D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples

• URL: http://arxiv.org/abs/2505.22002v1
• Date: Wed, 28 May 2025 06:03:41 GMT
• Title: D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples
• Authors: Zijing Hu, Fengda Zhang, Kun Kuang,
• Abstract summary: This paper introduces D-Fusion, a method to construct DPO-trainable visually consistent samples.<n>On one hand, by performing mask-guided self-attention fusion, the resulting images are not only well-aligned, but also visually consistent with given poorly-aligned images.<n>On the other hand, D-Fusion can retain the denoising trajectories of the resulting images, which are essential for DPO training.
• Score: 23.92307798902212
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The practical applications of diffusion models have been limited by the misalignment between generated images and corresponding text prompts. Recent studies have introduced direct preference optimization (DPO) to enhance the alignment of these models. However, the effectiveness of DPO is constrained by the issue of visual inconsistency, where the significant visual disparity between well-aligned and poorly-aligned images prevents diffusion models from identifying which factors contribute positively to alignment during fine-tuning. To address this issue, this paper introduces D-Fusion, a method to construct DPO-trainable visually consistent samples. On one hand, by performing mask-guided self-attention fusion, the resulting images are not only well-aligned, but also visually consistent with given poorly-aligned images. On the other hand, D-Fusion can retain the denoising trajectories of the resulting images, which are essential for DPO training. Extensive experiments demonstrate the effectiveness of D-Fusion in improving prompt-image alignment when applied to different reinforcement learning algorithms.

Related papers

• Mind the Gap: Aligning Vision Foundation Models to Image Feature Matching [31.42132290162457]
  We introduce a new framework called IMD (Image feature Matching with a pre-trained Diffusion model) with two parts.<n>Unlike the dominant solutions employing contrastive-learning based foundation models that emphasize global semantics, we integrate the generative-based diffusion models.<n>Our proposed IMD establishes a new state-of-the-art in commonly evaluated benchmarks, and the superior 12% improvement in IMIM indicates our method efficiently mitigates the misalignment.
  arXiv  Detail & Related papers  (2025-07-14T14:28:15Z)
• Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion [52.315729095824906]
  MLLM Semantic-Corrected Ping-Pong-Ahead Diffusion (PPAD) is a novel framework that introduces a Multimodal Large Language Model (MLLM) as a semantic observer during inference.<n>It performs real-time analysis on intermediate generations, identifies latent semantic inconsistencies, and translates feedback into controllable signals that actively guide the remaining denoising steps.<n>Extensive experiments demonstrate PPAD's significant improvements.
  arXiv  Detail & Related papers  (2025-05-26T14:42:35Z)
• ADT: Tuning Diffusion Models with Adversarial Supervision [16.974169058917443]
  Diffusion models have achieved outstanding image generation by reversing a forward noising process to approximate true data distributions.<n>We propose Adrial Diffusion Tuning (ADT) to stimulate the inference process during optimization and align the final outputs with training data.<n>ADT features a siamese-network discriminator with a fixed pre-trained backbone and lightweight trainable parameters.
  arXiv  Detail & Related papers  (2025-04-15T17:37:50Z)
• Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction [31.503662384666274]
  In science and engineering, the goal is to infer an unknown image from a small number of measurements collected from a known forward model describing certain imaging modality. Motivated Score-based diffusion models, due to its empirical success, have emerged as an impressive candidate of an exemplary prior in image reconstruction.
  arXiv  Detail & Related papers  (2024-03-25T15:58:26Z)
• Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation [59.184980778643464]
  Fine-tuning Diffusion Models remains an underexplored frontier in generative artificial intelligence (GenAI) In this paper, we introduce an innovative technique called self-play fine-tuning for diffusion models (SPIN-Diffusion) Our approach offers an alternative to conventional supervised fine-tuning and RL strategies, significantly improving both model performance and alignment.
  arXiv  Detail & Related papers  (2024-02-15T18:59:18Z)
• Steerable Conditional Diffusion for Out-of-Distribution Adaptation in Medical Image Reconstruction [75.91471250967703]
  We introduce a novel sampling framework called Steerable Conditional Diffusion.<n>This framework adapts the diffusion model, concurrently with image reconstruction, based solely on the information provided by the available measurement.<n>We achieve substantial enhancements in out-of-distribution performance across diverse imaging modalities.
  arXiv  Detail & Related papers  (2023-08-28T08:47:06Z)
• SDDM: Score-Decomposed Diffusion Models on Manifolds for Unpaired Image-to-Image Translation [96.11061713135385]
  This work presents a new score-decomposed diffusion model to explicitly optimize the tangled distributions during image generation. We equalize the refinement parts of the score function and energy guidance, which permits multi-objective optimization on the manifold. SDDM outperforms existing SBDM-based methods with much fewer diffusion steps on several I2I benchmarks.
  arXiv  Detail & Related papers  (2023-08-04T06:21:57Z)
• Contrast-augmented Diffusion Model with Fine-grained Sequence Alignment for Markup-to-Image Generation [15.411325887412413]
  This paper proposes a novel model named "Contrast-augmented Diffusion Model with Fine-grained Sequence Alignment" (FSA-CDM) FSA-CDM introduces contrastive positive/negative samples into the diffusion model to boost performance for markup-to-image generation. Experiments are conducted on four benchmark datasets from different domains.
  arXiv  Detail & Related papers  (2023-08-02T13:43:03Z)
• Training Diffusion Models with Reinforcement Learning [82.29328477109826]
  Diffusion models are trained with an approximation to the log-likelihood objective. In this paper, we investigate reinforcement learning methods for directly optimizing diffusion models for downstream objectives. We describe how posing denoising as a multi-step decision-making problem enables a class of policy gradient algorithms.
  arXiv  Detail & Related papers  (2023-05-22T17:57:41Z)
• Masked Images Are Counterfactual Samples for Robust Fine-tuning [77.82348472169335]
  Fine-tuning deep learning models can lead to a trade-off between in-distribution (ID) performance and out-of-distribution (OOD) robustness. We propose a novel fine-tuning method, which uses masked images as counterfactual samples that help improve the robustness of the fine-tuning model.
  arXiv  Detail & Related papers  (2023-03-06T11:51:28Z)
• Multiscale Structure Guided Diffusion for Image Deblurring [24.09642909404091]
  Diffusion Probabilistic Models (DPMs) have been employed for image deblurring. We introduce a simple yet effective multiscale structure guidance as an implicit bias. We demonstrate more robust deblurring results with fewer artifacts on unseen data.
  arXiv  Detail & Related papers  (2022-12-04T10:40:35Z)

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.