fofr/yue:be46b490 – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

fofr /yue:be46b490

Input

genre_description

string

Shift + Return to add a new line

inspiring female uplifting pop airy vocal electronic bright vocal vocalinspiring female uplifting pop airy vocal electronic bright vocal vocal

Text containing genre tags that describe the musical style (e.g. instrumental, genre, mood, vocal timbre, vocal gender)

Default: "inspiring female uplifting pop airy vocal electronic bright vocal vocal"

lyrics

string

Shift + Return to add a new line

[verse]
Oh yeah, oh yeah, oh yeah

[chorus]
Oh yeah, oh yeah, oh yeah[verse]
Oh yeah, oh yeah, oh yeah

[chorus]
Oh yeah, oh yeah, oh yeah

Lyrics for music generation. Must be structured in segments with [verse], [chorus], [bridge], or [outro] tags

Default: "[verse]\nOh yeah, oh yeah, oh yeah\n\n[chorus]\nOh yeah, oh yeah, oh yeah"

num_segments

integer

(minimum: 1, maximum: 10)

Number of segments to generate

Default: 2

max_new_tokens

integer

(minimum: 500, maximum: 3000)

Maximum number of new tokens to generate

Default: 1500

seed

integer

Set a seed for reproducibility. Random by default.

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

npx create-replicate --model=fofr/yue

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";

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

Run fofr/yue using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "fofr/yue:be46b4902810c246b66aa69b043ae3b0625dab20266583fbb3b62b87ba416aba",
  {
    input: {
      lyrics: "[verse]\nOh yeah, oh yeah, oh yeah\n\n[chorus]\nOh yeah, oh yeah, oh yeah",
      num_segments: 2,
      max_new_tokens: 1500,
      genre_description: "inspiring female uplifting pop airy vocal electronic bright vocal vocal"
    }
  }
);
console.log(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 fofr/yue using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fofr/yue:be46b4902810c246b66aa69b043ae3b0625dab20266583fbb3b62b87ba416aba",
    input={
        "lyrics": "[verse]\nOh yeah, oh yeah, oh yeah\n\n[chorus]\nOh yeah, oh yeah, oh yeah",
        "num_segments": 2,
        "max_new_tokens": 1500,
        "genre_description": "inspiring female uplifting pop airy vocal electronic bright vocal vocal"
    }
)
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 fofr/yue 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": "be46b4902810c246b66aa69b043ae3b0625dab20266583fbb3b62b87ba416aba",
    "input": {
      "lyrics": "[verse]\\nOh yeah, oh yeah, oh yeah\\n\\n[chorus]\\nOh yeah, oh yeah, oh yeah",
      "num_segments": 2,
      "max_new_tokens": 1500,
      "genre_description": "inspiring female uplifting pop airy vocal electronic bright vocal vocal"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Install Cog

brew install cog

If you don’t have Homebrew, there are other installation options available.

Pull and run fofr/yue using Cog (this will download the full model and run it in your local environment):

cog predict r8.im/fofr/yue@sha256:be46b4902810c246b66aa69b043ae3b0625dab20266583fbb3b62b87ba416aba \
  -i $'lyrics="[verse]\\nOh yeah, oh yeah, oh yeah\\n\\n[chorus]\\nOh yeah, oh yeah, oh yeah"' \
  -i 'num_segments=2' \
  -i 'max_new_tokens=1500' \
  -i 'genre_description="inspiring female uplifting pop airy vocal electronic bright vocal vocal"'

To learn more, take a look at the Cog documentation.

Pull and run fofr/yue using Docker (this will download the full model and run it in your local environment):

docker run -d -p 5000:5000 --gpus=all r8.im/fofr/yue@sha256:be46b4902810c246b66aa69b043ae3b0625dab20266583fbb3b62b87ba416aba
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "lyrics": "[verse]\\nOh yeah, oh yeah, oh yeah\\n\\n[chorus]\\nOh yeah, oh yeah, oh yeah",
      "num_segments": 2,
      "max_new_tokens": 1500,
      "genre_description": "inspiring female uplifting pop airy vocal electronic bright vocal vocal"
    }
  }' \
  http://localhost:5000/predictions

Output

No output yet! Press "Submit" to start a prediction.