Скачать с ютуб Latent Jamming in "Saatgut Proxy" в хорошем качестве

Latent Jamming in "Saatgut Proxy"

„Saatgut Proxy“ is an experimental generative setup implemented in Pure Data, that works with two neural audio model architectures: RAVE and vschaos2. It uses different techniques of direct and realtime intervention in latent space that I termed „Latent Jamming“ because of their explorative and performative nature. The models in this video have been trained on a selection of music that I produced and released in the past years. The output I’m able to generate with them is their interpretation of what they consider the dominant characteristics of my music. In the patch, I’m experimenting with combinations of signal values that mimic latent embeddings. These can be changed and played with, but also fixated in order to stabilize the models’ output to a repetitive or repeatable state. --- RAVE is "A variational autoencoder for fast and high-quality neural audio synthesis” created by Antoine Caillon and Philippe Esling of Artificial Creative Intelligence and Data Science (ACIDS) at IRCAM, Paris. RAVE on GitHub: https://github.com/acids-ircam/RAVE nn~ on GitHub: https://github.com/acids-ircam/nn_tilde To train models on Colab or Kaggle, you can use these Jupyter notebooks i've set up: https://github.com/devstermarts/Noteb...