Eyal Gruss

avatars4all. Live real-time avatars from your webcam in the browser. No dedicated hardware or software installation needed. A pure Google Colab wrapper for live First-order-motion-model, aka Avatarify in the browser. And other Colabs providing an accessible interface for using FOMM, Wav2Lip and Liquid-warping-GAN with your own media and a rich GUI.

word2vec-slim. word2vec Google News model slimmed down to 300k English words

hebrew_wordlists. Hebrew word lists

hebrew_tokenizer. A field-tested Hebrew tokenizer for dirty texts (ben-yehuda project, bible, cc100, mc4, opensubs, oscar, twitter) focused on multi-word expression extraction.

ztml. Extreme inline text compression for HTML / JS. A custom pipeline that generates stand-alone HTML or JS files which embed competitively compressed self-extracting text, with file sizes of 25% - 40% the original.

stylegan-encoder. forked from github.com/pbaylies/stylegan-encoder

clip_biggan. Jupyter Notebook

autotransformer. A transformer variant for semantic continuous sentence representation and generation

workshop. A hands-on workshop on deep neural networks

stylegan. StyleGAN Encoder - converts real images to latent space

skcd. skcd [scikit-xkcd] - Automagic stick-figure animation

projector. A minimalistic lightweight semi-automatic PDF gallery with lightbox

Wav2Lip. This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020.

LordTubeMaster. Live YouTube processing in client-side JS using self screen capture

alt-reality-cam. An semantic object layout based image search engine

first-order-model. This repository contains the source code for the paper First Order Motion Model for Image Animation

pix2pix-tensorflow. TensorFlow implementation of "Image-to-Image Translation Using Conditional Adversarial Networks".

uku3le. A simpler 3-string tuning for ukulele.

Qwen-Image-Edit-Plus-Lightning-Feedback-Loop. Jupyter Notebook

num2words. Modules to convert numbers to words. 42 --> forty-two

ediking. Client-side HTML/JS editor

webnn-developer-preview. JavaScript

ganbreeder. Breed and share images using biggan

iPERCore. Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis

pythotron. A simple MIDI controller audiovisual monitor (and wannabe musical instrument)

penitentia. The Penitentia Manuscript Parser

hashot. hashot! - new-media newsletter (bit.ly/hashot1)

fastface. Multiprocess realtime face landmark detection

U-2-Net. The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."

hebrew_scrapers. Hebrew web scrapers

Up-and-Out. A script for running experiments on EC2

impersonator. PyTorch implementation of our ICCV 2019 paper: Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis