# Elucidating Optimal Reward-Diversity Tradeoffs in Text-to-Image Diffusion Models

arXiv: https://arxiv.org/abs/2409.06493 · HTML: https://mlsanity.com/paper/2409.06493/

## Key facts

- Cited by 13 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 60 of its 74 references that are in the map.
- First posted on arXiv 9 Sep 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 60)

- [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)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [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)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Variational Diffusion Models](https://mlsanity.com/paper/2107.00630/) (2021)
- [Improved Techniques for Training Score-Based Generative Models](https://mlsanity.com/paper/2006.09011/) (2020)
- [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)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [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)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators](https://mlsanity.com/paper/2303.13439/) (2023)
- [Compositional Visual Generation with Composable Diffusion Models](https://mlsanity.com/paper/2206.01714/) (2022)

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

- [Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models](https://mlsanity.com/paper/2508.09968/) (2025)
- [Scalable Ranked Preference Optimization for Text-to-Image Generation](https://mlsanity.com/paper/2410.18013/) (2024)
- [Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges](https://mlsanity.com/paper/2604.13602/) (2026)
- [Distilling Diversity and Control in Diffusion Models](https://mlsanity.com/paper/2503.10637/) (2025)
- [CoDe: Blockwise Control for Denoising Diffusion Models](https://mlsanity.com/paper/2502.00968/) (2025)
- [ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation](https://mlsanity.com/paper/2503.22194/) (2025)
- [Text-to-Image Synthesis: A Decade Survey](https://mlsanity.com/paper/2411.16164/) (2024)
- [ImageReFL: Balancing Quality and Diversity in Human-Aligned Diffusion Models](https://mlsanity.com/paper/2505.22569/) (2025)
- [Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile Image Generation](https://mlsanity.com/paper/2601.12401/) (2026)
- [DreamBoothDPO: Improving Personalized Generation using Direct Preference Optimization](https://mlsanity.com/paper/2505.20975/) (2025)
- [Policy-based Tuning of Autoregressive Image Models with Instance- and Distribution-Level Rewards](https://mlsanity.com/paper/2603.23086/) (2026)
- [DiVid: Diagnosing Dimension-Specific Diversity Collapse in Video Generation Models](https://mlsanity.com/paper/2610.01661/) (2026)
- [iADD: Improving Alignment and Diversity in Diffusion Policy Optimization](https://mlsanity.com/paper/2610.01789/) (2026)

## Abstract (arXiv)

Text-to-image (T2I) diffusion models have become prominent tools for generating high-fidelity images from text prompts. However, when trained on unfiltered internet data, these models can produce unsafe, incorrect, or stylistically undesirable images that are not aligned with human preferences. To address this, recent approaches have incorporated human preference datasets to fine-tune T2I models or to optimize reward functions that capture these preferences. Although effective, these methods are vulnerable to reward hacking, where the model overfits to the reward function, leading to a loss of diversity in the generated images. In this paper, we prove the inevitability of reward hacking and study natural regularization techniques like KL divergence and LoRA scaling, and their limitations for diffusion models. We also introduce Annealed Importance Guidance (AIG), an inference-time regularization inspired by Annealed Importance Sampling, which retains the diversity of the base model while achieving Pareto-Optimal reward-diversity tradeoffs. Our experiments demonstrate the benefits of AIG for Stable Diffusion models, striking the optimal balance between reward optimization and image diversity. Furthermore, a user study confirms that AIG improves diversity and quality of generated images across different model architectures and reward functions.