--- layout: article title: Integrating fal.ai description: Learn how to integrate fal.ai into your Appwrite project. difficulty: intermediate readtime: 15 --- fal.ai is an AI inference platform with popular models such as Stable Diffusion XL, ControlNet, Whisper available as ready-to-use APIs so that you can easily integrate them into your applications. This tutorial will guide you through the process of setting up the fal.ai API to generate an image using the SDXL model and integrating it into your Appwrite project. # Prerequisites {% #prerequisites %} - An Appwrite Project - A [fal.ai API Key](https://fal.ai/docs/authentication/key-based) {% section #step-1 step=1 title="Create new function" %} Head to the [Appwrite Console](https://cloud.appwrite.io/console) then click on **Functions** in the left sidebar and then click on the **Create Function** button. {% only_dark %} ![Create function screen](/images/docs/functions/dark/template.avif) {% /only_dark %} {% only_light %} ![Create function screen](/images/docs/functions/template.avif) {% /only_light %} 1. In the Appwrite Console's sidebar, click **Functions**. 1. Click **Create function**. 1. Under **Connect Git repository**, select your provider. 1. After connecting to GitHub, under **Quick start**, select the **Node.js** starter template. 1. In the **Variables** step, add the `FAL_API_KEY`, generate it [here](https://fal.ai/docs/authentication/key-based). 1. Follow the step-by-step wizard and create the function. {% /section %} {% section #step-2 step=2 title="Add fal.ai SDK" %} Once the function is created, clone the function and open it in your development environment. Once you have the repository open, you can install the fal.ai SDK by running the following command in your terminal: ```bash npm install @fal-ai/serverless-client ``` {% /section %} {% section #step-3 step=3 title="Create utility function" %} In this example, the function will be able to accept both `GET` and `POST` requests. For the `GET` request, return a static HTML page. It will use AlpineJS to make a `POST` request to the function. The `POST` request will use the fal.ai SDK to make a request to the fal.ai API. Write the code to return a static HTML page. Create a new `src/utils.js` file with the following code: ```js import path from 'path'; import { fileURLToPath } from 'url'; import fs from 'fs'; const __filename = fileURLToPath(import.meta.url); const __dirname = path.dirname(__filename); const staticFolder = path.join(__dirname, '../static'); export function getStaticFile(fileName) { return fs.readFileSync(path.join(staticFolder, fileName)).toString(); } ``` {% /section %} {% section #step-4 step=4 title="Handle GET request" %} Write our `GET` request handler in the `src/main.js` file. This handler will return the static HTML page. ```js import { getStaticFile } from './utils.js'; export default async ({ req, res, error }) => { if (req.method === 'GET') { return res.text(getStaticFile('index.html'), 200, { 'Content-Type': 'text/html; charset=utf-8', }); } }; ``` {% /section %} {% section #step-5 step=5 title="Create static page" %} Create the static HTML page that the function will serve. Create a new file at `static/index.html` with some HTML boilerplate: ```html ``` Within the `` tag, add a `` tag with the necessary meta tags, stylesheets, and scripts: ```html fal.ai Demo ``` And after the `` tag, add our `` tag with the following content: ```html

fal.ai demo

Use this page to test your implementation with fal.ai. Enter text and receive the model output as a response.

``` This HTML form will allow users to input a prompt and generate an image using the fal.ai API. The AlpineJS script handles the form submission and display the result. {% /section %} {% section #step-6 step=6 title="Handle POST Request" %} Add methods necessary to integrate with fal.ai's API. Import the fal.ai SDK at the top of the `main.js` file: ```js import * as fal from '@fal-ai/serverless-client'; ``` Handle the `POST` requests to the function. Initialize the fal.ai SDK at the end of the handler function: ```js fal.config({ credentials: process.env.FAL_API_KEY }); ``` Make the request to generate an image using the SDXL model, and return the result: ```js const result = await fal.subscribe('fal-ai/fast-sdxl', { input: { prompt: req.body.prompt, }, }); return res.json({ ok: true, src: result.images[0].url }); ``` With the function complete, deploy it to Appwrite by pushing the changes to your repository. Additional models can be found in the [fal.ai model catalogue](https://fal.ai/models). {% /section %} {% section #step-7 step=7 title="Test the function" %} Now that the function is deployed, test it by visiting the function URL in a browser. The UI created earlier will be visible. To test it, write a prompt and click the submit button, after a brief the completion should appear below the input. ![Testing the function](/images/docs/ai/integrations/fal-ai/demo.avif) {% /section %}

fal.ai demo

Result: