Tiny AutoEncoder for Stable Diffusion

Tiny AutoEncoder for Hunyuan Video (and other video models)

Perceptual video quality assessment based on multi-method fusion.

Finetune a LLM to speak like you based on your WhatsApp Conversations

Focus on prompting and generating

Official Code for DragGAN (SIGGRAPH 2023)

Code for Enhancing Detail Preservation for Customized Text-to-Image Generation: A Regularization-Free Approach

LLM inference in C/C++

Tensor library for machine learning

Stable Diffusion in NCNN with c++, supported txt2img and img2img

Adaptation of Stable Diffusion with extra prompt guidance from images... An attempt at making the most flexible pipeline that will allow users to fully explore the capabilities of stable-diffusion.

Fast finetuning using a booster model that puts the initial state to a local minimum

Starlark implementation of bazel rules for CUDA.

Swift app demonstrating Core ML Stable Diffusion

A descriptive, diffable data source for UICollectionView

Stable Diffusion with Core ML on Apple Silicon

Effortless ZIP Handling in Swift

This is the repo for our new project Highly Accurate Dichotomous Image Segmentation

FgSegNet: Foreground Segmentation Network, Foreground Segmentation Using Convolutional Neural Networks for Multiscale Feature Encoding

Accessible large language models via k-bit quantization for PyTorch.

Transformer related optimization, including BERT, GPT

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

A comprehensive list of papers using large language/multi-modal models for Robotics/RL, including papers, codes, and related websites

Dolt – Git for Data

A fast and flexible implementation of Rigid Body Dynamics algorithms and their analytical derivatives

RBDL is a C++ library that contains some essential and efficient rigid body dynamics algorithms such as the Articulated Body Algorithm (ABA) for forward dynamics, Recursive Newton-Euler Algorithm (…

AI for autonomous soaring

Haptic input knob with software-defined endstops and virtual detents