For RLDG_835770db1c, I used a denoising diffusion model trained on a RAVE neural net based on my earlier discography (excluding remixes and collaborations with other artists) and the original dataset itself to create outputs based on randomized seed values.

RAVE-Latent Diffusion by Moisés Horta Valenzuela / 𝔥𝔢𝔵𝔬𝔯𝔠𝔦𝔰𝔪𝔬𝔰 is a denoising diffusion model designed to generate new RAVE latent codes with a large context window, faster than realtime, while maintaining music structural coherency. https://github.com/moiseshorta/RAVE-Latent-Diffusion

RAVE is a variational autoencoder for fast and high-quality neural audio synthesis created by Antoine Caillon and Philippe Esling at IRCAM. https://github.com/acids-ircam/RAVE