Step-aware Preference Optimization: Aligning Preference with Denoising Performance at Each Step

Arxiv Paper

Github Code

Project Page

Abstract

Recently, Direct Preference Optimization (DPO) has extended its success from aligning large language models (LLMs) to aligning text-to-image diffusion models with human preferences. Unlike most existing DPO methods that assume all diffusion steps share a consistent preference order with the final generated images, we argue that this assumption neglects step-specific denoising performance and that preference labels should be tailored to each step's contribution.

To address this limitation, we propose Step-aware Preference Optimization (SPO), a novel post-training approach that independently evaluates and adjusts the denoising performance at each step, using a step-aware preference model and a step-wise resampler to ensure accurate step-aware supervision. Specifically, at each denoising step, we sample a pool of images, find a suitable win-lose pair, and, most importantly, randomly select a single image from the pool to initialize the next denoising step. This step-wise resampler process ensures the next win-lose image pair comes from the same image, making the win-lose comparison independent of the previous step. To assess the preferences at each step, we train a separate step-aware preference model that can be applied to both noisy and clean images.

Our experiments with Stable Diffusion v1.5 and SDXL demonstrate that SPO significantly outperforms the latest Diffusion-DPO in aligning generated images with complex, detailed prompts and enhancing aesthetics, while also achieving more than 20× times faster in training efficiency. Code and model: https://rockeycoss.github.io/spo.github.io/

Model Description

This model is fine-tuned from runwayml/stable-diffusion-v1-5. It has been trained on 4,000 prompts for 10 epochs. This checkpoint is a LoRA checkpoint. For more information, please visit here

Citation

If you find our work useful, please consider giving us a star and citing our work.

@article{liang2024step,
  title={Step-aware Preference Optimization: Aligning Preference with Denoising Performance at Each Step},
  author={Liang, Zhanhao and Yuan, Yuhui and Gu, Shuyang and Chen, Bohan and Hang, Tiankai and Li, Ji and Zheng, Liang},
  journal={arXiv preprint arXiv:2406.04314},
  year={2024}
}