/SaltAI

Primary LanguagePythonGNU General Public License v3.0GPL-3.0

image

Salt AI

Accelerate your Comfy UI workflow creation, sharing, and scaling.

Overview

This repository offers a comprehensive suite of custom nodes for ComfyUI, a development tool designed for constructing node-based workflows. These workflows are enhanced by various AI models, enabling a wide array of functionalities.

About Salt

  • Mission: TO seamlessly connect people and organizations with the world’s foremost AI innovations, anywhere, anytime.

  • Vision: To foster a flourishing AI ecosystem where the world’s best developers can build and share their work, thereby redefining how software is made, pushing innovation forward, and ensuring as many people as possible can benefit from the positive promise of AI technologies.

  • Belief: We are convinced that ComfyUI serves as a critical instrument in realizing our mission and vision. It offers a platform for exploring AI models' capabilities and limitations in an interactive, visually engaging manner, requiring no coding skills for exploration.

By sharing our nodes and workflows, we aim to motivate and empower a broader audience to craft exceptional AI-driven content using ComfyUI.

🌟 Features

We're going to do our part to regularly release new nodes to help achieve a wide range of tasks. Below you can find some highlights of currently implemented features. This list may not contain all the awesomeness that can be found wtihin the SaltAI repo.

  • LLM Nodes These nodes are in development, but already feature rich allowing the creation of RAG systems, web page readers, prompt engineering, and helper tools such as basic arbitrary data conversion to different formats such as JSON, YAML, Markdown, and HTML without having to set up the LLM yourself.
  • Animation Keyframing These nodes contain float scheduling nodes which can help you with animation procedures. There is a conversion node which will convert float lists to MTB FLOATS format as well.

Documentation

The importance of documentation in mastering any software is well-acknowledged. Bearing this in mind, we are committed to comprehensively documenting all nodes and node packs supported on our platform. This initiative is ongoing, and we invite you to monitor the progress and view our existing documentation on GitHub. If you'd like to contribute, or fix any issues, please see our documentations repository.

🧭 Discover

🤝 Get Involved

Your contributions are valuable! We warmly invite you to join our project, whether you're:

  • 🐛 Identifying and reporting bugs
  • 🛠️ Offering fixes
  • 🚀 Proposing new features or improvements through pull requests

Your participation helps us grow and improve, fostering a collaborative and innovative environment.