Skip to main content

How to deploy FLUX.1

In this guide, we will create a simple FLUX image generation workflow using Ikomia API and deploy it to the cloud with Ikomia SCALE to integrate it into a Node.js application.

FLUX generated image

💫 This tutorial is also available as a Jupyter notebook.


1. Installation​

First, ensure that you have installed the Ikomia Python API and CLI:

pip install ikomia ikomia-cli

2. Create a workflow with Ikomia API​

To get started, let's create a workflow using infer_flux_1 algorithm from Ikomia HUB:

from ikomia.dataprocess.workflow import Workflow

workflow = Workflow("FLUX Image Generation")

flux = workflow.add_task(name="infer_flux_1")
flux.set_parameters({
    "model_name": "flux1-schnell",
})

# Save workflow as a JSON file
workflow.save("flux_workflow.json")

Running your workflow locally

Ikomia API is open-source and also highly suitable for self-hosted solutions if you prefer to run workflows locally.

Here's how you can modify the previous script to execute the workflow locally:

from ikomia.dataprocess.workflow import Workflow
from ikomia.utils.displayIO import display

workflow = Workflow("FLUX Image Generation")
flux = workflow.add_task(name="infer_flux_1")

# Configure the algorithm
flux.set_parameters({
    "model_name": "flux1-schnell",
    "prompt": "An adventurer in the jungle with a tshirt that says 'Deploy FLUX.1'.",
})

# Run the workflow
workflow.run()

# Display the output image
display(flux.get_output(0).get_image())
warning

Please note that FLUX is a large model that requires at least 12GB of VRAM.

To create more advanced workflows, check out the Ikomia API documentation.


3. Deploy your workflow to Ikomia SCALE​

If you haven't already, create an Ikomia account.

Create an API token​

To authorize the CLI and your code to access your Ikomia SCALE account, create an API token and set it as an environment variable:

export IKOMIA_TOKEN=PASTE_YOUR_TOKEN_HERE

Push your workflow​

Create a project and push your workflow to Ikomia SCALE:

ikcli project add YOUR_USERNAME FluxImageGeneration
ikcli project push FluxImageGeneration flux_workflow.json

You can now view and manage your project and workflow on the Ikomia SCALE dashboard.

Deploy​

warning

To deploy large algorithms like FLUX, you'll need to upgrade your plan to a paid subscription to access GPU deployments.

On the workflow page, select a deployment option and click on the Add deployment button.

Deploying our FLUX image generation workflow on a cloud GPU instance

Once your deployment is ready, you can test it via our online interface.


4. Integrate your deployment into a Node.js application​

Note

We also provide a REST API for integration with any language/platform.

Install our JavaScript client library:

npm install @ikomia/ikclient

Now, you can call your deployment from your Node.js application:

import fs from "fs";
import {Client} from "@ikomia/ikclient";

// Initialize the client with your deployment URL and token
const client = new Client({
  url: "https://your.deployment.url",
  token: "PASTE_YOUR_TOKEN_HERE",
});

// Generate an image
const results = await client.run({
  parameters: {
    prompt: "An adventurer in the jungle with a tshirt that says 'Deploy FLUX.1'.",
  },
});

// Save the image
const image = results.getOutput(0);
await fs.promises.writeFile("output.png", image.buffer);

For more advanced usage of the Ikomia SCALE JavaScript client library, check out the client documentation.