magic-research / InstaDrag

Experiencing lightning fast (~1s) and accurate drag-based image editing

InstaDrag: Lightning Fast and Accurate Drag-based Image Editing Emerging from Videos

Yujun Shi^*    Jun Hao Liew^{*^}    Hanshu Yan    Vincent Y. F. Tan    Jiashi Feng
National University of Singapore   |   ByteDance

^* Equal Contributions    ^{^} Project Lead

If you like our project, please give us a star ⭐ on GitHub for the latest update.

Disclaimer

This is a research project, NOT a commercial product. Users are granted the freedom to create images using this tool, but they are expected to comply with local laws and utilize it in a responsible manner. The developers do NOT assume any responsibility for potential misuse by users.

TODO

• Release inference code and model. We are now going through the open source procedure in the company. We will release the code and model after the procedure is completed (expected 2-4 weeks).
• Integrate with SDXL.

Qualitative Results Gallery

Single-round Dragging

Multi-round Dragging

Contact

For any questions on this project, please contact Yujun ([e-mail]) and Jun Hao ([e-mail])

BibTeX

If you find our repo helpful, please consider leaving a star or cite our paper :)

@article{shi2024instadrag,
         title={InstaDrag: Lightning Fast and Accurate Drag-based Image Editing Emerging from Videos},
         author={Shi, Yujun and Liew, Jun Hao, and Yan, Hanshu and Tan, Vincent YF and Feng, Jiashi},
         journal={arXiv preprint arXiv:2405.13722},
         year={2024}
}

Acknowledgement

Source image samples are collected from unsplash, pexels, pixabay. Also, a huge shout-out to all the amazing open source diffusion models, libraries, and technical reports.