sakemin / musicgen-remixer

Remix the music into another styles with MusicGen Chord

  • Public
  • 15.1K runs
  • A100 (40GB)
  • GitHub
  • License
Run with an API
Playground API Examples README Versions

Input

Current Time 00:00:000
Duration 00:00:000
Loaded: 0%
Stream Type LIVE
Remaining Time 00:00:000
 
1x
string

Model type. Computations take longer when using `large` or `stereo` models.

Default: "stereo-chord"

string
Shift + Return to add a new line

A description of the music you want to generate.

file

An audio file input for the remix.

boolean

If `True`, the EnCodec tokens will be decoded with MultiBand Diffusion. Not compatible with `stereo` models.

Default: false

string

Strategy for normalizing audio.

Default: "loudness"

number

When beat syncing, if the gap between generated downbeat timing and input audio downbeat timing is larger than `beat_sync_threshold`, consider the beats are not corresponding. If `None` or `-1`, `1.1/(bpm/60)` will be used as the value. 0.75 is a good value to set.

boolean

If `True`, more chords like 7th, diminished and etc are used. If `False` only 12 major and 12 minor chords are used.

Default: true

number
(minimum: 0.5, maximum: 2)

Coefficient value multiplied to multi-hot chord chroma.

Default: 1

integer

Reduces sampling to the k most likely tokens.

Default: 250

number

Reduces sampling to tokens with cumulative probability of p. When set to `0` (default), top_k sampling is used.

Default: 0

number

Controls the 'conservativeness' of the sampling process. Higher temperature means more diversity.

Default: 1

integer

Increases the influence of inputs on the output. Higher values produce lower-varience outputs that adhere more closely to inputs.

Default: 3

string

Output format for generated audio.

Default: "wav"

boolean

If `True`, the instrumental audio will also be returned.

Default: false

integer

Seed for random number generator. If `None` or `-1`, a random seed will be used.

Add a payment method to run this model.

Sign in with GitHub

By signing in, you agree to our
terms of service and privacy policy

Output

Current Time 00:00:000
Duration 00:00:000
Loaded: 0%
Stream Type LIVE
Remaining Time 00:00:000
 
1x
Generated in
Tweak itReport

This example was created by a different version, sakemin/musicgen-remixer:e7172deb.

Run time and cost

This model costs approximately $0.56 to run on Replicate, or 1 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 A100 (40GB) GPU hardware. Predictions typically complete within 9 minutes. The predict time for this model varies significantly based on the inputs.

Readme

MusicGen Remixer

MusicGen Remixer is an app based on MusicGen Chord. Users can upload a music track with vocals, type in the text description prompt, and the app will create a new background track based on the input and then make a remixed music output.

Prediction Inputs

  • model_version: Model type. Computations take longer when using large or stereo models.
  • prompt: A description of the music you want to generate.
  • music_input: An audio file input for the remix.
  • multi_band_diffusion: If True, the EnCodec tokens will be decoded with MultiBand Diffusion. Not compatible with stereo models.
  • normalization_strategy: Strategy for normalizing audio.
  • beat_sync_threshold: When beat syncing, if the gap between generated downbeat timing and input audio downbeat timing is larger than beat_sync_threshold, consider the beats are not corresponding.
  • chroma_coefficient: Coefficient value multiplied to multi-hot chord chroma.
  • top_k: Reduces sampling to the k most likely tokens.
  • top_p: Reduces sampling to tokens with cumulative probability of p. When set to 0 (default), top_k sampling is used.
  • temperature: Controls the ‘conservativeness’ of the sampling process. Higher temperature means more diversity.
  • classifier_free_guidance: Increases the influence of inputs on the output. Higher values produce lower-varience outputs that adhere more closely to inputs.
  • output_format: str = Output format for generated audio. “wav”, “mp3”
  • seed: Seed for random number generator. If None or -1, a random seed will be used.

Warnings

If the input music has a phase with no chords, (i.e. long intro part, or only vocal break) the model will get confused, and the output quality might go bad.

References

Licenses