Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization

• URL: http://arxiv.org/abs/2406.04314v2
• Date: Fri, 06 Dec 2024 17:59:18 GMT
• Title: Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization
• Authors: Zhanhao Liang, Yuhui Yuan, Shuyang Gu, Bohan Chen, Tiankai Hang, Mingxi Cheng, Ji Li, Liang Zheng,
• Abstract summary: This paper introduces step-by-step preference optimization (SPO) to improve aesthetics economically. SPO discards the propagation strategy and allows fine-grained image details to be assessed. SPO converges much faster than DPO methods due to the step-by-step alignment of fine-grained visual details.
• Score: 20.698818784349015
• License:
• Abstract: Generating visually appealing images is fundamental to modern text-to-image generation models. A potential solution to better aesthetics is direct preference optimization (DPO), which has been applied to diffusion models to improve general image quality including prompt alignment and aesthetics. Popular DPO methods propagate preference labels from clean image pairs to all the intermediate steps along the two generation trajectories. However, preference labels provided in existing datasets are blended with layout and aesthetic opinions, which would disagree with aesthetic preference. Even if aesthetic labels were provided (at substantial cost), it would be hard for the two-trajectory methods to capture nuanced visual differences at different steps. To improve aesthetics economically, this paper uses existing generic preference data and introduces step-by-step preference optimization (SPO) that discards the propagation strategy and allows fine-grained image details to be assessed. Specifically, at each denoising step, we 1) sample a pool of candidates by denoising from a shared noise latent, 2) use a step-aware preference model to find a suitable win-lose pair to supervise the diffusion model, and 3) randomly select one from the pool to initialize the next denoising step. This strategy ensures that the diffusion models to focus on the subtle, fine-grained visual differences instead of layout aspect. We find that aesthetic can be significantly enhanced by accumulating these improved minor differences. When fine-tuning Stable Diffusion v1.5 and SDXL, SPO yields significant improvements in aesthetics compared with existing DPO methods while not sacrificing image-text alignment compared with vanilla models. Moreover, SPO converges much faster than DPO methods due to the step-by-step alignment of fine-grained visual details. Code and models are available at https://github.com/RockeyCoss/SPO.

Related papers

• Dual Caption Preference Optimization for Diffusion Models [51.223275938663235]
  We propose Dual Caption Preference Optimization (DCPO), a novel approach that utilizes two distinct captions to mitigate irrelevant prompts. Our experiments show that DCPO significantly improves image quality and relevance to prompts, outperforming Stable Diffusion (SD) 2.1, SFT_Chosen, Diffusion-DPO, and MaPO across multiple metrics.
  arXiv  Detail & Related papers  (2025-02-09T20:34:43Z)
• Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization [46.888425016169144]
  Preference optimization for diffusion models aims to align them with human preferences for images. Previous methods typically leverage Vision-Language Models (VLMs) as pixel-level reward models to approximate human preferences. In this work, we demonstrate that diffusion models are inherently well-suited for step-level reward modeling in the latent space. We introduce Latent Preference Optimization (LPO), a method designed for step-level preference optimization directly in the latent space.
  arXiv  Detail & Related papers  (2025-02-03T04:51:28Z)
• Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking [50.325021634589596]
  We propose a Tailored Optimization Preference (TailorPO) framework for aligning diffusion models with human preference. Our approach directly ranks intermediate noisy samples based on their step-wise reward, and effectively resolves the gradient direction issues. Experimental results demonstrate that our method significantly improves the model's ability to generate aesthetically pleasing and human-preferred images.
  arXiv  Detail & Related papers  (2025-02-01T16:08:43Z)
• Personalized Preference Fine-tuning of Diffusion Models [75.22218338096316]
  We introduce PPD, a multi-reward optimization objective that aligns diffusion models with personalized preferences. With PPD, a diffusion model learns the individual preferences of a population of users in a few-shot way. Our approach achieves an average win rate of 76% over Stable Cascade, generating images that more accurately reflect specific user preferences.
  arXiv  Detail & Related papers  (2025-01-11T22:38:41Z)
• Scalable Ranked Preference Optimization for Text-to-Image Generation [76.16285931871948]
  We investigate a scalable approach for collecting large-scale and fully synthetic datasets for DPO training. The preferences for paired images are generated using a pre-trained reward function, eliminating the need for involving humans in the annotation process. We introduce RankDPO to enhance DPO-based methods using the ranking feedback.
  arXiv  Detail & Related papers  (2024-10-23T16:42:56Z)
• Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization [97.35427957922714]
  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. We show that PSO can directly adapt distilled models to human-preferred generation with both offline and online-generated pairwise preference image data.
  arXiv  Detail & Related papers  (2024-10-04T07:05:16Z)
• Diffusion Model Alignment Using Direct Preference Optimization [103.2238655827797]
  Diffusion-DPO is a method to align diffusion models to human preferences by directly optimizing on human comparison data. We fine-tune the base model of the state-of-the-art Stable Diffusion XL (SDXL)-1.0 model with Diffusion-DPO. We also develop a variant that uses AI feedback and has comparable performance to training on human preferences.
  arXiv  Detail & Related papers  (2023-11-21T15:24:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.