This repository is a curated list of resources for creating art and music with machine learning, targeting artists, creative coders, and researchers interested in generative AI. It provides a comprehensive overview of influential people, projects, articles, learning materials, and libraries in the field of ML art.

How It Works

The list compiles a wide array of ML techniques applied to creative domains, including generative adversarial networks (GANs) for visual art, recurrent neural networks (RNNs) for music generation, and style transfer algorithms. It highlights projects that explore novel interactions between AI and human creativity, such as real-time performance systems and interactive tools for artists.

Quick Start & Requirements

• Installation: Primarily involves browsing the curated links. Specific projects may require Python, TensorFlow, PyTorch, or JavaScript environments.
• Prerequisites: Varies by project; some require specific ML libraries, while others are browser-based.
• Resources: Links to projects like Magenta, TensorFlow.js, and ml5.js offer accessible entry points.

Highlighted Details

• Features prominent figures in ML art like Mario Klingemann, Anna Ridler, and Gene Kogan.
• Curates projects spanning visual art (e.g., art-DCGAN, Fast Style Transfer) and music (e.g., Magenta, Infinite Drum Machine, Performance RNN).
• Includes links to academic workshops and influential articles discussing the intersection of AI and art.
• Highlights libraries like ml5.js and TensorFlow.js designed to make ML accessible to artists.

Maintenance & Community

The list is community-driven, with contributions welcome. It references key organizations and initiatives like Google's Magenta and Artists and Machine Intelligence program.

Licensing & Compatibility

The content of this repository is licensed under Creative Commons Attribution 3.0. Individual projects linked within the list will have their own licenses.

Limitations & Caveats

This is a curated list, not a runnable software project. The "awesome-lint" TODO suggests potential for improved organization. Some linked projects may be experimental or have specific hardware/software requirements.