# A Simple and Effective Reinforcement Learning Method for Text-to-Image Diffusion Fine-tuning

arXiv: https://arxiv.org/abs/2503.00897 · HTML: https://mlsanity.com/paper/2503.00897/

## Key facts

- Cited by 30 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 38 of its 57 references that are in the map.
- First posted on arXiv 2 Mar 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)
- Deep reinforcement learning methods / [RL with diffusion and flow models](https://mlsanity.com/deeprl/rl-with-diffusion-and-flow-models/)

## Builds on (most cited first, 30 of 38)

- [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)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [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)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Constrained Policy Optimization](https://mlsanity.com/paper/1705.10528/) (2017)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [Compositional Visual Generation with Composable Diffusion Models](https://mlsanity.com/paper/2206.01714/) (2022)
- [Aligning Text-to-Image Models using Human Feedback](https://mlsanity.com/paper/2302.12192/) (2023)
- [Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis](https://mlsanity.com/paper/2212.05032/) (2022)
- [Monte Carlo Gradient Estimation in Machine Learning](https://mlsanity.com/paper/1906.10652/) (2019)
- [Geometric Latent Diffusion Models for 3D Molecule Generation](https://mlsanity.com/paper/2305.01140/) (2023)
- [Efficient Diffusion Policies for Offline Reinforcement Learning](https://mlsanity.com/paper/2305.20081/) (2023)
- [Token-level Direct Preference Optimization](https://mlsanity.com/paper/2404.11999/) (2024)
- [DPO Meets PPO: Reinforced Token Optimization for RLHF](https://mlsanity.com/paper/2404.18922/) (2024)
- [Reinforcement Learning for Long-Horizon Interactive LLM Agents](https://mlsanity.com/paper/2502.01600/) (2025)
- [Aligning Diffusion Models by Optimizing Human Utility](https://mlsanity.com/paper/2404.04465/) (2024)
- [Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design](https://mlsanity.com/paper/2410.13643/) (2024)
- [Amortizing intractable inference in diffusion models for vision, language, and control](https://mlsanity.com/paper/2405.20971/) (2024)
- [A Dense Reward View on Aligning Text-to-Image Diffusion with Preference](https://mlsanity.com/paper/2402.08265/) (2024)

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

- [Flow-GRPO: Training Flow Matching Models via Online RL](https://mlsanity.com/paper/2505.05470/) (2025)
- [X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again](https://mlsanity.com/paper/2507.22058/) (2025)
- [RewardDance: Reward Scaling in Visual Generation](https://mlsanity.com/paper/2509.08826/) (2025)
- [RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning](https://mlsanity.com/paper/2505.17540/) (2025)
- [Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion Reinforcement Learning](https://mlsanity.com/paper/2512.24146/) (2025)
- [GARDO: Reinforcing Diffusion Models without Reward Hacking](https://mlsanity.com/paper/2512.24138/) (2025)
- [TR2-D2: Tree Search Guided Trajectory-Aware Fine-Tuning for Discrete Diffusion](https://mlsanity.com/paper/2509.25171/) (2025)
- [UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation](https://mlsanity.com/paper/2603.23500/) (2026)
- [Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advances](https://mlsanity.com/paper/2508.10316/) (2025)
- [The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation](https://mlsanity.com/paper/2511.20256/) (2025)
- [Iterative Distillation for Reward-Guided Fine-Tuning of Diffusion Models in Biomolecular Design](https://mlsanity.com/paper/2507.00445/) (2025)
- [Identity-GRPO: Optimizing Multi-Human Identity-preserving Video Generation via Reinforcement Learning](https://mlsanity.com/paper/2510.14256/) (2025)
- [Reinforcement Learning for Large Model: A Survey](https://mlsanity.com/paper/2508.08189/) (2025)
- [PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling](https://mlsanity.com/paper/2512.04784/) (2025)
- [LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories](https://mlsanity.com/paper/2604.15311/) (2026)
- [Embedding-perturbed Exploration Preference Optimization for Flow Models](https://mlsanity.com/paper/2605.15803/) (2026)
- [MultiCrafter: High-Fidelity Multi-Subject Generation via Disentangled Attention and Identity-Aware Preference Alignment](https://mlsanity.com/paper/2509.21953/) (2025)
- [Alignment and Safety of Diffusion Models via Reinforcement Learning and Reward Modeling: A Survey](https://mlsanity.com/paper/2505.17352/) (2025)
- [T2I-Eval-R1: Reinforcement Learning-Driven Reasoning for Interpretable Text-to-Image Evaluation](https://mlsanity.com/paper/2505.17897/) (2025)
- [Parallel Diffusion Solver via Residual Dirichlet Policy Optimization](https://mlsanity.com/paper/2512.22796/) (2025)
- [What Happens Next? Next Scene Prediction with a Unified Video Model](https://mlsanity.com/paper/2512.13015/) (2025)
- [Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards](https://mlsanity.com/paper/2603.00918/) (2026)
- [Critic-Guided Reinforcement Unlearning in Text-to-Image Diffusion](https://mlsanity.com/paper/2601.03213/) (2026)
- [Temporal Difference Learning for Diffusion Models](https://mlsanity.com/paper/2606.15048/) (2026)
- [Constraints-Guided Diffusion Reasoner for Neuro-Symbolic Learning](https://mlsanity.com/paper/2508.16524/) (2025)
- [Safe, Efficient, and Robust Reinforcement Learning for Ranking and Diffusion Models](https://mlsanity.com/paper/2510.15429/) (2025)
- [ReDiF: Reinforced Distillation for Few Step Diffusion](https://mlsanity.com/paper/2512.22802/) (2025)
- [Explicit Critic Guidance for Aligning Diffusion Models](https://mlsanity.com/paper/2605.27736/) (2026)
- [LeanGRPO: Eliminating Redundant Recomputation in Diffusion RL](https://mlsanity.com/paper/2609.03528/) (2026)
- [Panoptic Scene Program Diffusion Transformer](https://mlsanity.com/paper/2609.31780/) (2026)

## Abstract (arXiv)

Reinforcement learning (RL)-based fine-tuning has emerged as a powerful approach for aligning diffusion models with black-box objectives. Proximal policy optimization (PPO) is a popular choice of method for policy optimization. While effective in terms of performance and sample complexity, PPO is highly sensitive to hyper-parameters and involves substantial computational overhead. REINFORCE, on the other hand, mitigates some implementation complexities such as high memory overhead and sensitive hyper-parameter tuning, but has suboptimal performance due to high variance and crucially sample inefficiency, which is the primary notion of efficiency we study in this work. While the variance of the REINFORCE can be reduced by sampling multiple actions per input prompt and using a baseline correction term, it still suffers from sample inefficiency. To address these challenges, we systematically analyze the sample efficiency-effectiveness trade-off between REINFORCE and PPO, and propose leave-one-out PPO ( LOOP), a novel RL for diffusion fine-tuning method. LOOP combines variance reduction techniques from REINFORCE, such as sampling multiple actions per input prompt and a baseline correction term, with the robustness and sample efficiency of PPO via clipping and importance sampling. Our results demonstrate that LOOP effectively improves diffusion models on various black-box objectives, and achieves a better balance between sample efficiency and final performance.