Source-Prior-Driven Selective Adaptation for Efficient Diffusion Model Finetuning

• URL: http://arxiv.org/abs/2607.20913v1
• Date: Thu, 23 Jul 2026 04:46:48 GMT
• Title: Source-Prior-Driven Selective Adaptation for Efficient Diffusion Model Finetuning
• Abstract summary: We propose a novel source-prior-driven selective adaptation method to efficiently fine-tune diffusion models.<n>Our method relies on two key observations: (1) the loss of general generative capability is highly inconsistent across pretrained parameters, and (2) parameters that have a relatively small impact on the model's general generative capability remain structurally inconsistent.<n> Experiments show that our method achieves a better adaptation-retention trade-off than existing strong baselines.
• Score: 8.882340997244558
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fine-tuning large diffusion models for new domains or styles involves a trade-off: improving target-specific generation often degrades the pretrained model's broad generative capability. Existing full and parameter-efficient fine-tuning methods typically handle this trade-off only implicitly. In this work, we propose a novel source-prior-driven selective adaptation method to efficiently fine-tune diffusion models, achieving a favorable trade-off. Our method relies on two key observations: (1) the loss of general generative capability is highly inconsistent across pretrained parameters, and (2) parameters that have a relatively small impact on the model's general generative capability remain structurally inconsistent across layers and parameter types. Motivated by these observations, we first learn a static mask to explicitly identify parameters better suited for downstream adaptation, and then construct structured update strategies for the selected subset. Experiments show that our method achieves a better adaptation-retention trade-off than existing strong baselines.

Related papers

• Preserving Domain Generalization in Fine-Tuning via Joint Parameter Selection [26.366275954455514]
  We introduce Joint Selection (JPS), a novel method that restricts updates to a small subset of parameters, thereby retaining and harnessing the strength of pre-trained models.<n>JPS achieves superior performance compared to state-of-the-art domain generalization methods, substantiating both the efficiency and efficacy of the proposed approach.
  arXiv  Detail & Related papers  (2025-08-23T10:00:45Z)
• Divergence Minimization Preference Optimization for Diffusion Model Alignment [66.31417479052774]
  Divergence Minimization Preference Optimization (DMPO) is a principled method for aligning diffusion models by minimizing reverse KL divergence.<n>DMPO can consistently outperform or match existing techniques across different base models and test sets.
  arXiv  Detail & Related papers  (2025-07-10T07:57:30Z)
• Diffusion-NPO: Negative Preference Optimization for Better Preference Aligned Generation of Diffusion Models [32.586647934400105]
  We argue that existing preference alignment methods neglect the critical role of handling unconditional/negative-conditional outputs.<n>We propose a straightforward but versatile effective approach that involves training a model specifically attuned to negative preferences.<n>Our approach integrates seamlessly with models such as SD1.5, SDXL, video diffusion models and models that have undergone preference optimization.
  arXiv  Detail & Related papers  (2025-05-16T13:38:23Z)
• InPO: Inversion Preference Optimization with Reparametrized DDIM for Efficient Diffusion Model Alignment [12.823734370183482]
  We introduce DDIM-InPO, an efficient method for direct preference alignment of diffusion models.<n>Our approach conceptualizes diffusion model as a single-step generative model, allowing us to fine-tune the outputs of specific latent variables selectively.<n> Experimental results indicate that our DDIM-InPO achieves state-of-the-art performance with just 400 steps of fine-tuning.
  arXiv  Detail & Related papers  (2025-03-24T08:58:49Z)
• GeneralizeFormer: Layer-Adaptive Model Generation across Test-Time Distribution Shifts [58.95913531746308]
  We consider the problem of test-time domain generalization, where a model is trained on several source domains and adjusted on target domains never seen during training.<n>We propose to generate multiple layer parameters on the fly during inference by a lightweight meta-learned transformer, which we call textitGeneralizeFormer.
  arXiv  Detail & Related papers  (2025-02-15T10:10:49Z)
• Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement [0.7558576228782637]
  We propose a framework for efficient Source-Free Domain Adaptation (SFDA)<n>Our approach introduces an improved paradigm for source-model preparation and target-side adaptation.<n>We demonstrate that our framework is compatible with various SFDA methods and achieves significant computational efficiency.
  arXiv  Detail & Related papers  (2024-10-03T02:12:03Z)
• SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation [52.6922833948127]
  In this work, we investigate the importance of parameters in pre-trained diffusion models.<n>We propose a novel model fine-tuning method to make full use of these ineffective parameters.<n>Our method enhances the generative capabilities of pre-trained models in downstream applications.
  arXiv  Detail & Related papers  (2024-09-10T16:44:47Z)
• Spectrum-Aware Parameter Efficient Fine-Tuning for Diffusion Models [73.88009808326387]
  We propose a novel spectrum-aware adaptation framework for generative models. Our method adjusts both singular values and their basis vectors of pretrained weights. We introduce Spectral Ortho Decomposition Adaptation (SODA), which balances computational efficiency and representation capacity.
  arXiv  Detail & Related papers  (2024-05-31T17:43:35Z)
• On the Effectiveness of Parameter-Efficient Fine-Tuning [79.6302606855302]
  Currently, many research works propose to only fine-tune a small portion of the parameters while keeping most of the parameters shared across different tasks. We show that all of the methods are actually sparse fine-tuned models and conduct a novel theoretical analysis of them. Despite the effectiveness of sparsity grounded by our theory, it still remains an open problem of how to choose the tunable parameters.
  arXiv  Detail & Related papers  (2022-11-28T17:41:48Z)
• Variational Model Perturbation for Source-Free Domain Adaptation [64.98560348412518]
  We introduce perturbations into the model parameters by variational Bayesian inference in a probabilistic framework. We demonstrate the theoretical connection to learning Bayesian neural networks, which proves the generalizability of the perturbed model to target domains.
  arXiv  Detail & Related papers  (2022-10-19T08:41:19Z)

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.