Last Updated | Version | Changes |
---|---|---|
12/20/2022 | 1.0 | Quick’n’Dirty Tutorial Created |
12/21/2022 | 1.1 | Advanced Info (in progress) |
12/28/2022 | 1.2 | Bug Fix (Thanks to CosmicRain!) |
5/15/2023 | 1.3 | Google MusicLM (AI Test Kitchen) Update |
<aside> <img src="https://s3-us-west-2.amazonaws.com/secure.notion-static.com/8c478f4f-1831-4aed-9921-1f6b12d7831b/Digital-Patreon-Logo_FieryCoral.png" alt="https://s3-us-west-2.amazonaws.com/secure.notion-static.com/8c478f4f-1831-4aed-9921-1f6b12d7831b/Digital-Patreon-Logo_FieryCoral.png" width="40px" /> If this page has been helpful, please consider joining my Patreon, where I produce advanced Stable Diffusion tutorials and erotic art - from a female (adult) content-creator perspective. patreon.com/theally
</aside>
Text input, audio output! Not great audio, true, but it’ll improve. This is the first model for txt2audio, and it was a hobby project by Seth Forsgren and Hayk Martiros https://www.riffusion.com/about
Here's an example of what's possible with this model - some simple beats I made earlier -
2022-12-20_11-32-37_joined.wav
https://github.com/enlyth/sd-webui-riffusion