naturomics

rembg

Rembg is a tool to remove images background

DALL-E

PyTorch package for the discrete VAE used for DALL·E.

LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

outlines

Structured Text Generation

progressive_growing_of_gans

Progressive Growing of GANs for Improved Quality, Stability, and Variation

pytorch-metric-learning

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

IP-Adapter

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

edward

A probabilistic programming language in TensorFlow. Deep generative models, variational inference.

vmaf

Perceptual video quality assessment based on multi-method fusion.

seldon-core

An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models

probability

Probabilistic reasoning and statistical analysis in TensorFlow

phoenix

AI Observability & Evaluation

vtracer

Raster to Vector Graphics Converter

gradient-checkpointing

Make huge neural nets fit in memory

waveglow

A Flow-based Generative Network for Speech Synthesis

LyCORIS

Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion.

lorax

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Bayesian-Neural-Networks

Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more

torchsde

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

score_sde

Official code for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)

NVAE

The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)

diffvg

Differentiable Vector Graphics Rasterization

mellotron

Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data

ffjord

code for "FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models".

InvariantRiskMinimization

PyTorch code to run synthetic experiments.

residual-flows

code for "Residual Flows for Invertible Generative Modeling".

bayeSDE

Code for "Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations"

expRNN

Optimization with orthogonal constraints and on general manifolds

CP-Flow

Convex potential flows

emerging