https://github.com/SherryXTChen/TiNO-Edit

TiNO-Edit: Timestep and Noise Optimization for Robust Diffusion-Based Image Editing (CVPR 2024)
https://github.com/SherryXTChen/TiNO-Edit

Last synced: 13 days ago
JSON representation

TiNO-Edit: Timestep and Noise Optimization for Robust Diffusion-Based Image Editing (CVPR 2024)

• Host: GitHub
• URL: https://github.com/SherryXTChen/TiNO-Edit
• Owner: SherryXTChen
• License: apache-2.0
• Created: 2024-03-24T18:20:55.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2024-07-07T23:35:39.000Z (4 months ago)
• Last Synced: 2024-08-01T18:33:33.479Z (3 months ago)
• Language: Python
• Homepage:
• Size: 2.24 MB
• Stars: 17
• Watchers: 5
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-diffusion-categorized - [Code

README

        
# TiNO-Edit: Timestep and Noise Optimization for Robust Diffusion-Based Image Editing (CVPR 2024)

[[Arxiv](https://arxiv.org/abs/2404.11120)] [[Poster](https://cvpr.thecvf.com/virtual/2024/poster/31387)] [[Youtube](https://www.youtube.com/watch?v=latSSiMcfds)]

TiNO-Edit is an image editing algorithm built on top of Stable Diffusion (SD) by optimizing noise and timesteps in the SD latent space.

## Capabilities



  

  



## LatentCLIPvis & LatentVGG

LatentCLIPvis and LatentVGG are the SD latent space equivalents of the CLIP vision model and VGG. To train these models, see `latentclip` and `latentvgg` respectively. We will provide an explanation of our code soon. We also provide pretrained checkpoints [here](https://www.dropbox.com/scl/fo/0jdk7kddwtfstpc0gshx4/h?rlkey=wdfejfkf5sho513v8l7ddw2px&st=e3nhfopc&dl=0).

## Method (Code coming soon ...)



  





  



## BibTeX

``` bibtex

@inproceedings{chen2024tino,

  title={TiNO-Edit: Timestep and Noise Optimization for Robust Diffusion-Based Image Editing},

  author={Chen, Sherry X and Vaxman, Yaron and Ben Baruch, Elad and Asulin, David and Moreshet, Aviad and Lien, Kuo-Chin and Sra, Misha and Sen, Pradeep},

  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},

  pages={6337--6346},

  year={2024}

}

```