[CVPR 2026 Oral] ChordEdit: One-Step Low-Energy Transport for Image Editing

Liangsi Lu¹, Xuhang Chen², Minzhe Guo¹, Shichu Li³, Jingchao Wang⁴, Yang Shi^1†
1 Guangdong University of Technology, ² Huizhou University, ³ Shenzhen University, ⁴ Peking University
^† Corresponding author

• Python 3.12
• PyTorch 2.5.0
• This repository requires the sd-turbo weights: https://huggingface.co/stabilityai/sd-turbo
• Model root should contain:
  • unet/
  • scheduler/
  • text_encoder/
  • tokenizer/
  • vae/

pip install -r requirement.txt

Launch the interactive demo:

python app.py --model-root /path/to/sd-turbo --server-port 7860

Running python app.py now launches a local Gradio web app.

• Left panel: upload the original image, set source prompt, target prompt, and tuning parameters.
• Right panel: view the edited output image.
• Bottom section: click built-in examples (image + source prompt + target prompt) to auto-fill inputs.

Run PIE-Bench export with:

python run_pie_bench.py --model-root /path/to/sd-turbo --pie-root /path/to/pie_bench

--pie-root should point to a PIE-Bench folder containing at least:

1. annotation_images/ — original PIE-Bench images (subfolders keep the official naming).
2. mapping_file.json — the mapping metadata describing prompts, instructions, and masks.

Example layout:

pie_bench
|-annotation_images
|-mapping_file.json

For PIE-Bench data preparation and protocol details, please refer to: https://github.com/cure-lab/PnPInversion

If you find our work helpful, please star 🌟 this repo and cite 📑 our paper. Thanks for your support!

@article{lu2026chordedit,
  title={ChordEdit: One-Step Low-Energy Transport for Image Editing},
  author={Lu, Liangsi and Chen, Xuhang and Guo, Minzhe and Li, Shichu and Wang, Jingchao and Shi, Yang},
  journal={arXiv preprint arXiv:2602.19083},
  year={2026}
}