Instructions to use LuckyOda/comfyui-carbonara-bundle with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use LuckyOda/comfyui-carbonara-bundle with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="LuckyOda/comfyui-carbonara-bundle", filename="models/text_encoders/qwen-4b-zimage-heretic-q8.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use LuckyOda/comfyui-carbonara-bundle with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf LuckyOda/comfyui-carbonara-bundle # Run inference directly in the terminal: llama cli -hf LuckyOda/comfyui-carbonara-bundle
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf LuckyOda/comfyui-carbonara-bundle # Run inference directly in the terminal: llama cli -hf LuckyOda/comfyui-carbonara-bundle
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf LuckyOda/comfyui-carbonara-bundle # Run inference directly in the terminal: ./llama-cli -hf LuckyOda/comfyui-carbonara-bundle
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf LuckyOda/comfyui-carbonara-bundle # Run inference directly in the terminal: ./build/bin/llama-cli -hf LuckyOda/comfyui-carbonara-bundle
Use Docker
docker model run hf.co/LuckyOda/comfyui-carbonara-bundle
- LM Studio
- Jan
- Ollama
How to use LuckyOda/comfyui-carbonara-bundle with Ollama:
ollama run hf.co/LuckyOda/comfyui-carbonara-bundle
- Unsloth Studio
How to use LuckyOda/comfyui-carbonara-bundle with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for LuckyOda/comfyui-carbonara-bundle to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for LuckyOda/comfyui-carbonara-bundle to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for LuckyOda/comfyui-carbonara-bundle to start chatting
- Pi
How to use LuckyOda/comfyui-carbonara-bundle with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf LuckyOda/comfyui-carbonara-bundle
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "LuckyOda/comfyui-carbonara-bundle" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use LuckyOda/comfyui-carbonara-bundle with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf LuckyOda/comfyui-carbonara-bundle
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default LuckyOda/comfyui-carbonara-bundle
Run Hermes
hermes
- Atomic Chat new
- OpenClaw new
How to use LuckyOda/comfyui-carbonara-bundle with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf LuckyOda/comfyui-carbonara-bundle
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "LuckyOda/comfyui-carbonara-bundle" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
- Docker Model Runner
How to use LuckyOda/comfyui-carbonara-bundle with Docker Model Runner:
docker model run hf.co/LuckyOda/comfyui-carbonara-bundle
- Lemonade
How to use LuckyOda/comfyui-carbonara-bundle with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull LuckyOda/comfyui-carbonara-bundle
Run and chat with the model
lemonade run user.comfyui-carbonara-bundle-{{QUANT_TAG}}List all available models
lemonade list
| # SPDX-License-Identifier: MIT | |
| # Copyright (C) 2025 ComfyUI-Multiband Contributors | |
| """Load Multiband Image from path node.""" | |
| import os | |
| import hashlib | |
| from ..multiband_types import MULTIBAND_IMAGE, numpy_to_multiband | |
| from ..utils.io_numpy import load_numpy, load_npz | |
| from ..utils.io_tiff import load_tiff | |
| from ..utils.io_exr import load_exr, is_available as exr_available | |
| class LoadMultibandFromPath: | |
| """ | |
| Load a multi-band image from an absolute file path (STRING input). | |
| Supports: .npy, .npz, .tiff, .tif, .exr | |
| """ | |
| def INPUT_TYPES(cls): | |
| return { | |
| "required": { | |
| "file_path": ("STRING", { | |
| "default": "", | |
| "tooltip": "Absolute path to multiband file (.npz, .npy, .tiff, .exr)" | |
| }), | |
| }, | |
| "optional": { | |
| "normalize": ("BOOLEAN", { | |
| "default": False, | |
| "tooltip": "Normalize values to [0, 1] range" | |
| }), | |
| } | |
| } | |
| RETURN_TYPES = (MULTIBAND_IMAGE, "INT", "STRING") | |
| RETURN_NAMES = ("multiband", "num_channels", "channel_names") | |
| FUNCTION = "load" | |
| CATEGORY = "multiband/io" | |
| def load(self, file_path: str, normalize: bool = False): | |
| if not os.path.exists(file_path): | |
| raise FileNotFoundError(f"File not found: {file_path}") | |
| ext = os.path.splitext(file_path)[1].lower() | |
| if ext == '.npy': | |
| arr, channel_names, metadata = load_numpy(file_path, normalize) | |
| elif ext == '.npz': | |
| arr, channel_names, metadata = load_npz(file_path, normalize) | |
| elif ext in ('.tiff', '.tif'): | |
| arr, channel_names, metadata = load_tiff(file_path, normalize) | |
| elif ext == '.exr': | |
| if not exr_available(): | |
| raise ImportError("OpenEXR not installed. Install with: pip install OpenEXR") | |
| arr, channel_names, metadata = load_exr(file_path, normalize) | |
| else: | |
| raise ValueError(f"Unsupported file format: {ext}") | |
| multiband = numpy_to_multiband(arr, channel_names, metadata) | |
| num_channels = multiband['samples'].shape[1] | |
| names_str = ",".join(multiband['channel_names']) | |
| return (multiband, num_channels, names_str) | |
| def IS_CHANGED(cls, file_path, normalize=False): | |
| if not os.path.exists(file_path): | |
| return "" | |
| m = hashlib.sha256() | |
| with open(file_path, 'rb') as f: | |
| m.update(f.read()) | |
| return m.digest().hex() | |