ComfyUI  >  Nodes  >  ComfyUI-Qwen-2

ComfyUI Extension: ComfyUI-Qwen-2

Repo Name


ZHO-ZHO-ZHO (Account age: 337 days)
View all nodes (3)
Latest Updated
Github Stars

How to Install ComfyUI-Qwen-2

Install this extension via the ComfyUI Manager by searching for  ComfyUI-Qwen-2
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI-Qwen-2 in the search bar
After installation, click the  Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • High-speed GPU machines
  • 200+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 50+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

ComfyUI-Qwen-2 Description

ComfyUI-Qwen-2 integrates Qwen-2 models into ComfyUI, enabling advanced AI functionalities. It supports seamless model loading, configuration, and execution within the ComfyUI interface, enhancing user experience and efficiency.

ComfyUI-Qwen-2 Introduction

ComfyUI-Qwen-2 is an extension that integrates the Qwen2 language models into the ComfyUI platform. This extension supports two powerful models: Qwen2-7B-Instruct and Qwen2-72B-Instruct. These models are designed to generate and complete prompts, as well as engage in multi-turn conversations. The extension is particularly effective in handling Chinese language inputs and can automatically translate them into English prompts. This makes it a valuable tool for AI artists who want to enhance their creative workflows with advanced language generation capabilities.

How ComfyUI-Qwen-2 Works

ComfyUI-Qwen-2 works by leveraging the Qwen2 language models to process and generate text based on user inputs. The extension includes several nodes that facilitate different functionalities:

  1. ModelLoader Node: This node automatically downloads the required Qwen2 model. It ensures that the model is ready for use by maintaining an active internet connection during the download process.
  2. Qwen2 Node: This node allows users to set system instructions, which guide the model's behavior and responses.
  3. Qwen2 Chat Node: This node supports multi-turn conversations, enabling the model to maintain context across multiple interactions. By using these nodes, AI artists can create complex workflows that involve text generation, prompt completion, and interactive dialogues.

ComfyUI-Qwen-2 Features

ModelLoader Node

  • Function: Automatically downloads the Qwen2 models.
  • Customization: Ensure a stable internet connection for seamless model downloading.
  • Example: Loading the Qwen2-7B-Instruct model, which requires approximately 16GB of VRAM.

Qwen2 Node

  • Function: Supports setting system instructions to guide the model's responses.
  • Customization: Users can input specific instructions to tailor the model's output.
  • Example: Setting an instruction to generate creative writing prompts.

Qwen2 Chat Node

  • Function: Supports multi-turn conversations with system instructions.
  • Customization: Users can engage in dialogues where the model maintains context across multiple turns.
  • Example: Using the node to simulate a conversation with a virtual assistant.

ComfyUI-Qwen-2 Models


  • Description: A smaller model that requires around 16GB of VRAM.
  • Use Case: Suitable for generating and completing prompts quickly.
  • Example: Generating creative writing prompts or short story ideas.


  • Description: A larger model that requires around 160GB of VRAM.
  • Use Case: Ideal for more complex tasks and maintaining context in longer conversations.
  • Example: Engaging in detailed multi-turn conversations or generating extensive text content.

What's New with ComfyUI-Qwen-2

Version 1.0

  • System Instructions: Added support for setting system instructions to guide model behavior.
  • Dual Mode: Supports both single and multi-turn conversation modes.
  • Language Support: Automatically translates Chinese inputs into English prompts. These updates enhance the flexibility and usability of the extension, making it more powerful for AI artists who need advanced text generation capabilities.

Troubleshooting ComfyUI-Qwen-2

Common Issues and Solutions

  1. Model Download Issues:
  • Problem: The model fails to download.
  • Solution: Ensure a stable internet connection and sufficient disk space.
  1. High VRAM Usage:
  • Problem: The model requires more VRAM than available.
  • Solution: Use a machine with higher VRAM or switch to a smaller model like Qwen2-7B-Instruct.
  1. Incorrect Outputs:
  • Problem: The model generates irrelevant or incorrect text.
  • Solution: Adjust the system instructions to better guide the model's responses.

Frequently Asked Questions

  • Q: Can I use the extension offline?
  • A: No, an internet connection is required to download the models initially.
  • Q: How do I switch between single and multi-turn conversation modes?
  • A: Use the Qwen2 Chat node for multi-turn conversations and the Qwen2 node for single-turn interactions.

Learn More about ComfyUI-Qwen-2

For additional resources and support, consider exploring the following:

  • : Access the source code and detailed documentation.
  • : Learn about integrating text display nodes with ComfyUI-Qwen-2. - Community Forums: Join discussions and seek help from other AI artists using the extension. By leveraging these resources, you can maximize the potential of ComfyUI-Qwen-2 in your creative projects.

ComfyUI-Qwen-2 Related Nodes


© Copyright 2024 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals.