A collective list of free APIs

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

Focus on prompting and generating

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Let us control diffusion models!

Open-Sora: Democratizing Efficient Video Production for All

OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw). OpenViking unifies the management of context (memory, resources, and skills) that Agents need th…

Fully automatic censorship removal for language models

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

A logical, reasonably standardized, but flexible project structure for doing and sharing data science work.

Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.

Supercharge Your Model Training

😎 A curated list of awesome MLOps tools

NanoGPT (124M) in 2 minutes

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

Compute FID scores with PyTorch.

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Muon is an optimizer for hidden layers in neural networks

PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control

set prompt to divided region

Simulation of spiking neural networks (SNNs) using PyTorch.

Official repository for our work on micro-budget training of large-scale diffusion models.

Open-source implementations of OpenAI Gym MuJoCo environments for use with the OpenAI Gym Reinforcement Learning Research Platform.

A suite of test scenarios for multi-agent reinforcement learning.

The Prodigy optimizer and its variants for training neural networks.