ComfyUI-Qwen

ComfyUI-Qwen 🐼

Where Figma meets VSCode: Artistic vision meets engineering precision —— a romantic manifesto from designers to the code world.
✨ The Qwen3 ComfyUI Integration is a powerful tool designed specifically for ComfyUI workflows, aiming to seamlessly integrate Qwen series large language models (LLMs). This component provides both single-turn generation and multi-turn conversation nodes, supporting advanced features such as automatic model download, intelligent memory management, and a "thinking mode". ✨

Star History Model Download

---

🚀 Why Choose ComfyUI-Qwen?

At the intersection of creativity and technology, ComfyUI-Qwen serves as your intelligent creative companion. Through an intuitive visual interface, it seamlessly integrates Qwen series large language models, empowering creators, developers, and AI enthusiasts with powerful multimodal generation capabilities.

🌟 Key Features

Feature Category	Detailed Description
Model Support	Comprehensive coverage of Qwen3 series models (from 0.6B to 235B, catering to various scenarios)
Intelligent Device Adaptation	Automatically detects the optimal running device (GPU/CPU/MPS) and optimizes configuration
Dual-source Accelerated Download	Automatically selects the fastest download source (Hugging Face/ModelScope) with resume support
Quantization Technology	Supports 4-bit/8-bit quantization, significantly reducing VRAM requirements (min 2GB VRAM)
Thinking Mode	Enhances complex task processing capabilities with transparent reasoning and customizable thinking markers

💻 Installation

1. Navigate to the custom_nodes directory of ComfyUI
2. Clone this repository:

   git clone https://github.com/SXQBW/ComfyUI-Qwen3.git
   

3. Install dependencies:

   cd ComfyUI-Qwen3
   pip install -r requirements.txt
   

4. Restart ComfyUI

🎯 Examples

Multi-turn Conversation Node (Qwen Conversation)

This node supports full multi-turn conversations, maintaining conversation history, suitable for chatbot applications and prompt expansion in image generation workflows:

alt text

Prompt expansion result 1 for Flux image generation

alt text

Prompt expansion result 2 for Flux image generation

alt text

1. Select the model version (Qwen3-7B recommended by default)
2. Choose the quantization level (4-bit for low VRAM devices, 8-bit balances precision and performance)
3. Enable or disable "thinking mode" (suitable for complex reasoning tasks)
4. Enter your prompt text
5. Adjust the maximum generation length
6. Choose whether to unload the model after generation to free up resources

Single-turn Generation Node (Qwen Generation)

This node focuses on single text generation, suitable for prompt engineering, text expansion, and other tasks:

Single-turn generation node example 1

alt text

Single-turn generation node example 2 alt text

1. Select the model version
2. Choose the quantization level
3. Enable or disable "thinking mode"
4. Enter your prompt text
5. Adjust the maximum generation length
6. Choose whether to unload the model after generation to free up resources

🛠️ Technical Details

Memory Management

The component automatically detects your dev