🎵

diffrhythm

falai

DiffRhythm is a blazing fast model for transforming lyrics into full songs. It boasts the capability to generate full songs in less than 30 seconds.

Model Type

music

Cost

20 tokens / 1_megabitpixiels

Features

Model Settings

lyrics

The prompt to generate the song from. Must have two sections. Sections start with either [chorus] or a [verse].

scheduler

euler, midpoint, rk4, implicit_adams

cfg strength

4

style prompt

pop

music duration

95s, 285s

num inference steps

32

reference audio url

Upload mp3/wav or enter a url

Join the Discussion

Have questions or want to share your experience with diffrhythm? Join the conversation in our forums.

Visit Forums