[HN Gopher] Riffusion Release v0.3 - Stable Diffusion for audio
___________________________________________________________________
Riffusion Release v0.3 - Stable Diffusion for audio
Author : haykmartiros
Score : 29 points
Date : 2022-12-27 17:35 UTC (5 hours ago)
(HTM) web link (github.com)
(TXT) w3m dump (github.com)
| haykmartiros wrote:
| We were blown away by the community interest in our Riffusion
| experiment (see https://www.riffusion.com/about).
|
| We're now catching up and did a full rewrite to go from a hack to
| a quality software project. It also includes an extensible CLI
| tool and an interactive streamlit app for common tasks, MPS
| backend support, stereo spectrogram encoding, a test suite run by
| CI, and more. These tools provide a solid foundation to build
| upon.
| ronsor wrote:
| Is it a good idea to save spectrograms as JPEGs? Won't the
| lossy compression be an issue?
| klysm wrote:
| I guess you could listen to what different lossy image
| compression algorithms sound like
| rafaelero wrote:
| Why haven't you guys used <title> <artist> <album> <lyrics> as
| input to generate the song? It would be much cooler.
___________________________________________________________________
(page generated 2022-12-27 23:02 UTC)