Manipulate-Anything-QwenVL

This repository provides the implementation for Qwen-VL which is used for Manipulate-Anything.

Installation

Follow the steps below to set up the environment:

Step 1: Clone the Repository

git clone https://github.com/Robot-MA/QWen-VL-MA.git
cd Manipulate-Anything-QwenVL

Step 2: Install Dependencies

Install the required Python packages by running:

pip install -r requirements.txt

Step 3: Download Checkpoints

1. Go to the Qwen-VL-Chat repository on Hugging Face.
2. Download the Qwen-VL-Chat Checkpoints.
3. Place the downloaded checkpoints into the Qwen-VL-Chat directory in this repository.

Step 4: Go back to the main repo

https://github.com/Robot-MA/manipulate-anything and follow the rest of the setup script

Refer to the provided scripts and documentation for usage instructions.

Feel free to open an issue if you encounter any problems during setup or execution.

License

MIT License

Acknowledgements

This project leverages the Qwen-VL-Chat model. Visit the official Qwen-VL-Chat page for more details.

@article{Qwen-VL,
  title={Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond},
  author={Bai, Jinze and Bai, Shuai and Yang, Shusheng and Wang, Shijie and Tan, Sinan and Wang, Peng and Lin, Junyang and Zhou, Chang and Zhou, Jingren},
  journal={arXiv preprint arXiv:2308.12966},
  year={2023}
}