Please note, ML Lab features have become experimental, and support beyond published documentation is very limited.
Please note that this feature of Runway is experimental 🧪
To run models locally on your computer, you need to download and install them individually. Some local models require you to install Docker. Docker CE is free and open-source software. You do not need Docker to run models remotely!
If you need to install Docker, here are the steps:
Download Docker from the following links:
Docker for Windows requires Microsoft Hyper-V, which is supported only in the Pro, Enterprise, or Education editions of Windows. If you don't have a Pro, Enterprise, or Education Windows edition then you will not be able to install Docker, and you can only run some Runway models.
On Mac: a Docker icon in the top status bar. This indicates that Docker is running and accessible from Runway. Please refer to this official Docker installation guide on Mac if you are having any issues.
A whale in the top status bar indicates that Docker is running.
On Windows: a Docker icon in the bottom notifications area. This indicates that Docker is running and accessible from Runway. If you encounter any issues with Docker on Windows, please check that your Windows Firewall is not affecting Docker. Also, be sure that Windows has at least one Share Drive with Docker. Please refer to this official Docker installation guide on Windows if you continue to have any issues.
Docker icon in the Notifications area or System tray.
On Linux: verify if Docker is installed and running with the following command:
In the bottom status bar inside Runway, look for a whale icon and a message that that Docker is available:
A whale icon in the bottom status bar inside Runway.
If Docker is not installed, unavailable, or not running you will see the following message:
If Docker is not available, Runway will show a "Docker Unavailable" message in the bottom status bar.
Several models require a significant amount of memory in order to run properly. By default, Docker allocates a maximum of 2 GB of memory to run models. Some Runway models exceed that, which may lead to errors. Without enough memory models, may misbehave or fail silently without a helpful error message. To prevent that, you need to increase Docker's memory limit. Follow the steps in this related technical support article: Docker Errors. Having trouble with Docker? Here are few tips.
Related Technical Support Resources:
- Changing Where Local Models are Downloaded
- Deleting Local Models
- Docker Errors. Having trouble with Docker? Here are few tips.
- Running Docker without sudo