jourdelune / diffrhythm

"DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion"

  • Public
  • 269 runs
  • T4
  • GitHub
  • Weights
  • Paper
  • License

Input

Video Player is loading.
Current Time 00:00:000
Duration 00:00:000
Loaded: 0%
Stream Type LIVE
Remaining Time 00:00:000
 
1x
string
Shift + Return to add a new line

Lyric to generate a song for, format: [00:00.00]lyrics

Default: ""

integer

Length of generated song

Default: 95

string
Shift + Return to add a new line

Prompt to use as style reference

Default: ""

file

Audio to use as reference, have to be longer than 10 seconds

Default: ""

Output

Video Player is loading.
Current Time 00:00:000
Duration 00:00:000
Loaded: 0%
Stream Type LIVE
Remaining Time 00:00:000
 
1x
Generated in

Run time and cost

This model costs approximately $0.048 to run on Replicate, or 20 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 4 minutes. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.