comfyui-ollama

comfyui-ollama
★ 801

ComfyUIOllama大语言模型扩展节点
为 ComfyUI 提供与 Ollama（通过 ollama-python）交互的自定义节点，便于在工作流中调用和整合大语言模型能力。
💡 在 ComfyUI 流程中接入 Ollama 模型进行文本生成与交互
🍴 75 Forks💻 Python🔄 2025-10-23
📦
网盘下载
复制链接后前往夸克网盘下载
https://pan.quark.cn/s/9671236b7e59
📦 requirements.txt
ollama==0.4.5
📄 README

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.

Buy Me A Coffee

Installation

1. Install ollama server on the desired host

Instructions

Download for macOS

Download for Windows

Install on Linux

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

Docker Installation

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

2. Install the custom nodes

Use ComfyUI’s built-in extension manager to install the nodes. Search for comfyui-ollama by Stav Sapir.

Or

If you prefer ComfyUI-Manager, search for ollama and select the one by stavsap

Or

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

    • Configuration (Ollama Key)

    If you are using Ollama Cloud templates that require authentication, you must provide your Ollama public key.

    You can do this automatically with the CLI:

    ollama signin

    Or by manually adding your public key at ollama.com/settings/key.

    Your public key is located at:

    | OS | Path to id_ed25519.pub |

    |—-|———————–|

    | macOS | ~/.ollama/id_ed25519.pub |

    | Linux | /usr/share/ollama/.ollama/id_ed25519.pub |

    | Windows | C:\Users\\.ollama\id_ed25519.pub |

    See Ollama’s FAQ for more details.

    Nodes

    OllamaGenerate

    A node that provides ability to set the system prompt and the prompt.

    Ability to save context locally in the node enable/disable

    Inputs:

  • OllamaConnectivity (optional)
  • OllamaOptions (optional)
  • images (optional)
  • context (optional), a context from other OllamaConnectivity
  • meta (optional), passing metadata of the OllamaConnectivity and OllamaOptions from other OllamaGenerate node.

    • Notes:

  • For this node to be operational, OllamaConnectivity or meta must be inputted!.
  • If images are inputted and a chain of meta usage is made, all the images need to be passed as well to the next OllamaConnectivity nodes.

    • OllamaChat

    A node for conversational interaction using the dedicated Ollama chat endpoint (ollama.chat). It manages the full conversation history natively and allows for chained sequences of chat nodes.

  • Functionality: Unlike OllamaGenerate, this node is designed specifically for multi-turn conversations and cloud models with your Ollama public key (see the Configuration section).
  • Key Features:
  • Conversation history is handled natively within the node instance.
  • Dedicated history outputs for chaining multiple chat nodes.
  • Option to reset the current conversation history on demand.

    • Inputs:

  • OllamaConnectivity (optional)
  • OllamaOptions (optional)
  • images (optional)
  • meta (optional), passing metadata of the OllamaConnectivity and

    • OllamaOptions from other OllamaChat node.

  • history (optional), passing history ID from other OllamaChat node.

    • Outputs:

  • result: The generated text
  • thinking: The thinking text
  • meta: The metadata to pass to the next OllamaChat node
  • history: The history ID to pass to the next OllamaChat node

    • OllamaConnectivity

    A node responsible only fot the connectivity to the ollama server

    OllamaOptions

    A node for full control of the ollama api options.

    For an option to take effect, each option have also enable/disable, enabled options are passed to api call to ollama server.

    Ollama API options can be found in this table.

    Note: There is an additional option debug that enables debug print in the cli, its not part of ollama api.

    Deprecated nodes

    Old V1 nodes are still available, please replace them with the above ones. Here’s the documentation of V1 nodes.

    Usage Example

    Please see the example_workflows folder or use ComfyUI’s template browser.

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