Skip to content

kk42yy/FIA-Edit

Repository files navigation

FIA-Edit

[AAAI 2026] FIA-Edit: Frequency-Interactive Attention for Efficient and High-Fidelity Inversion-Free Text-Guided Image Editing

🚀 Getting Started

Environment

conda create -n FSI-Edit python=3.12 -y
conda activate FSI-Edit
conda install conda install pytorch==2.2.0 torchvision==0.17.0 torchaudio==2.2.0 pytorch-cuda=11.8 -c pytorch -c nvidia
pip install -r requirements.txt

Benchmark Download ⬇️

Please refer to PIE-Bench.

Running Scripts

Inference

Run PIE-Bench

source Infer.sh

Run Single Image

python run_FIA-Edit.py

Evaluation

source Evaluate.sh

Comparison Results

FlowEdit and Our results are here, the rest of our comparision results can be found FSI-Edit and PnP Inversion.

🤝🏼 Cite Us

@article{yang2025fia,
  title={FIA-Edit: Frequency-Interactive Attention for Efficient and High-Fidelity Inversion-Free Text-Guided Image Editing},
  author={Yang, Kaixiang and Shen, Boyang and Li, Xin and Dai, Yuchen and Luo, Yuxuan and Ma, Yueran and Fang, Wei and Li, Qiang and Wang, Zhiwei},
  journal={arXiv preprint arXiv:2511.12151},
  year={2025}
}

💖 Acknowledgement

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors