Salvato in:
Dettagli Bibliografici
Autori principali: Marjit, Shyam, Singh, Harshit, Mathur, Nityanand, Paul, Sayak, Yu, Chia-Mu, Chen, Pin-Yu
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2402.17412
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910347154161664
author Marjit, Shyam
Singh, Harshit
Mathur, Nityanand
Paul, Sayak
Yu, Chia-Mu
Chen, Pin-Yu
author_facet Marjit, Shyam
Singh, Harshit
Mathur, Nityanand
Paul, Sayak
Yu, Chia-Mu
Chen, Pin-Yu
contents In the realm of subject-driven text-to-image (T2I) generative models, recent developments like DreamBooth and BLIP-Diffusion have led to impressive results yet encounter limitations due to their intensive fine-tuning demands and substantial parameter requirements. While the low-rank adaptation (LoRA) module within DreamBooth offers a reduction in trainable parameters, it introduces a pronounced sensitivity to hyperparameters, leading to a compromise between parameter efficiency and the quality of T2I personalized image synthesis. Addressing these constraints, we introduce \textbf{\textit{DiffuseKronA}}, a novel Kronecker product-based adaptation module that not only significantly reduces the parameter count by 35\% and 99.947\% compared to LoRA-DreamBooth and the original DreamBooth, respectively, but also enhances the quality of image synthesis. Crucially, \textit{DiffuseKronA} mitigates the issue of hyperparameter sensitivity, delivering consistent high-quality generations across a wide range of hyperparameters, thereby diminishing the necessity for extensive fine-tuning. Furthermore, a more controllable decomposition makes \textit{DiffuseKronA} more interpretable and even can achieve up to a 50\% reduction with results comparable to LoRA-Dreambooth. Evaluated against diverse and complex input images and text prompts, \textit{DiffuseKronA} consistently outperforms existing models, producing diverse images of higher quality with improved fidelity and a more accurate color distribution of objects, all the while upholding exceptional parameter efficiency, thus presenting a substantial advancement in the field of T2I generative modeling. Our project page, consisting of links to the code, and pre-trained checkpoints, is available at https://diffusekrona.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2402_17412
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DiffuseKronA: A Parameter Efficient Fine-tuning Method for Personalized Diffusion Models
Marjit, Shyam
Singh, Harshit
Mathur, Nityanand
Paul, Sayak
Yu, Chia-Mu
Chen, Pin-Yu
Computer Vision and Pattern Recognition
In the realm of subject-driven text-to-image (T2I) generative models, recent developments like DreamBooth and BLIP-Diffusion have led to impressive results yet encounter limitations due to their intensive fine-tuning demands and substantial parameter requirements. While the low-rank adaptation (LoRA) module within DreamBooth offers a reduction in trainable parameters, it introduces a pronounced sensitivity to hyperparameters, leading to a compromise between parameter efficiency and the quality of T2I personalized image synthesis. Addressing these constraints, we introduce \textbf{\textit{DiffuseKronA}}, a novel Kronecker product-based adaptation module that not only significantly reduces the parameter count by 35\% and 99.947\% compared to LoRA-DreamBooth and the original DreamBooth, respectively, but also enhances the quality of image synthesis. Crucially, \textit{DiffuseKronA} mitigates the issue of hyperparameter sensitivity, delivering consistent high-quality generations across a wide range of hyperparameters, thereby diminishing the necessity for extensive fine-tuning. Furthermore, a more controllable decomposition makes \textit{DiffuseKronA} more interpretable and even can achieve up to a 50\% reduction with results comparable to LoRA-Dreambooth. Evaluated against diverse and complex input images and text prompts, \textit{DiffuseKronA} consistently outperforms existing models, producing diverse images of higher quality with improved fidelity and a more accurate color distribution of objects, all the while upholding exceptional parameter efficiency, thus presenting a substantial advancement in the field of T2I generative modeling. Our project page, consisting of links to the code, and pre-trained checkpoints, is available at https://diffusekrona.github.io/.
title DiffuseKronA: A Parameter Efficient Fine-tuning Method for Personalized Diffusion Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.17412