ComfyUI Extension: Custom nodes for llm chat with optional image input
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
A custom node for ComfyUI that enables Large Language Model (LLM) chat interactions with optional image input support.
Looking for a different extension?
Custom Nodes (0)
README
ComfyUI LLM Chat Node
A custom node for ComfyUI that enables Large Language Model (LLM) chat interactions with optional image input support. This node allows you to interact with various text and vision language models directly within your ComfyUI workflows.
<img src="assets/node.jpg" width="400"/>
Features
- Support for both text-only and vision-enabled language models
- Configurable model parameters (temperature, max tokens)
- Optional image input support
- Adjustable random seed for consistent outputs
- Easy integration with existing ComfyUI workflows
Installation and Usage
- Navigate to ComfyUI/custom_nodes folder in terminal or command prompt.
- Clone the repo using the following command:
git clone https://github.com/ComfyUI-Workflow/ComfyUI-OpenAI - Go to
custom_nodes/COMFYUI-LLM-APIand install depedencies by runningpip install -r requirements.txt - Restart ComfyUI
Example use cases:

Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.