2025-11-24 15:40:40 +08:00
2025-11-24 12:12:35 +08:00
2025-11-24 16:13:31 +08:00
2025-11-24 12:12:35 +08:00
2025-11-24 12:51:44 +08:00
2025-11-24 12:12:35 +08:00
2025-11-24 12:12:35 +08:00
2025-11-24 18:26:18 +08:00
2025-11-24 12:12:35 +08:00
2025-11-24 16:22:09 +08:00
2025-11-24 18:06:29 +08:00
2025-11-24 16:22:09 +08:00

ComfyUI-Chord

arXiv Project Page Code

ComfyUI custom node for the paper: Chord: Chain of Rendering Decomposition for PBR Material Estimation from Generated Texture Images

Installation

  1. Download and install ComfyUI. If you are new to ComfyUI, refer to the original repository to get started. Make sure you have the latest version.

  2. Download the pretrained model from Hugging Face and place the file chord_v1.ckpt in the folder ./ComfyUI/models/checkpoints.

  3. Install the custom nodes from the ComfyUI-Manager or manually clone this repository in the custom nodes folder, with the argument --recursive:

    # Clone the repository
    cd ./ComfyUI/custom_nodes
    git clone --recursive https://github.com/ubisoft/ComfyUI-Chord.git
    
    # Install dependencies
    ## For Python version
    pip install -r .\ComfyUI-Chord\requirements.txt
    
    ## Or for Windows portable version
    ..\..\python_embeded\python.exe -s -m pip install -r .\ComfyUI-Chord\requirements.txt
    

Example Workflow

You can load this workflow using the JSON file examples/chord_example.json or by dropping the image in ComfyUI.

Example workflow

License

This project is released under the Ubisoft Machine Learning License (Research-Only - Copyleft). See the full terms in the LICENSE file.

Citation

If you find our work useful, please consider citing:

@misc{ying2025chord,
    title={Chord: Chain of Rendering Decomposition for PBR Material Estimation from Generated Texture Images}, 
    author={Zhi Ying and Boxiang Rong and Jingyu Wang and Maoyuan Xu},
    year={2025},
    eprint={2509.09952},
    archivePrefix={arXiv},
    primaryClass={cs.GR},
    url={https://arxiv.org/abs/2509.09952}, 
}

© [2025] Ubisoft Entertainment. All Rights Reserved.

S
Description
No description provided
Readme
3.9 MiB
Languages
Python 100%