zsxkib/flux-music – Run with an API on Replicate

Input

prompt

string

Shift + Return to add a new line

A wild and rebellious rock anthem with psychedelic and bluesy undertones, this song is loud and energetic.A wild and rebellious rock anthem with psychedelic and bluesy undertones, this song is loud and energetic.

Text prompt for music generation

Default: "The song is an epic blend of space-rock, rock, and post-rock genres."

negative_prompt

string

Shift + Return to add a new line

Text prompt for negative guidance (unconditioned prompt)

Default: "low quality, gentle"

guidance_scale

number

(minimum: 0, maximum: 20)

Classifier-free guidance scale

Default: 7

model_version

string

Select the model version to use

Default: "base"

steps

integer

(minimum: 1, maximum: 200)

Number of sampling steps

Default: 50

save_spectrogram

boolean

Whether to save the spectrogram image

Default: false

seed

integer

Random seed. Leave blank to randomize the seed

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

npx create-replicate --model=zsxkib/flux-music

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 zsxkib/flux-music using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "zsxkib/flux-music:eebfed4a1749bb1172f005f71fac5a1e0377502ec149c9d02b56ac1de3aa9f07",
  {
    input: {
      steps: 50,
      prompt: "A wild and rebellious rock anthem with psychedelic and bluesy undertones, this song is loud and energetic.",
      model_version: "base",
      guidance_scale: 7,
      negative_prompt: "low quality, gentle",
      save_spectrogram: true
    }
  }
);
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 zsxkib/flux-music using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "zsxkib/flux-music:eebfed4a1749bb1172f005f71fac5a1e0377502ec149c9d02b56ac1de3aa9f07",
    input={
        "steps": 50,
        "prompt": "A wild and rebellious rock anthem with psychedelic and bluesy undertones, this song is loud and energetic.",
        "model_version": "base",
        "guidance_scale": 7,
        "negative_prompt": "low quality, gentle",
        "save_spectrogram": True
    }
)
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 zsxkib/flux-music 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": "eebfed4a1749bb1172f005f71fac5a1e0377502ec149c9d02b56ac1de3aa9f07",
    "input": {
      "steps": 50,
      "prompt": "A wild and rebellious rock anthem with psychedelic and bluesy undertones, this song is loud and energetic.",
      "model_version": "base",
      "guidance_scale": 7,
      "negative_prompt": "low quality, gentle",
      "save_spectrogram": true
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

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

Run this to download the model and run it in your local environment:

cog predict r8.im/zsxkib/flux-music@sha256:eebfed4a1749bb1172f005f71fac5a1e0377502ec149c9d02b56ac1de3aa9f07 \
  -i 'steps=50' \
  -i 'prompt="A wild and rebellious rock anthem with psychedelic and bluesy undertones, this song is loud and energetic."' \
  -i 'model_version="base"' \
  -i 'guidance_scale=7' \
  -i 'negative_prompt="low quality, gentle"' \
  -i 'save_spectrogram=true'

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

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/zsxkib/flux-music@sha256:eebfed4a1749bb1172f005f71fac5a1e0377502ec149c9d02b56ac1de3aa9f07
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "steps": 50,
      "prompt": "A wild and rebellious rock anthem with psychedelic and bluesy undertones, this song is loud and energetic.",
      "model_version": "base",
      "guidance_scale": 7,
      "negative_prompt": "low quality, gentle",
      "save_spectrogram": true
    }
  }' \
  http://localhost:5000/predictions

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

Output

wav

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

melspectrogram

Generated in

5.8 seconds

Tweak it ShareReport

Run time and cost

This model costs approximately $0.052 to run on Replicate, or 19 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 54 seconds. The predict time for this model varies significantly based on the inputs.