You're looking at a specific version of this model. Jump to the model overview.
zoharbarzilai /drumtest2:e9f65a21
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
|
The prompt for the audio generation.
|
|
| negative_prompt |
string
|
|
The negative prompt to steer the generation away from.
|
| init_audio |
string
|
An initial audio file to use for audio-to-audio generation.
|
|
| init_noise_level |
number
|
1
|
The noise level for the initial audio.
|
| steps |
integer
|
100
|
Number of diffusion steps.
|
| cfg_scale |
number
|
7
|
Classifier-free guidance scale.
|
| sampler |
string
(enum)
|
k-dpmpp-2s-ancestral
Options: k-heun, k-lms, k-dpmpp-2s-ancestral, k-dpm-2, k-dpm-fast, k-dpm-adaptive, dpmpp-2m-sde, dpmpp-3m-sde |
The sampler to use.
|
| seed |
integer
|
-1
|
The random seed. -1 for a random seed.
|
| seconds_total |
integer
|
30
|
The total length of the audio in seconds.
|
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'}