andreasjansson / ace-step

  • Public
  • 5 runs
Iterate in playground

Run andreasjansson/ace-step with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

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_duration
number
30
Duration of the generated audio in seconds
prompt
string
pop music, catchy melody, upbeat
Text description of the music to generate
lyrics
string
Lyrics for the music (optional)
infer_step
integer
27

Min: 10

Max: 100

Number of inference steps
guidance_scale
number
15

Min: 1

Max: 20

Guidance scale for classifier-free guidance
scheduler_type
string (enum)
euler

Options:

euler, heun

Scheduler type
cfg_type
string (enum)
apg

Options:

apg, cfg, cfg_star

CFG type
omega_scale
number
10

Min: 1

Max: 20

Omega scale
seed
integer
-1
Seed for random number generation
guidance_interval
number
0.5

Max: 1

Guidance interval
guidance_interval_decay
number
0

Max: 1

Guidance interval decay
min_guidance_scale
number
3

Min: 1

Max: 15

Minimum guidance scale
use_erg_tag
boolean
True
Use ERG for tags
use_erg_lyric
boolean
True
Use ERG for lyrics
use_erg_diffusion
boolean
True
Use ERG for diffusion

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{
  "type": "string",
  "title": "Output",
  "format": "uri"
}