You're looking at a specific version of this model. Jump to the model overview.
lucataco /zeta-editing:ff80c3cc
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 |
|---|---|---|---|
| audio |
string
|
Input Audio File
|
|
| prompt |
string
|
A recording of an arcade game soundtrack
|
Describe your desired edited output
|
| t_start |
integer
|
45
Min: 15 Max: 85 |
Lower % returns closer to the original audio, higher returns stronger edit
|
| audio_version |
string
(enum)
|
cvssp/audioldm2-music
Options: cvssp/audioldm2, cvssp/audioldm2-large, cvssp/audioldm2-music |
Choose the audio version to return
|
| source_prompt |
string
|
|
Optional: describe the original audio input
|
| steps |
integer
|
50
|
Number of diffusion steps, higher values(200) yield high-quality generations
|
| cfg_scale_src |
number
|
3
|
Source Guidance Scale
|
| cfg_scale_tar |
number
|
12
|
Target Guidance Scale
|
| seed |
integer
|
Random seed
|
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'}