How to Use CogVideo

CogVideo Online Usage

Experience the power of CogVideo through our online platform with the following steps:

  1. Navigate to the corresponding service URL:
  2. Wait for resources to load (depending on your network, it might take a few seconds).
  3. Choose the input type (Text, Image, or Video) and upload the corresponding file.
  4. Adjust the parameters according to your requirements (e.g., video duration, quality, etc.).
  5. Click the Generate button and enjoy the results!

With CogVideo Online, you can effortlessly generate AI-powered videos from your text, images, or existing videos!

CogVideo Local Usage

If you prefer running CogVideo on your local machine, follow the steps below to set up and use it:

  1. Clone the repository from GitHub:
    git clone https://github.com/THUDM/CogVideo.git
  2. Install the required dependencies. Ensure you have Python 3.8+ and PyTorch installed:
    pip install -r requirements.txt
  3. Download the pretrained CogVideo models:
    python download.py
  4. Run the CogVideo script:
    python cogvideo_demo.py
  5. Access the local web interface by navigating to http://localhost:8000 in your browser.

For more advanced usage or to customize the parameters, refer to the official GitHub documentation.