Skip to content

Latest commit

 

History

History
57 lines (45 loc) · 2.4 KB

README.md

File metadata and controls

57 lines (45 loc) · 2.4 KB
Raw

FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition

[Paper] [Project Page]

Sicheng Mo1*, Fangzhou Mu2*, Kuan Heng Lin1, Yanli Liu3, Bochen Guan3, Yin Li2, Bolei Zhou1
1 UCLA, 2 University of Wisconsin-Madison, 3 Innopeak Technology, Inc
* Equal contribution
Computer Vision and Pattern Recognition (CVPR), 2024

teaser

Getting Started

Environment Setup

conda env create -f environment.yml
conda activate freecontrol

Sample Semantic Bases

  • We provide two example file under the scripts folder as an example of how to compute target semantic bases.
  • You can also download from google drive to use our pre-computed bases.
  • After downloading the file, you can put it under the dataset folder and use the gradio demo.

Gradio demo

  • We provide the user interface for testing out method. Ruuning the following commend to start the demo.
python gradio_app.py

Galley:

We are building a gallery generated with FreeControl. You are wellcomed to share your generated images with us.

Contact

Sicheng Mo (smo3@cs.ucla.edu)

Reference

@article{mo2023freecontrol,
  title={FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition},
  author={Mo, Sicheng and Mu, Fangzhou and Lin, Kuan Heng and Liu, Yanli and Guan, Bochen and Li, Yin and Zhou, Bolei},
  journal={arXiv preprint arXiv:2312.07536},
  year={2023}
}