Diffsound: Discrete Diffusion Model for Text-to-Sound Generation | Dark Hacker News

Dark Hacker News

new|best|ask|show|jobs

Built with the HackerNews API. Developed by LJT.AI

Note: The HackerNews API provides up to 500 stories per category

Diffsound: Discrete Diffusion Model for Text-to-Sound Generation | Dark Hacker News

Diffsound: Discrete Diffusion Model for Text-to-Sound Generation(dongchaoyang.top)

51 points by selimonder 3 years ago | 3 comments

notorious-dto 3 years ago |

Twiddling around trying to get this to work. Looks exciting :)

pbronez 3 years ago |

Very cool. Need to dig around and figure out what the training dataset is. Could be a great way to get some sample fodder.

notorious-dto 3 years ago |

There seems to be a missing python module called "image_synthesis", anyone know more about this?