Sign in

Nodes Browser

ComfyDeploy: How ComfyUI-VLM_Captions works in ComfyUI?

What is ComfyUI-VLM_Captions?

A simple ComfyUI node that let's you use Claude or ChatGPT 4o's VLM capabilities to generate captions/tags for images.

How to install it in ComfyDeploy?

Head over to the machine page

  1. Click on the "Create a new machine" button
  2. Select the Edit build steps
  3. Add a new step -> Custom Node
  4. Search for ComfyUI-VLM_Captions and select it
  5. Close the build step dialig and then click on the "Save" button to rebuild the machine

ComfyUI-VLM-Captions

A simple ComfyUI node that let's you use Claude or ChatGPT 4o's VLM capabilities to generate captions/tags for images.

Installation

  • git clone this repository into Comfyui/custom_nodes/

Usage

The node accepts an image and a prompt as inputs to generate captions. The input image is automatically resized to 512 pixels to optimize performance and reduce costs. To generate a caption, provide a prompt such as "Create a concise description for the given image" in the text field. Be sure to replace the placeholder API key with your own to enable functionality.

Workflow Example

image Right click > Convert widget to input to convert conditioning text box into a node input