Music Generation

Music Generation using the riffusion/riffusion AI Model.

Query

model

string

default:

"riffusion/riffusion"

required

The model to be used;

Body

prompt_a

string

required

The prompt for your audio

denoising

float

default:

"0.75"

How much to transform input spectrogram

prompt_b

string

The second prompt to interpolate with the first, leave blank if no interpolation

alpha

float

default:

"0.5"

Interpolation alpha if using two prompts. A value of 0 uses prompt_a fully, a value of 1 uses prompt_b fully

num_inference_steps

int

default:

"50"

Number of steps to run the diffusion model

seed_image_id

string

default:

"vibes"

Seed spectrogram to use