# Diffusion-RPO: Aligning Diffusion Models through Relative Preference Optimization

arXiv: https://arxiv.org/abs/2406.06382 · HTML: https://mlsanity.com/paper/2406.06382/

## Key facts

- Cited by 32 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 31 of its 46 references that are in the map.
- First posted on arXiv 10 Jun 2024.

## 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 31)

- [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)
- [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)
- [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)
- [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)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [ORPO: Monolithic Preference Optimization without Reference Model](https://mlsanity.com/paper/2403.07691/) (2024)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [Tackling the Generative Learning Trilemma with Denoising Diffusion GANs](https://mlsanity.com/paper/2112.07804/) (2021)
- [A Neural Algorithm of Artistic Style](https://mlsanity.com/paper/1508.06576/) (2015)
- [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)
- [Aligning Text-to-Image Diffusion Models with Reward Backpropagation](https://mlsanity.com/paper/2310.03739/) (2023)
- [Diffusion-GAN: Training GANs with Diffusion](https://mlsanity.com/paper/2206.02262/) (2022)
- [In-Context Learning Unlocked for Diffusion Models](https://mlsanity.com/paper/2305.01115/) (2023)
- [A Prototype-Oriented Framework for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2110.12024/) (2021)
- [Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts](https://mlsanity.com/paper/2402.10958/) (2024)
- [Exploiting Chain Rule and Bayes' Theorem to Compare Probability Distributions](https://mlsanity.com/paper/2012.14100/) (2020)

## Built on by (most cited first, 30 of 32)

- [TempFlow-GRPO: When Timing Matters for GRPO in Flow Models](https://mlsanity.com/paper/2508.04324/) (2025)
- [A Survey of Direct Preference Optimization](https://mlsanity.com/paper/2503.11701/) (2025)
- [Scalable Ranked Preference Optimization for Text-to-Image Generation](https://mlsanity.com/paper/2410.18013/) (2024)
- [Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs](https://mlsanity.com/paper/2506.21656/) (2025)
- [A Simple and Effective Reinforcement Learning Method for Text-to-Image Diffusion Fine-tuning](https://mlsanity.com/paper/2503.00897/) (2025)
- [DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling](https://mlsanity.com/paper/2412.00759/) (2024)
- [Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization](https://mlsanity.com/paper/2410.03190/) (2024)
- [CoDe: Blockwise Control for Denoising Diffusion Models](https://mlsanity.com/paper/2502.00968/) (2025)
- [Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferences](https://mlsanity.com/paper/2506.02698/) (2025)
- [Aligning Few-Step Diffusion Models with Dense Reward Difference Learning](https://mlsanity.com/paper/2411.11727/) (2024)
- [Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model](https://mlsanity.com/paper/2501.02790/) (2025)
- [Discrete Diffusion Trajectory Alignment via Stepwise Decomposition](https://mlsanity.com/paper/2507.04832/) (2025)
- [Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization](https://mlsanity.com/paper/2410.05255/) (2024)
- [Reinforcement Learning for Large Model: A Survey](https://mlsanity.com/paper/2508.08189/) (2025)
- [MIRA: Towards Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion Models](https://mlsanity.com/paper/2510.01549/) (2025)
- [CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2412.13195/) (2024)
- [Towards Better Optimization For Listwise Preference in Diffusion Models](https://mlsanity.com/paper/2510.01540/) (2025)
- [BalancedDPO: Adaptive Multi-Metric Alignment](https://mlsanity.com/paper/2503.12575/) (2025)
- [Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping](https://mlsanity.com/paper/2605.10937/) (2026)
- [Test-Time Preference Optimization for Image Restoration](https://mlsanity.com/paper/2511.19169/) (2025)
- [Direct Diffusion Score Preference Optimization via Stepwise Contrastive Policy-Pair Supervision](https://mlsanity.com/paper/2512.23426/) (2025)
- [Preference Aligned Visuomotor Diffusion Policies for Deformable Object Manipulation](https://mlsanity.com/paper/2602.09583/) (2026)
- [ColorFLUX: A Structure-Color Decoupling Framework for Old Photo Colorization](https://mlsanity.com/paper/2603.28162/) (2026)
- [PromptEcho: Annotation-Free Reward from Vision-Language Models for Text-to-Image Reinforcement Learning](https://mlsanity.com/paper/2604.12652/) (2026)
- [When Preferences Diverge: Aligning Diffusion Models with Minority-Aware Adaptive DPO](https://mlsanity.com/paper/2503.16921/) (2025)
- [Self-NPO: Data-Free Diffusion Model Enhancement via Truncated Diffusion Fine-Tuning](https://mlsanity.com/paper/2505.11777/) (2025)
- [PC-Diffusion: Aligning Diffusion Models with Human Preferences via Preference Classifier](https://mlsanity.com/paper/2511.07806/) (2025)
- [RL-RIG: A Generative Spatial Reasoner via Intrinsic Reflection](https://mlsanity.com/paper/2602.19974/) (2026)
- [Towards General Preference Alignment: Diffusion Models at Nash Equilibrium](https://mlsanity.com/paper/2605.04494/) (2026)
- [SwiftExplorer: Training-free Diffusion Model Alignment with Swift Diversity Exploration](https://mlsanity.com/paper/2609.06651/) (2026)

## Abstract (arXiv)

Aligning large language models with human preferences has emerged as a critical focus in language modeling research. Yet, integrating preference learning into Text-to-Image (T2I) generative models is still relatively uncharted territory. The Diffusion-DPO technique made initial strides by employing pairwise preference learning in diffusion models tailored for specific text prompts. We introduce Diffusion-RPO, a new method designed to align diffusion-based T2I models with human preferences more effectively. This approach leverages both prompt-image pairs with identical prompts and those with semantically related content across various modalities. Furthermore, we have developed a new evaluation metric, style alignment, aimed at overcoming the challenges of high costs, low reproducibility, and limited interpretability prevalent in current evaluations of human preference alignment. Our findings demonstrate that Diffusion-RPO outperforms established methods such as Supervised Fine-Tuning and Diffusion-DPO in tuning Stable Diffusion versions 1.5 and XL-1.0, achieving superior results in both automated evaluations of human preferences and style alignment. Our code is available at https://github.com/yigu1008/Diffusion-RPO