Moisés Horta Valenzuela

Realtime audio generation model using Flow Matching DiT on CoDiCodec latents.

Generate new latent codes for RAVE with Denoising Diffusion models.

Variational Autoencoder in the mel-spectrogram domain for one-shot audio synthesis

MelGAN-VC: Voice Conversion and Audio Style Transfer on arbitrarily long samples using Spectrograms

Exploring the Latent Space of Neural Audio Synthesis with Complex Systems

Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder

Audio generation using diffusion models, in PyTorch.

No description.

LLM and Agentic Conversational SOTA research for OurBrood (OMSK Social Club)

Apply diffusion models using the new Hugging Face diffusers package to synthesize music instead of images.

Encode and decode audio samples to/from compressed latent representations!

Neural sound synthesis with TensorFlow 2

WaveGAN: Learn to synthesize raw audio with generative adversarial networks

easy generation of latent trajectories

spectrogram inversion tools in PyTorch. Documentation: https://spectrogram-inversion.readthedocs.io

zero-shot voice conversion & singing voice conversion, with real-time support

No description.

A Collection of Variational Autoencoders (VAE) in PyTorch.

Code for the paper "Jukebox: A Generative Model for Music"

CLIP + FFT/DWT/RGB = text to image/video

PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, wav2lip, picture repair, image editing, photo2cartoon, image style transfer, and so on.

Code for Unconditional Audio Generation with GAN and Cycle Regularization

Encode and decode audio samples to/from continuous and discrete compressed representations!

Continuous Thought Machines, because thought takes time and reasoning is a process.

A real-time granular fx plugin made with JUCE & RNBO C++ Export

Implementation of rectified flow and some of its followup research / improvements in Pytorch

Pytorch implementation of the xLSTM model by Beck et al. (2024)

Generative models for conditional audio generation

Rembg Background Removal node for ComfyUI

No description.

No description.

Tools to train a generative model on arbitrary audio samples

StyleGAN2-ADA - Official PyTorch implementation

Auto trim and auto transcription of audio for using in Tacotron 2

No description.

Aligning Latent and Image Spaces to Connect the Unconnectable

StyleGAN2 for practice

Implementation of Differentiable Digital Signal Processing (DDSP) in Pytorch

No description.

StyleGAN2 - Official TensorFlow Implementation (Tweaks for latent space manipulation)

DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.

A port of SqueezeNet to Runway