Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS …

The first AI agent that builds permissionless integrations through reverse engineering platforms' internal APIs.

OpenMender: A community-driven, distributed system that autonomously discovers and fixes issues in open source repositories. Combining AI and human oversight to improve the digital commons.

ComfyUI nodes for LivePortrait

An unofficial practical guide to getting started developing custom nodes for ComfyUI

A powerful tool that translates ComfyUI workflows into executable Python code.

Karras et al. (2022) diffusion models for PyTorch

Distributing earnings from hic et nunc among multiple collaborators

Network-to-Network Translation with Conditional Invertible Neural Networks

[CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting

Python extension to capture video with video4linux2 (fork of https://launchpad.net/python-v4l2-capture)

StyleGAN Encoder - converts real images to latent space

Pytorch implementation of "An intriguing failing of convolutional neural networks and the CoordConv solution" - https://arxiv.org/abs/1807.03247

Multimodal Unsupervised Image-to-Image Translation

Re-implement CycleGAN in Tensorlayer

Demo for CVPR 2017 paper

Photographic Image Synthesis with Cascaded Refinement Networks

Inotify bindings for Lua

Image-to-image translation with conditional adversarial nets

Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

Fast and complete guided filter implementation for OpenCV

Composable GAN framework with api and user interface

Code for paper "Plug and Play Generative Networks"

This repository implements a demo of the Human pose estimation via Convolutional Part Heatmap Regression paper.

Scripts to read data out of the Neurosky Mindwave Mobile unter Ubuntu

A Node.js client library for the ThinkGear Socket Protocol from NeuroSky

Using Neurosky's Mindwave Mobile EEG headset, expose live data with WebSocket and view live stream in browser with HTML & Javscript.

A C++ port of Wave Function Collapse Tiling

Tool for extracting a visual summary of new papers uploaded to ArXiv.