Tensors and Dynamic neural networks in Python with strong GPU acceleration

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

The uncompromising Python code formatter

Let us control diffusion models!

Reverse engineered ChatGPT API

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

Official inference repo for FLUX.1 models

DALL·E Mini - Generate images from a text prompt

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

Ongoing research training transformer models at scale

Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

🔎 📈 🐍 💰 Backtest trading strategies in Python.

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

A command line utility to display dependency tree of the installed Python packages

A native PyTorch Library for large model training

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch

A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".

Optax is a gradient processing and optimization library for JAX.

Implementation of 'lightweight' GAN, proposed in ICLR 2021, in Pytorch. High resolution image generations that can be trained within a day or two

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.