Fastest SDXL Endpoint

fal-ai/ fast-sdxl

text-to-imageRun SDXL at the speed of lightloras embeddings

Here is a quick guide on how to use this model from an API in less than 1 minute. Before we proceed, you need to create an API key. This key secret will be used to authenticate your requests to the fal API.

fal.config({
  credentials: "PASTE_YOUR_FAL_KEY_HERE",
});

Now you can call our Model API endpoint using the fal js client:

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/fast-sdxl", {
  input: {
    prompt:
      "photo of a rhino dressed suit and tie sitting at a table in a bar with a bar stools, award winning photography, Elke vogelsang",
  },
});

A typical inference takes 2.3 seconds and will cost ~$0.0025.

Image Uploads Should Not Waste GPU CyclesWe upload the output image in a background thread so we don’t charge any GPU time for time spent on the GPU that is not directly inference.

⌘I

Model APIs

Serverless

Fastest SDXL Endpoint

fal-ai/ fast-sdxl