Stars
Minimalistic 4D-parallelism distributed training framework for education purpose
A generative world for general-purpose robotics & embodied AI learning.
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA
Official inference repo for FLUX.1 models
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
Video+code lecture on building nanoGPT from scratch
Get up and running with Llama 3.3, Mistral, Gemma 2, and other large language models.
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
⚡ Flash Diffusion ⚡: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation (AAAI 2025)
A massively parallel, high-level programming language
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
High-Resolution Image Synthesis with Latent Diffusion Models
Taming Transformers for High-Resolution Image Synthesis
Accepted as [NeurIPS 2024] Spotlight Presentation Paper
This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.
Meditron is a suite of open-source medical Large Language Models (LLMs).
Transformer based on a variant of attention that is linear complexity in respect to sequence length
General Resources for Competitive Programming
Open-Sora: Democratizing Efficient Video Production for All