Stars
A playbook for systematically maximizing the performance of deep learning models.
Neural network-based singing voice synthesis library for research
ImageBind One Embedding Space to Bind Them All
Easily train a good VC model with voice data <= 10 mins!
[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
A multi-voice TTS system trained with an emphasis on quality
Collection of google colaboratory notebooks for fast and easy experiments
Combustion engine simulator that generates realistic audio.
Stable diffusion for real-time music generation
The Deep Visualizer uses BigGAN (Brock et al., 2018) to visualize music.
Stable Diffusion web UI
GUI for a Vocal Remover that uses Deep Neural Networks.
A collection of inspiring lists, manuals, cheatsheets, blogs, hacks, one-liners, cli/web tools and more.
Code to accompany "A Method for Animating Children's Drawings of the Human Figure"
Create a music video automatically using generative AI tools
Generate, Enhance, Print, Loop - A ChatGPT enhanced Python REPL
stable diffusion webui colab
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
A Node.js script for seeing which dates are available for driving test centers around Ontario
♟ Inspired by Chess Tempo, users can interact with a chessboard to input/retrieve game data, determine best moves based on historical games and view stats.
Recognizing handwritten digits with a Deep Neural Network