Sign in

Nodes Browser

ComfyDeploy: How ComfyUI Ollama works in ComfyUI?

What is ComfyUI Ollama?

Custom ComfyUI Nodes for interacting with [a/Ollama](https://ollama.com/) using the [a/ollama python client](https://github.com/ollama/ollama-python). Integrate the power of LLMs into CompfyUI workflows easily.

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 Ollama and select it
  5. Close the build step dialig and then click on the "Save" button to rebuild the machine

ComfyUI Ollama

Custom ComfyUI Nodes for interacting with Ollama using the ollama python client.

Integrate the power of LLMs into ComfyUI workflows easily or just experiment with LLM inference.

To use this properly, you would need a running Ollama server reachable from the host that is running ComfyUI.

<a href="https://www.buymeacoffee.com/stavsapq" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/default-orange.png" alt="Buy Me A Coffee" height="40" width="174"></a>

Installation

Install ollama server on the desired host

<a href="https://ollama.com/" target="_blank"> <img src="https://img.shields.io/badge/v0.4.2-green.svg?style=for-the-badge&labelColor=gray&label=Ollama&color=blue" alt=""/> </a>

<a href="https://ollama.com/download/Ollama-darwin.zip" target="_blank">Download for macOS</a>

<a href="https://ollama.com/download/OllamaSetup.exe" target="_blank">Download for Windows</a>

Install on Linux

curl -fsSL https://ollama.com/install.sh | sh

<a href="https://hub.docker.com/r/ollama/ollama" target="_blank">Docker Installation</a>

CPU only

docker run -d -p 11434:11434 -v ollama:/root/.ollama --name ollama ollama/ollama

NVIDIA GPU

docker run -d -p 11434:11434 --gpus=all -v ollama:/root/.ollama --name ollama  ollama/ollama

Use the compfyui manager "Custom Node Manager":

pic

Search ollama and select the one by stavsap

pic

Or

  1. git clone into the custom_nodes folder inside your ComfyUI installation or download as zip and unzip the contents to custom_nodes/compfyui-ollama.
  2. pip install -r requirements.txt
  3. Start/restart ComfyUI

Nodes

OllamaVision

A node that gives an ability to query input images.

pic

A model name should be model with Vision abilities, for example: https://ollama.com/library/llava.

OllamaGenerate

A node that gives an ability to query an LLM via given prompt.

pic

OllamaGenerateAdvance

A node that gives an ability to query an LLM via given prompt with fine tune parameters and an ability to preserve context for generate chaining.

Check ollama api docs to get info on the parameters.

More params info

pic

Usage Example

Consider the following workflow of vision an image, and perform additional text processing with desired LLM. In the OllamaGenerate node set the prompt as input.

pic

The custom Text Nodes in the examples can be found here: https://github.com/pythongosssss/ComfyUI-Custom-Scripts