ComfyUI Extension: Ollama and Llava Vision integration for ComfyUI

Authored by fairy-root

Created

Updated

17 stars

Ollama and Llava / vision integration for ComfyUI

Custom Nodes (1)

README

ComfyUI Ollama Integration

This repository, maintained by fairy-root, provides custom nodes for ComfyUI, integrating with the Ollama API for language model interactions and offering text manipulation capabilities.

<div align="center"> <img src="imgs/nodes.png"> </div>

Installation Guide

Features

  • Ollama Chat: Interact with Ollama's language models, including streaming and logging capabilities.
  • Concatenate Text LLMs: Concatenate instructional text with prompts, offering customizable text formatting.
  • Ollama Vision: Loads Llava model and interacts with loaded images based on the user prompts.

Installation

Requirements

Steps

  1. Installing the node:
  • Goto ComfyUI/custom_nodes dir in terminal(cmd)
  • Clone the repository 
    git clone https://github.com/fairy-root/comfyui-ollama-llms.git
  • Restart ComfyUI
  1. Install required Python packages: 
    pip install ollama

Getting Started

Obtaining Ollama Model

Phi3 is just an example since it is small and fast. You can choose any other models as well.

  • To use the Load Ollama LLms node, you'll need to install Ollama. Visit Ollama and install the Ollama App for your OS, then in the terminal use the command: 
    ollama pull phi3
    or 
    ollama run phi3

Donation

Your support is appreciated:

  • USDt (TRC20): TGCVbSSJbwL5nyXqMuKY839LJ5q5ygn2uS
  • BTC: 13GS1ixn2uQAmFQkte6qA5p1MQtMXre6MT
  • ETH (ERC20): 0xdbc7a7dafbb333773a5866ccf7a74da15ee654cc
  • LTC: Ldb6SDxUMEdYQQfRhSA3zi4dCUtfUdsPou

Author and Contact

License

This project is licensed under the MIT License. See the LICENSE file for details.

Contributing

Contributions are welcome! Please open an issue or submit a pull request for any improvements or features.