# Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization

arXiv: https://arxiv.org/abs/2410.03190 · HTML: https://mlsanity.com/paper/2410.03190/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 65 of its 76 references that are in the map.
- First posted on arXiv 4 Oct 2024.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 30 of 65)

- [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)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [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)
- [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2211.01095/) (2022)
- [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Adversarial Diffusion Distillation](https://mlsanity.com/paper/2311.17042/) (2023)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [Pseudo Numerical Methods for Diffusion Models on Manifolds](https://mlsanity.com/paper/2202.09778/) (2022)
- [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (2024)
- [Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion](https://mlsanity.com/paper/2310.02279/) (2023)

## Built on by (most cited first, 26 of 26)

- [Distribution Matching Distillation Meets Reinforcement Learning](https://mlsanity.com/paper/2511.13649/) (2025)
- [Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models](https://mlsanity.com/paper/2508.09968/) (2025)
- [D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models](https://mlsanity.com/paper/2605.05204/) (2026)
- [Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning](https://mlsanity.com/paper/2503.06339/) (2025)
- [MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Models](https://mlsanity.com/paper/2505.19415/) (2025)
- [Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning](https://mlsanity.com/paper/2511.20549/) (2025)
- [Reward Fine-Tuning Two-Step Diffusion Models via Learning Differentiable Latent-Space Surrogate Reward](https://mlsanity.com/paper/2411.15247/) (2024)
- [SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization](https://mlsanity.com/paper/2412.05095/) (2024)
- [Learnable Sparsity for Vision Generative Models](https://mlsanity.com/paper/2412.02852/) (2024)
- [Reinforcing Few-step Generators via Reward-Tilted Distribution Matching](https://mlsanity.com/paper/2605.26108/) (2026)
- [TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward](https://mlsanity.com/paper/2603.07700/) (2026)
- [MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators](https://mlsanity.com/paper/2607.15273/) (2026)
- [Faster and Better Alignment for Flow Matching Models via Step-aware Advantages](https://mlsanity.com/paper/2602.01591/) (2026)
- [Drifting Preference Optimization for One-Step Generative Models](https://mlsanity.com/paper/2606.02521/) (2026)
- [Coeff-Tuning: A Graph Filter Subspace View for Tuning Attention-Based Large Models](https://mlsanity.com/paper/2503.18337/) (2025)
- [Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning](https://mlsanity.com/paper/2505.20107/) (2025)
- [DreamBoothDPO: Improving Personalized Generation using Direct Preference Optimization](https://mlsanity.com/paper/2505.20975/) (2025)
- [Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation](https://mlsanity.com/paper/2511.18281/) (2025)
- [Sparse Fine-Tuning of Transformers for Generative Tasks](https://mlsanity.com/paper/2507.10855/) (2025)
- [MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency](https://mlsanity.com/paper/2510.25897/) (2025)
- [Rdm: Re-conceptualizing Distribution Matching as a Reward for Diffusion Distillation](https://mlsanity.com/paper/2603.28460/) (2026)
- [Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs](https://mlsanity.com/paper/2605.09433/) (2026)
- [In-Context Compositional Learning via Sparse Coding Transformer](https://mlsanity.com/paper/2511.20194/) (2025)
- [SelfLift: Accelerating Few-Step Diffusion via Self-Recovering Resolution Transition](https://mlsanity.com/paper/2609.02036/) (2026)
- [FestDPO: Few-step Generator Alignment with Direct Preference Optimization](https://mlsanity.com/paper/2609.34673/) (2026)
- [Salvation Lies Within: Eliciting Inherent Style Transfer in Step-Distilled Diffusion Models](https://mlsanity.com/paper/2610.05066/) (2026)

## Abstract (arXiv)

Recent advancements in timestep-distilled diffusion models have enabled high-quality image generation that rivals non-distilled multi-step models, but with significantly fewer inference steps. While such models are attractive for applications due to the low inference cost and latency, fine-tuning them with a naive diffusion objective would result in degraded and blurry outputs. An intuitive alternative is to repeat the diffusion distillation process with a fine-tuned teacher model, which produces good results but is cumbersome and computationally intensive; the distillation training usually requires magnitude higher of training compute compared to fine-tuning for specific image styles. In this paper, we present an algorithm named pairwise sample optimization (PSO), which enables the direct fine-tuning of an arbitrary timestep-distilled diffusion model. PSO introduces additional reference images sampled from the current time-step distilled model, and increases the relative likelihood margin between the training images and reference images. This enables the model to retain its few-step generation ability, while allowing for fine-tuning of its output distribution. We also demonstrate that PSO is a generalized formulation which can be flexibly extended to both offline-sampled and online-sampled pairwise data, covering various popular objectives for diffusion model preference optimization. We evaluate PSO in both preference optimization and other fine-tuning tasks, including style transfer and concept customization. We show that PSO can directly adapt distilled models to human-preferred generation with both offline and online-generated pairwise preference image data. PSO also demonstrates effectiveness in style transfer and concept customization by directly tuning timestep-distilled diffusion models.