# Self-NPO: Data-Free Diffusion Model Enhancement via Truncated Diffusion Fine-Tuning

arXiv: https://arxiv.org/abs/2505.11777 · HTML: https://mlsanity.com/paper/2505.11777/

## Key facts

- Cited by 1 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 36 of its 51 references that are in the map.
- First posted on arXiv 17 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 36)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [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)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Variational Diffusion Models](https://mlsanity.com/paper/2107.00630/) (2021)
- [CAT3D: Create Anything in 3D with Multi-View Diffusion Models](https://mlsanity.com/paper/2405.10314/) (2024)
- [Guiding a Diffusion Model with a Bad Version of Itself](https://mlsanity.com/paper/2406.02507/) (2024)
- [Human Preference Score: Better Aligning Text-to-Image Models with Human Preference](https://mlsanity.com/paper/2303.14420/) (2023)
- [Improving Video Generation with Human Feedback](https://mlsanity.com/paper/2501.13918/) (2025)
- [Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation](https://mlsanity.com/paper/2404.04057/) (2024)
- [Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling](https://mlsanity.com/paper/2401.15977/) (2024)
- [JourneyDB: A Benchmark for Generative Image Understanding](https://mlsanity.com/paper/2307.00716/) (2023)
- [Large-scale Reinforcement Learning for Diffusion Models](https://mlsanity.com/paper/2401.12244/) (2024)
- [DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis](https://mlsanity.com/paper/2405.14224/) (2024)
- [Enhancing Large Vision Language Models with Self-Training on Image Comprehension](https://mlsanity.com/paper/2405.19716/) (2024)
- [Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow](https://mlsanity.com/paper/2410.07303/) (2024)
- [Rethinking the Spatial Inconsistency in Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2404.05384/) (2024)
- [Deep Equilibrium Approaches to Diffusion Models](https://mlsanity.com/paper/2210.12867/) (2022)
- [AnimateLCM: Computation-Efficient Personalized Style Video Generation without Personalized Video Data](https://mlsanity.com/paper/2402.00769/) (2024)
- [GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking](https://mlsanity.com/paper/2501.02690/) (2025)
- [OSV: One Step is Enough for High-Quality Image to Video Generation](https://mlsanity.com/paper/2409.11367/) (2024)
- [Diffusion-RPO: Aligning Diffusion Models through Relative Preference Optimization](https://mlsanity.com/paper/2406.06382/) (2024)
- [Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation](https://mlsanity.com/paper/2403.13745/) (2024)

## Built on by (most cited first, 1 of 1)

- [RealDPO: Real or Not Real, that is the Preference](https://mlsanity.com/paper/2510.14955/) (2025)

## Abstract (arXiv)

Diffusion models have demonstrated remarkable success in various visual generation tasks, including image, video, and 3D content generation. Preference optimization (PO) is a prominent and growing area of research that aims to align these models with human preferences. While existing PO methods primarily concentrate on producing favorable outputs, they often overlook the significance of classifier-free guidance (CFG) in mitigating undesirable results. Diffusion-NPO addresses this gap by introducing negative preference optimization (NPO), training models to generate outputs opposite to human preferences and thereby steering them away from unfavorable outcomes through CFG. However, prior NPO approaches rely on costly and fragile procedures for obtaining explicit preference annotations (e.g., manual pairwise labeling or reward model training), limiting their practicality in domains where such data are scarce or difficult to acquire. In this work, we propose Self-NPO, specifically truncated diffusion fine-tuning, a data-free approach of negative preference optimization by directly learning from the model itself, eliminating the need for manual data labeling or reward model training. This data-free approach is highly efficient (less than 1% training cost of Diffusion-NPO) and achieves comparable performance to Diffusion-NPO in a data-free manner. We demonstrate that Self-NPO integrates seamlessly into widely used diffusion models, including SD1.5, SDXL, and CogVideoX, as well as models already optimized for human preferences, consistently enhancing both their generation quality and alignment with human preferences. Code is available at https://github.com/G-U-N/Diffusion-NPO.