ComfyUI Extension: ComfyUI-fal-Connector
The ComfyUI-fal-Connector is a tool designed to provide an integration between ComfyUI and fal. This extension allows users to execute their ComfyUI workflows directly on a/fal.ai. This enables users to leverage the computational power and resources provided by fal.ai for running their ComfyUI workflows.
Custom Nodes (8)
README
ComfyUI-fal-Connector
The ComfyUI-fal-Connector is a tool designed to provide an integration between
ComfyUI and fal. This extension allows users to execute their ComfyUI
workflows directly on fal.ai. This enables users to leverage the
computational power and resources provided by fal.ai for running their
ComfyUI workflows.
Usage
Installation:
- Cloning the required repositories: Clone the ComfyUI-fal and install the required dependencies using the
provided requirements.txt file.
ComfyUI-falrepository includes all the necessary custom extensions including this one.
git clone --recursive https://github.com/badayvedat/ComfyUI-fal.git
cd ComfyUI-fal
pip install -r requirements.txt
-
Set up credentials:
- Generate a
falAPI key from fal dashboard - (Optional) Get your Hugging Face token from Hugging Face settings
- Add these credentials to the
fal-config.inifile in theComfyUI-fal/custom_nodes/ComfyUI-fal-Connectordirectory:
[fal] application_name = fal-ai/comfy-server/stream api_key = your-fal-api-key [huggingface] token = your-huggingface-token # Optional - Generate a
[!WARNING] The
fal-config.inifile is not in the root directory of theComfyUI-falrepository, but in theComfyUI-fal/custom_nodes/ComfyUI-fal-Connectordirectory.
-
Start the Comfy Server: Run the
main.pyfile to start the Comfy server and initiate the connector. -
Execute Workflows: Use ComfyUI to create and configure your AI workflows. When ready, execute the workflows directly on
falusing the connector.
How to use it outside of ComfyUI?
After you set up a workflow, and made sure it is working properly. You can generate a
"fal format" using Save as fal format button. Then you can post the generated JSON
to https://fal.run/fal-ai/comfy-server to execute it and obtain the results.