Diffusion Model Adaptation

Latest papers

40 papers10 papers in the last four weeks, up 150% on the four weeks before. 0.1% of all new papers.

OrthoFuse: Training-free Riemannian Fusion of Orthogonal Style-Concept Adapters for Diffusion Models
Apr 6, 2026Ali Aliev, Kamil Garifullin, Nikolay Yudin +5Model Merging Diffusion Model Adaptation
HSE University · FusionBrain Lab · AXXX
Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation
Mar 23, 2026Donald Shenaj, Federico Errica, Antonio CartaLow-Rank Adaptation Adaptive Rank Allocation
University of Pisa · NEC Laboratories Europe
Diffusion Controller: Framework, Algorithms and Parameterization
Mar 7, 2026Tong Yang, Moonkyung Ryu, Chih-Wei Hsu +4Diffusion Model Adaptation Diffusion Model Fine-Tuning
Carnegie Mellon University; Intern at Google Research · Google · Yale University
Training-Free Adaptation of Diffusion Models via Doob's $h$ -Transform
Feb 18, 2026Qijie Zhu, Zeqi Ye, Han Liu +2Diffusion Model Adaptation Diffusion Models
Department of Statistics and Data Science, Northwestern University. · Department of Industrial Engineering and Management Sciences, Northwestern University. · Department of Computer Science, Northwestern University.
Efficient Text-Guided Convolutional Adapter for the Diffusion Model
Feb 16, 2026Aryan Das, Koushik Biswas, Swalpa Kumar Roy +2Diffusion Model Adaptation Conditional Image Generation
VIT Bhopal · IIIT Delhi · Tezpur University Assam +1
X2HDR: HDR Image Generation in a Perceptually Uniform Space
Feb 4, 2026Ronghuan Wu, Wanchao Su, Kede Ma +2Image Generation HDR Imaging
City University of Hong Kong, Hong Kong · Monash University, Australia · University of Cambridge, United Kingdom
FeRA: Frequency-Energy Constrained Routing for Effective Diffusion Adaptation Fine-Tuning
Nov 22, 2025Bo Yin, Xiaobin Hu, Xingyu Zhou +7Fine-Tuning Adaptive Model Routing
National University of Singapore · University of Electronic Science and Technology of China · Nanyang Technological University +4
Inverse-and-Edit: Simple and Effective Framework for Fast Image Editing
Jun 23, 2025Ilia Beletskii, Andrey Kuznetsov, Aibek AlanovText-Guided Image Editing Diffusion-Based Image Editing
HSE University, AIRI · AIRI, Sber, Innopolis
Low-dimensional adaptation of diffusion models: Convergence in total variation
Jan 22, 2025Jiadong Liang, Zhihan Huang, Yuxin ChenDiffusion Sampling Diffusion Models
Department of Statistics and Data Science, the Wharton School, University of Pennsylvania
FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model
Oct 17, 2024ZiDong Wang, Zeyu Lu, Di Huang +4Image Generation Diffusion-Based Image Generation
Shanghai AI Laboratory, Shanghai, 200000, China. · Chinese University of Hong Kong, Shatin, 999077, Hong Kong. · Shanghai Jiao Tong University, Shanghai, 200000, China. +2

Apr 6, 2026J/K move · Enter open · S save

OrthoFuse: Training-free Riemannian Fusion of Orthogonal Style-Concept Adapters for Diffusion Models

Ali Aliev, Kamil Garifullin, Nikolay Yudin, Vera Soboleva+4

HSE University · FusionBrain Lab · AXXX

Model Merging Diffusion Model Adaptation Diffusion Model Fine-Tuning Diffusion Models Fine-Tuning Orthogonal Representation Learning

Open paper AskPDF arXiv

In a rapidly growing field of model training there is a constant practical interest in parameter-efficient fine-tuning and various techniques that use a small amount of training data to adapt the model to a narrow task. However, there is an open question: how to combine several adapters tuned for different tasks into one which is able to yield adequate results on both tasks? Specifically, merging subject and style adapters for generative models remains unresolved. In this paper we seek to show that in the case of orthogonal fine-tuning (OFT), we can use structured orthogonal parametrization and its geometric properties to get the formulas for training-free adapter merging. In particular, we derive the structure of the manifold formed by the recently proposed Group-and-Shuffle (

\mathcal{GS}

) orthogonal matrices, and obtain efficient formulas for the geodesics approximation between two points. Additionally, we propose a

\text{spectra restoration}

transform that restores spectral properties of the merged adapter for higher-quality fusion. We conduct experiments in subject-driven generation tasks showing that our technique to merge two

\mathcal{GS}

orthogonal matrices is capable of uniting concept and style features of different adapters. To the best of our knowledge, this is the first training-free method for merging multiplicative orthogonal adapters. Code is available via the link.