Stars
Qwen-Image text to image lora trainer
Custom nodes that bring Character.AI's Ovi video+audio generator to ComfyUI with streamlined setup, selectable precision, attention-backend control, and per-node device targeting for multi-GPU rigs.
🔉 spafe: Simplified Python Audio Features Extraction
ComfyUI-native nodes to run First Order Motion Model for Image Animation and its non-diffusion-based successors.
An Archive of the original Windows Speech API 4 SDK and Voices
TurboLPC is a fast, simple yet powerful Python library that provides the functionality of Linear Predictive Coding for signals.
Pitch and Formant Frequency detector using Cepstrum
A collection of nodes for working with audio data.
A graphical editor for creating and editing Text-to-Speech language and voice files.
A tacotron compatible version of https://keithito.com/LJ-Speech-Dataset/ using DECTalk for the voice data instead of a human
Use the Dectalk voice sythesizer directly in .NET applications
Pytorch Reimplementation of DiffWave unconditional generation: a high quality waveform synthesizer.
ANSI C port of ROMWak, a tool for manipulating binary files/ROM images (padding, splitting, and so on).
Double Pendulum Simulation in Python with ScyPy
Script for Korg nanoKONTROL Studio controller for FL Studio
OneTrainer is a one-stop solution for all your stable diffusion training needs.
A launcher and mod/patch tool for the 1997 video game LEGO Island.
A VST effect that emulates Environmental Audio Extensions (EAX) reverb
A tool providing additional ECC protection for optical media (unofficial version)
The ultimate training toolkit for finetuning diffusion models