508.08189/) (2025)
- [Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO](https://mlsanity.com/paper/2602.06422/) (2026)
- [Towards Better Optimization For Listwise Preference in Diffusion Models](https://mlsanity.com/paper/2510.01540/) (2025)
- [HP-Edit: A Human-Preference Post-Training Framework for Image Editing](https://mlsanity.com/paper/2604.19406/) (2026)
- [Asynchronous Denoising Diffusion Models for Aligning Text-to-Image Generation](https://mlsanity.com/paper/2510.04504/) (2025)
- [Noise Projection: Closing the Prompt-Agnostic Gap Behind Text-to-Image Misalignment in Diffusion Models](https://mlsanity.com/paper/2510.14526/) (2025)
- [Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation](https://mlsanity.com/paper/2511.01450/) (2025)
- [SpatialFusion: Endowing Unified Image Generation with Intrinsic 3D Geometric Awareness](https://mlsanity.com/paper/2604.26341/) (2026)
- [Accelerating Inference of Masked Image Generators via Reinforcement Learning](https://mlsanity.com/paper/2512.01094/) (2025)
- [Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs](https://mlsanity.com/paper/2605.09433/) (2026)
- [Towards Anatomically Plausible Human Image Generation via Synthetic Localized Preferences](https://mlsanity.com/paper/2605.25759/) (2026)
- [Di3PO - Diptych Diffusion DPO for Targeted Improvements in Image Generation](https://mlsanity.com/paper/2602.06355/) (2026)
- [ToPO: Token-Conditioned Preference Routing for Attention-Based Latent Diffusion Models](https://mlsanity.com/paper/2609.03688/) (2026)

## Abstract (arXiv)

The practical applications of diffusion models have been limited by the misalignment between generated images and corresponding text prompts. Recent studies have introduced direct preference optimization (DPO) to enhance the alignment of these models. However, the effectiveness of DPO is constrained by the issue of visual inconsistency, where the significant visual disparity between well-aligned and poorly-aligned images prevents diffusion models from identifying which factors contribute positively to alignment during fine-tuning. To address this issue, this paper introduces D-Fusion, a method to construct DPO-trainable visually consistent samples. On one hand, by performing mask-guided self-attention fusion, the resulting images are not only well-aligned, but also visually consistent with given poorly-aligned images. On the other hand, D-Fusion can retain the denoising trajectories of the resulting images, which are essential for DPO training. Extensive experiments demonstrate the effectiveness of D-Fusion in improving prompt-image alignment when applied to different reinforcement learning algorithms.