This repository contains ComfyUI custom nodes that allow you to leverage the power of Google's Vertex AI models, specifically Veo3 for video generation and Imagen4 for image generation, directly within your ComfyUI workflows.
- Veo3 Node: Generate high-quality videos from text prompts using Google's state-of-the-art Veo3 model.
- Imagen4 Node: Create stunning images from text prompts with Google's powerful Imagen4 model.
Before you can use these custom nodes, you need to have the Google Cloud SDK installed and authenticated on your system.
Follow the official Google Cloud documentation to install the gcloud CLI tool for your operating system:
https://cloud.google.com/sdk/docs/install
After installing the SDK, you need to authenticate your machine. Run the following command in your terminal:
gcloud auth application-default loginThis command will open a web browser where you can log in with your Google account and grant the necessary permissions.
To install these custom nodes, you need to clone this repository into the custom_nodes directory of your ComfyUI installation.
-
Navigate to your ComfyUI installation directory.
-
Go to the
custom_nodesdirectory. -
Clone this repository:
git clone https://github.com/your-username/vertexai-comfyui-api-nodes.git
-
Install the required Python packages for each custom node. Navigate to the directory of each node and run:
pip install -r requirements.txt
For example:
cd vertexai-comfyui-api-nodes/Veo3Custom pip install -r requirements.txt cd ../Imagen4Custom pip install -r requirements.txt
-
Restart ComfyUI.
Once installed, you will find the new nodes in the "Vertex AI" category in ComfyUI.
- Veo3 Node: This node takes a text prompt as input and generates a video. You can use the VHS (Video Helper Suite) for video manipulation and previewing.
- Imagen4 Node: This node takes a text prompt as input and generates an image. You can use the Easy API Nodes for image manipulation and previewing.
This project is licensed under the Apache License 2.0. See the LICENSE file for details.
