moiseshorta

RAVE-Latent-Diffusion

Generate new latent codes for RAVE with Denoising Diffusion models.

MelSpecVAE

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

ADD-audio-dataset-downloader

Simple Python CLI script for downloading N-hours of audio from Youtube, based on a list of music genres.

MelGAN-VC

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

ravejs

audio-diffusion-pytorch

Audio generation using diffusion models, in PyTorch.

RAVE

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

aphantasia

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

audio-diffusion

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

jukebox

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

PaddleGAN

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.

PyTorch-VAE

A Collection of Variational Autoencoders (VAE) in PyTorch.

rave_vst

unagan

Code for Unconditional Audio Generation with GAN and Cycle Regularization

alis

Aligning Latent and Image Spaces to Connect the Unconnectable

ddsp_pytorch

Implementation of Differentiable Digital Signal Processing (DDSP) in Pytorch

diffwave

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

jukebox-saveopt

prism-samplernn

Neural sound synthesis with TensorFlow 2

rembg-comfyui-node

Rembg Background Removal node for ComfyUI

sample-generator

Tools to train a generative model on arbitrary audio samples

spectrogram-inversion

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

stable-audio-tools

Generative models for conditional audio generation

StyleGAN-nada

stylegan2

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

stylegan2-ada-pytorch

StyleGAN2-ADA - Official PyTorch implementation

stylegan2_eps

StyleGAN2 for practice

Tacotron2AutoTrim

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

textual_inversion

trajectories

easy generation of latent trajectories