andreasjansson/ace-step | Run with an API on Replicate

andreasjansson / ace-step

(Updated 1 month, 1 week ago)

Cold

Public
5 runs
A100 (80GB)

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

audio_duration

number

Duration of the generated audio in seconds

Default: 30

prompt

string

Shift + Return to add a new line

Text description of the music to generate

Default: "pop music, catchy melody, upbeat"

lyrics

string

Shift + Return to add a new line

Lyrics for the music (optional)

Default: ""

infer_step

integer

(minimum: 10, maximum: 100)

Number of inference steps

Default: 27

guidance_scale

number

(minimum: 1, maximum: 20)

Guidance scale for classifier-free guidance

Default: 15

scheduler_type

string

Scheduler type

Default: "euler"

cfg_type

string

CFG type

Default: "apg"

omega_scale

number

(minimum: 1, maximum: 20)

Omega scale

Default: 10

seed

integer

Seed for random number generation

Default: -1

guidance_interval

number

(minimum: 0, maximum: 1)

Guidance interval

Default: 0.5

guidance_interval_decay

number

(minimum: 0, maximum: 1)

Guidance interval decay

Default: 0

min_guidance_scale

number

(minimum: 1, maximum: 15)

Minimum guidance scale

Default: 3

use_erg_tag

boolean

Use ERG for tags

Default: true

use_erg_lyric

boolean

Use ERG for lyrics

Default: true

use_erg_diffusion

boolean

Use ERG for diffusion

Default: true

Run this model in Node.js with one line of code:

npx create-replicate --model=andreasjansson/ace-step

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run andreasjansson/ace-step using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/ace-step:9fa9677db3357a7f1975ed49365e2825ab7e9a61ba659768534cef95a1ffb303",
  {
    input: {
      seed: -1,
      lyrics: "",
      prompt: "pop music, catchy melody, upbeat",
      cfg_type: "apg",
      infer_step: 27,
      omega_scale: 10,
      use_erg_tag: true,
      use_erg_lyric: true,
      audio_duration: 30,
      guidance_scale: 15,
      scheduler_type: "euler",
      guidance_interval: 0.5,
      use_erg_diffusion: true,
      min_guidance_scale: 3,
      guidance_interval_decay: 0
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run andreasjansson/ace-step using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/ace-step:9fa9677db3357a7f1975ed49365e2825ab7e9a61ba659768534cef95a1ffb303",
    input={
        "seed": -1,
        "lyrics": "",
        "prompt": "pop music, catchy melody, upbeat",
        "cfg_type": "apg",
        "infer_step": 27,
        "omega_scale": 10,
        "use_erg_tag": True,
        "use_erg_lyric": True,
        "audio_duration": 30,
        "guidance_scale": 15,
        "scheduler_type": "euler",
        "guidance_interval": 0.5,
        "use_erg_diffusion": True,
        "min_guidance_scale": 3,
        "guidance_interval_decay": 0
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run andreasjansson/ace-step using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "andreasjansson/ace-step:9fa9677db3357a7f1975ed49365e2825ab7e9a61ba659768534cef95a1ffb303",
    "input": {
      "seed": -1,
      "lyrics": "",
      "prompt": "pop music, catchy melody, upbeat",
      "cfg_type": "apg",
      "infer_step": 27,
      "omega_scale": 10,
      "use_erg_tag": true,
      "use_erg_lyric": true,
      "audio_duration": 30,
      "guidance_scale": 15,
      "scheduler_type": "euler",
      "guidance_interval": 0.5,
      "use_erg_diffusion": true,
      "min_guidance_scale": 3,
      "guidance_interval_decay": 0
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.