Skip to content

[CVPR 2024] Official PyTorch implementation of FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition

Notifications You must be signed in to change notification settings

aim-uofa/FreeCustom

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 

Repository files navigation

FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition

Ganggui Ding*, Canyu Zhao*, Wen Wang*, Zhen Yang, Zide Liu, Hao Chen†, Chunhua Shen† (*equal contribution, †corresponding author)

Project Page | Paper

Customized image generation

results_of_multi_concept results_of_single_concept Our method excels at rapidly generating high-quality images with multiple concept combinations and single concept customization, without any model parameter tuning. The identity of each concept is remarkably preserved. Furthermore, our method exhibits great versatility and robustness when dealing with different categories of concepts. This versatility allows users to generate customized images that involve diverse combinations of concepts, catering to their specific needs and preferences. Best viewed on screen.

Code will be released soon

BibTeX

@inproceedings{ding2024freecustom,
  title={FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition}, 
  author={Ganggui Ding and Canyu Zhao and Wen Wang and Zhen Yang and Zide Liu and Hao Chen and Chunhua Shen},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2024}
}

About

[CVPR 2024] Official PyTorch implementation of FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published