The ArtificialSongGenerator automatically composes and compiles the Artifical Audio Multitrack dataset (AAM).

Video generation via code

Post-training with Tinker

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

A unified inference and post-training framework for accelerated video generation.

Deceased Superior Technician archive of music! Def. worth checking out!

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Specification and documentation for the Model Context Protocol

Replace 'hub' with 'ingest' in any github url to get a prompt-friendly extract of a codebase

Open Source DeepWiki: AI-Powered Wiki Generator for GitHub/Gitlab/Bitbucket Repositories. Join the discord: https://discord.gg/gMwThUMeme

A fully local Loveable, Replit, Bolt alternative that you can run with your own LLM. No monthly subscriptions, private by default.

MiniJinja is a powerful but minimal dependency template engine for Rust compatible with Jinja/Jinja2

The world’s fastest framework for building websites.

Comprehensive cross-platform input for GameMaker

Idle thoughts on the game engine I use for my job

Snyk CLI scans and monitors your projects for security vulnerabilities.

Multimodal LLM for text and images

Interactive roadmaps, guides and other educational content to help developers grow in their careers.

High-quality Text-to-Audio Generation with Efficient Diffusion Transformer

Building AI agents, atomically

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer