Skip to main content
EXTENDED SEARCH
Log in
Top
Published in:
Read chapter Read first chapter

2025 | OriginalPaper | Chapter

ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs

Authors : Viraj Shah, Nataniel Ruiz, Forrester Cole, Erika Lu, Svetlana Lazebnik, Yuanzhen Li, Varun Jampani

Published in: Computer Vision – ECCV 2024

Publisher: Springer Nature Switzerland

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

ZipLoRA is a groundbreaking method that merges independently trained style and content LoRAs to generate any user-provided subject in any user-provided style using diffusion models. This approach leverages key insights about LoRA weights, such as their sparsity and alignment, to create robust, high-quality merges. ZipLoRA is hyperparameter-free and requires minimal computational resources, making it a practical solution for personalized stylization tasks. The method is demonstrated to outperform existing approaches in terms of both subject and style fidelity, and it maintains the ability to generate individual concepts accurately. Additionally, ZipLoRA exhibits superior performance on the Stable Diffusion XL model, highlighting its potential for real-world applications in artistic and creative domains.
AI Generated

This summary of the content was generated with the help of AI.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Business + Economics & Engineering + Technology"

Online-Abonnement

Springer Professional "Business + Economics & Engineering + Technology" gives you access to:

  • more than 102.000 books
  • more than 537 journals

from the following subject areas:

  • Automotive
  • Construction + Real Estate
  • Business IT + Informatics
  • Electrical Engineering + Electronics
  • Energy + Sustainability
  • Finance + Banking
  • Management + Leadership
  • Marketing + Sales
  • Mechanical Engineering + Materials
  • Insurance + Risk


Secure your knowledge advantage now!

inform now

Springer Professional "Engineering + Technology"

Online-Abonnement

Springer Professional "Engineering + Technology" gives you access to:

  • more than 67.000 books
  • more than 390 journals

from the following specialised fileds:

  • Automotive
  • Business IT + Informatics
  • Construction + Real Estate
  • Electrical Engineering + Electronics
  • Energy + Sustainability
  • Mechanical Engineering + Materials





 

Secure your knowledge advantage now!

inform now

Springer Professional "Business + Economics"

Online-Abonnement

Springer Professional "Business + Economics" gives you access to:

  • more than 67.000 books
  • more than 340 journals

from the following specialised fileds:

  • Construction + Real Estate
  • Business IT + Informatics
  • Finance + Banking
  • Management + Leadership
  • Marketing + Sales
  • Insurance + Risk



Secure your knowledge advantage now!

inform now
previous chapter SMooDi: Stylized Motion Diffusion Model
next chapter SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image Using Latent Video Diffusion
Appendix
This content is only visible if you are logged in and have the appropriate permissions.
Literature
This content is only visible if you are logged in and have the appropriate permissions.
Metadata
Title
ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs
Authors
Viraj Shah
Nataniel Ruiz
Forrester Cole
Erika Lu
Svetlana Lazebnik
Yuanzhen Li
Varun Jampani
Copyright Year
2025
Book
Computer Vision – ECCV 2024

Print ISBN: 978-3-031-73231-7

Electronic ISBN: 978-3-031-73232-4

Copyright Year: 2025

DOI
https://doi.org/10.1007/978-3-031-73232-4_24

Premium Partner

    Image Credits