Skip to main content

Quickstart

Python​

Installing Python SDK​

pip install flymyai

Getting an API Key​

  1. Register on flymy.ai
  2. Go to your profile and get your key, username, and project_name

Example: Fastest Image Generation in the World​

# Install the FlyMyAI package
# pip install flymyai
from flymyai import client, FlyMyAIPredictException
import base64

# Set secret api key. You can find your api key in the profile settings
apikey = "fly-***" 
# Set the model name
model = "flymyai/SDXLTurbo"
# Prepare the input data
payload = {
  "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic, photorealistic",
  "negative_prompt": "Dark colors, gloomy atmosphere, horror"
}

# Initialize the client
fma_client = client(apikey=apikey)
try:
    response = fma_client.predict(
        model=model,
        payload=payload
    )
    # Process the output data
    sample_encoded = response.output_data["sample"][0]
    sample = base64.b64decode(sample_encoded)
    with open(f"sample_output.jpg", "wb") as file:
        file.write(sample)
    print(f"Saved sample_output.jpg")
except FlyMyAIPredictException as e:
    print(e)
    raise e

JavaScript​

Installing JavaScript SDK​

npm install flymyai-js-client

or

yarn add flymyai-js-client

Example: Fastest Image Generation in the World​

import { FlyMyAI } from "flymyai-js-client";
import base64 from 'base64-js';

// Initialize the client
const client = new FlyMyAI({ apiKey: "fly-***" });

// Set the model name
const model = "flymyai/SDXLTurbo";

// Prepare the input data
const payload = {
  prompt: "An astronaut riding a rainbow unicorn, cinematic, dramatic, photorealistic",
  negative_prompt: "Dark colors, gloomy atmosphere, horror"
};

try {
  const response = await client.predict(payload, model);
  
  // Process the output data
  const sample_encoded = response.output_data["sample"][0];
  const sample = base64.toByteArray(sample_encoded);
  const blob = new Blob([sample], { type: 'image/jpeg' });
  const url = URL.createObjectURL(blob);
  
  // Download the image
  const a = document.createElement('a');
  a.href = url;
  a.download = 'sample_output.jpg';
  a.click();
  
  console.log('Saved sample_output.jpg');
} catch (error) {
  console.error('Error making prediction:', error);
  throw error;
}

Streaming Example​

import { FlyMyAI } from "flymyai-js-client";

const client = new FlyMyAI({ apiKey: "fly-***" });
const model = "flymyai/SDTurboFMAAceleratedH100";

const payload = {
  i_prompt: "An astronaut riding a rainbow unicorn, cinematic, dramatic, photorealistic",
  i_negative_prompt: "Dark colors, gloomy atmosphere, horror"
};

async function streamPredictions() {
  try {
    for await (const result of client.stream(payload, model)) {
      console.log(
        "Streaming result:",
        (result.output_data?.output || [])[0] || ""
      );
    }
  } catch (error) {
    console.error("Error during streaming:", error);
  }
}

streamPredictions();

More​