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 …

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

A flexible framework of neural networks for deep learning

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

The Open Images dataset

Multimodal Unsupervised Image-to-Image Translation

Karras et al. (2022) diffusion models for PyTorch

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

ComfyUI nodes for LivePortrait

Simple web service providing a word embedding model

Photographic Image Synthesis with Cascaded Refinement Networks

Composable GAN framework with api and user interface

Code for paper "Plug and Play Generative Networks"

Music Structure Analysis Framework

Code for paper "Synthesizing the preferred inputs for neurons in neural networks via deep generator networks"

Network-to-Network Translation with Conditional Invertible Neural Networks

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

Re-implement CycleGAN in Tensorlayer

Manifests of the public domain images uploaded to Flickr Commons, with descriptive information about the books they were taken from.

Provides examples to demonstrate how FIGURE8 works. (Note: this version is deprecated and no longer recommended as a teaching demo. Please contact me for updated examples.)

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.

Distributing earnings from hic et nunc among multiple collaborators