Instructions to use vidfom/Ltx-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use vidfom/Ltx-3 with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="vidfom/Ltx-3", filename="ComfyUI/models/text_encoders/gemma-3-12b-it-qat-UD-Q4_K_XL.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use vidfom/Ltx-3 with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf vidfom/Ltx-3:UD-Q4_K_XL # Run inference directly in the terminal: llama-cli -hf vidfom/Ltx-3:UD-Q4_K_XL
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf vidfom/Ltx-3:UD-Q4_K_XL # Run inference directly in the terminal: llama-cli -hf vidfom/Ltx-3:UD-Q4_K_XL
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 vidfom/Ltx-3:UD-Q4_K_XL # Run inference directly in the terminal: ./llama-cli -hf vidfom/Ltx-3:UD-Q4_K_XL
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 vidfom/Ltx-3:UD-Q4_K_XL # Run inference directly in the terminal: ./build/bin/llama-cli -hf vidfom/Ltx-3:UD-Q4_K_XL
Use Docker
docker model run hf.co/vidfom/Ltx-3:UD-Q4_K_XL
- LM Studio
- Jan
- Ollama
How to use vidfom/Ltx-3 with Ollama:
ollama run hf.co/vidfom/Ltx-3:UD-Q4_K_XL
- Unsloth Studio new
How to use vidfom/Ltx-3 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 vidfom/Ltx-3 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 vidfom/Ltx-3 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for vidfom/Ltx-3 to start chatting
- Docker Model Runner
How to use vidfom/Ltx-3 with Docker Model Runner:
docker model run hf.co/vidfom/Ltx-3:UD-Q4_K_XL
- Lemonade
How to use vidfom/Ltx-3 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull vidfom/Ltx-3:UD-Q4_K_XL
Run and chat with the model
lemonade run user.Ltx-3-UD-Q4_K_XL
List all available models
lemonade list
ComfyUI-Manager: Node Database (node_db)
This directory contains the JSON database files that power ComfyUI-Manager's legacy node registry system. While the manager is gradually transitioning to the online Custom Node Registry (CNR), these local JSON files continue to provide important metadata about custom nodes, models, and their integrations.
Directory Structure
The node_db directory is organized into several subdirectories, each serving a specific purpose:
- dev/: Development channel files with latest additions and experimental nodes
- legacy/: Historical/legacy nodes that may require special handling
- new/: New nodes that have passed initial verification but are still being evaluated
- forked/: Forks of existing nodes with modifications
- tutorial/: Example and tutorial nodes designed for learning purposes
Core Database Files
Each subdirectory contains a standard set of JSON files:
- custom-node-list.json: Primary database of custom nodes with metadata
- extension-node-map.json: Maps between extensions and individual nodes they provide
- model-list.json: Catalog of models that can be downloaded through the manager
- alter-list.json: Alternative implementations of nodes for compatibility or functionality
- github-stats.json: GitHub repository statistics for node popularity metrics
Database Schema
custom-node-list.json
{
"custom_nodes": [
{
"title": "Node display name",
"name": "Repository name",
"reference": "Original repository if forked",
"files": ["GitHub URL or other source location"],
"install_type": "git",
"description": "Description of the node's functionality",
"pip": ["optional pip dependencies"],
"js": ["optional JavaScript files"],
"tags": ["categorization tags"]
}
]
}
extension-node-map.json
{
"extension-id": [
["list", "of", "node", "classes"],
{
"author": "Author name",
"description": "Extension description",
"nodename_pattern": "Optional regex pattern for node name matching"
}
]
}
Transition to Custom Node Registry (CNR)
This local database system is being progressively replaced by the online Custom Node Registry (CNR), which provides:
- Real-time updates without manual JSON maintenance
- Improved versioning support
- Better security validation
- Enhanced metadata
The Manager supports both systems simultaneously during the transition period.
Implementation Details
- The database follows a channel-based architecture for different sources
- Multiple database modes are supported: Channel, Local, and Remote
- The system supports differential updates to minimize bandwidth usage
- Security levels are enforced for different node installations based on source
Usage in the Application
The Manager's backend uses these database files to:
- Provide browsable lists of available nodes and models
- Resolve dependencies for installation
- Track updates and new versions
- Map node classes to their source repositories
- Assess risk levels for installation security
Maintenance Scripts
Each subdirectory contains a scan.sh script that assists with:
- Scanning repositories for new nodes
- Updating metadata
- Validating database integrity
- Generating proper JSON structures
This database system enables a flexible, secure, and comprehensive management system for the ComfyUI ecosystem while the transition to CNR continues.