Nodes Browser
ComfyDeploy: How ComfyUI DeepSeek_R1 Chat Node works in ComfyUI?
What is ComfyUI DeepSeek_R1 Chat Node?
A custom node for ComfyUI that integrates DeepSeek's powerful chat and instruction API, enabling seamless AI interactions within your ComfyUI workflows.
How to install it in ComfyDeploy?
Head over to the machine page
- Click on the "Create a new machine" button
- Select the
Edit
build steps - Add a new step -> Custom Node
- Search for
ComfyUI DeepSeek_R1 Chat Node
and select it - Close the build step dialig and then click on the "Save" button to rebuild the machine
ComfyUI DeepSeek_R1 Chat Node
A custom node for ComfyUI that integrates DeepSeek's powerful chat and instruction API, enabling seamless AI interactions within your ComfyUI workflows.
Features
-
Dual Operating Modes
- Chat mode with conversation memory
- Single-turn instruction mode
-
Vision Integration
- Support for image context through vision descriptions
- Seamless integration with ComfyUI's visual workflows
-
Advanced Configuration
- Customizable max token limit (up to 8192 tokens)
- Optional reasoning display
- Configurable chat history management
- Built-in rate limiting protection
Installation
- Clone this repository into your ComfyUI custom nodes directory:
cd ComfyUI/custom_nodes
git clone https://github.com/ShmuelRonen/comfyui-deepseek-chat.git
-
Get your DeepSeek API key:
- Go to platform.deepseek.com/api_keys
- Sign in or create an account
- Generate a new API key
- Copy the key
-
Edit the
config.json
file in the node directory:
{
"deepseek_api_key": "your-api-key-here"
}
Important
Check API availability on this site: [DeepSeek API status](https://platform.deepseek.com/
Usage
Node Configuration
The node provides several input parameters:
- mode: Choose between "chat" and "instruct"
- prompt: Your input text/question
- max_tokens: Maximum response length (1-8192)
- show_reasoning: Toggle reasoning display
- clear_history: Option to reset conversation
- remember_chat: Enable/disable chat history persistence
- vision_description: Optional image context description. This can be used to:
- Provide image descriptions for visual context
- Connect with image generation nodes
- Enable vision-language tasks
- Process image analysis results
Example Workflow
- Add the "DeepSeek-V3 Chat/Instruct" node to your workflow
- Configure the node parameters
- Connect it to other nodes as needed
- Execute the workflow
Outputs
The node provides two outputs:
latest_response
: The most recent AI responsefull_chat_history
: Complete conversation history
Rate Limiting
The node implements a 1-second minimum interval between requests to comply with API limits.
Error Handling
- Comprehensive error logging
- Graceful handling of API failures
- Clear error messages in node outputs
Technical Details
API Integration
API Endpoint: https://api.deepseek.com/v1/chat/completions
Model: deepseek-reasoner
- Supports full chat context with message history
- Handles authentication via API key
- Implements rate limiting protection
File Structure
comfyui-deepseek-chat/
├── deepseek_chat_node.py
├── config.json
├── chat_history.json
└── README.md
Dependencies
- Python 3.6+
- requests library
- ComfyUI environment
Contributing
- Fork the repository
- Create your feature branch
- Commit your changes
- Push to the branch
- Open a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- Built for ComfyUI
- Powered by DeepSeek's API
- Inspired by community needs for AI integration in visual workflows