You're looking at a specific version of this model. Jump to the model overview.
press1209 /musicgen-90s:8c21f3e3
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| prompt |
string
|
90s, r&b, new jack swing, energetic, groovy, synthesizer, drums
|
Music description. Format: '90s, [genre], [subgenre], [mood1], [mood2], [instrument1], [instrument2]'
|
| duration |
integer
|
20
Min: 5 Max: 30 |
Duration in seconds (max 30).
|
| temperature |
number
|
0.85
Min: 0.1 Max: 2 |
Controls diversity. Lower = more consistent, Higher = more varied.
|
| classifier_free_guidance |
number
|
7
Min: 1 Max: 10 |
Prompt adherence. Higher = follows prompt more closely.
|
| top_k |
integer
|
200
|
Reduces sampling to k most likely tokens.
|
| top_p |
number
|
0
|
Nucleus sampling probability. 0 to disable.
|
| output_format |
None
|
wav
|
Output format.
|
| seed |
integer
|
-1
|
Random seed. -1 for random.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}