ComfyUI Extension: ComfyUI BuimenLabo - Unified Package
Comprehensive collection of ComfyUI custom nodes: 🦙 Advanced LLM text generation with Llama-CPP (CPU/GPU acceleration), 🌐 Smart multi-language prompt translation (Google/DeepL/Yandex/Baidu), 🌍 20-language interface toggle, 📸 AI-powered Gemini pose analysis, 🎛️ Smart ControlNet management. Perfect unified package for AI artists and creators. Blog: https://note.com/hirodream44
Custom Nodes (0)
README
🚀 ComfyUI BuimenLabo - Unified Package
📖 Visit the author's blog: https://note.com/hirodream44
🎓 Learn ComfyUI custom node development: ComfyUI Custom Node Tutorial Series
A comprehensive collection of ComfyUI custom nodes that brings together powerful AI tools in one unified package. This package demonstrates practical custom node development techniques covered in the author's tutorial series, with detailed usage guides and examples available on the blog.
✨ Features
🦙 Advanced LLM Text Generation
- Llama-CPP All-In-One: Complete text generation solution with one-click controls
- Multiple Models: Support for CPU/GPU acceleration with llama-cpp-python
- Smart UI: Generate, Reset, and Unload buttons with real-time result viewer
- Memory Management: Automatic VRAM cleanup and model caching
🌐 Smart Prompt Translation
- Multi-Provider Support: Google Translate (free), DeepL, Yandex, Baidu
- One-Click Translation: Direct translation buttons with token counting
- 20+ Languages: Comprehensive language support
- API Key Management: Secure local storage of API credentials
🌍 Multi-Language Interface
- 20 Language Support: Switch ComfyUI interface between 20 languages
- Floating Toggle: Draggable language switcher in top-right corner
- Quick Switch: Left-click for EN ↔ Last Language, Right-click for full menu
- Persistent Settings: Remembers your language preference
🎛️ Smart ControlNet Management
- Multi-ControlNet Loader: Load multiple ControlNet models efficiently
- SD/SDXL Support: Works with both Stable Diffusion versions
- Easy Configuration: Simple dropdown selection interface
📸 AI-Powered Pose Analysis
- Gemini Integration: Advanced pose analysis using Google's Gemini API
- 22 Language Support: Descriptions in your preferred language
- Flexible Analysis: Full body, face focus, or detailed pose analysis
- Natural Language Output: Human-readable pose descriptions
🛠️ Installation
Method 1: ComfyUI Manager (Recommended)
- Open ComfyUI Manager
- Search for "BuimenLabo"
- Click Install
- Restart ComfyUI
Method 2: Manual Installation
- Navigate to
ComfyUI/custom_nodes/
- Clone this repository:
git clone https://github.com/YOUR_USERNAME/comfyui-builmenlabo.git
- Run the installation script:
cd comfyui-builmenlabo ./install.bat # Windows
- Restart ComfyUI
🔧 Quick Setup
LLM Text Generation
- Download GGUF models from HuggingFace
- Place models in
ComfyUI/models/llm/
(auto-created) - Recommended:
Qwen2.5-7B-Instruct-Q8_0.gguf
Gemini Pose Analyzer
- Get API key from Google AI Studio
- Enter key in the node's API field
- Upload images for pose analysis
Prompt Translation
- Google: Works without API key (free service)
- DeepL: Get key from DeepL API
- API keys are stored locally and remembered
📋 Available Nodes
| Node | Description | Category | |------|-------------|----------| | 🦙 Llama-CPP All-In-One | Complete LLM text generation | Text | | 🦙 Llama-CPP Loader | Load LLM models | Model | | 🦙 Llama-CPP Generate | Generate text | Text | | 🦙 Llama-CPP Unload | Unload from VRAM | Memory | | 🌐 Prompt Translator | Multi-language translation | Text | | 🎛️ Multi ControlNet Loader | Load multiple ControlNets | Model | | 📸 Gemini Pose Analyzer | AI pose analysis | Analysis |
🎯 Usage Tips
LLM Generation
- Use Generate button for instant text generation
- Reset button restores default settings
- Unload button frees VRAM when done
- Adjust GPU layers based on your VRAM
Translation
- Try Google first (no API key needed)
- DeepL provides higher quality for supported languages
- Translation results are cached to avoid repeated API calls
Language Toggle
- Drag the 🌐 button to reposition
- Left-click for quick EN ↔ Previous language
- Right-click for full language menu
🔍 Troubleshooting
Common Issues
- Language toggle not showing: Refresh browser (F5)
- VRAM issues: Lower GPU layers or use smaller models
- API errors: Check internet connection and API keys
- Installation issues: Run as administrator
GPU Support
- NVIDIA: Use CUDA installation option
- AMD: Use ROCm installation (experimental)
- Apple Silicon: Use Metal installation
- CPU Only: Universal but slower
📝 Requirements
- ComfyUI (latest version)
- Python 3.8+
- For GPU acceleration: CUDA 11.8+ or ROCm 5.4+
🔗 Links
- Blog: https://note.com/hirodream44
- Support: Submit issues via ComfyUI Manager
- Updates: Check ComfyUI Manager for latest version
📄 License
This project is licensed under the MIT License.
Made with ❤️ by BuimenLabo
Bringing AI tools together for creative workflows