Example: Text-to-Image Generation

Complete example of generating images from text using Atlas Cloud API

Overview

This tutorial walks through a complete text-to-image generation workflow using the Atlas Cloud API — from submitting the request to retrieving the final image.

Prerequisites

Complete Python Example

import requests
import time
import os

API_KEY = os.environ.get("ATLASCLOUD_API_KEY", "your-api-key")
BASE_URL = "https://api.atlascloud.ai/api/v1"

def generate_image(prompt, model="seedream-3.0"):
    """Submit an image generation task."""
    response = requests.post(
        f"{BASE_URL}/model/generateImage",
        headers={
            "Authorization": f"Bearer {API_KEY}",
            "Content-Type": "application/json"
        },
        json={
            "model": model,
            "prompt": prompt
        }
    )
    response.raise_for_status()
    return response.json().get("predictionId")

def wait_for_result(prediction_id, interval=2, timeout=120):
    """Poll for generation result."""
    elapsed = 0
    while elapsed < timeout:
        response = requests.get(
            f"{BASE_URL}/model/getResult?predictionId={prediction_id}",
            headers={"Authorization": f"Bearer {API_KEY}"}
        )
        result = response.json()
        status = result.get("status")

        if status == "completed":
            return result.get("output")
        elif status == "failed":
            raise Exception(f"Failed: {result.get('error')}")

        print(f"  Status: {status} ({elapsed}s)")
        time.sleep(interval)
        elapsed += interval

    raise TimeoutError("Generation timed out")

# Generate an image
prompt = "A majestic snow-capped mountain reflected in a crystal-clear lake at sunrise, photorealistic"
print(f"Generating image: {prompt}")

prediction_id = generate_image(prompt)
print(f"Task submitted: {prediction_id}")

image_url = wait_for_result(prediction_id)
print(f"Image ready: {image_url}")

Complete Node.js Example

const API_KEY = process.env.ATLASCLOUD_API_KEY || "your-api-key";
const BASE_URL = "https://api.atlascloud.ai/api/v1";

async function generateImage(prompt, model = "seedream-3.0") {
  const response = await fetch(`${BASE_URL}/model/generateImage`, {
    method: "POST",
    headers: {
      Authorization: `Bearer ${API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({ model, prompt }),
  });

  if (!response.ok) throw new Error(`HTTP ${response.status}`);
  const data = await response.json();
  return data.predictionId;
}

async function waitForResult(predictionId, interval = 2000, timeout = 120000) {
  const start = Date.now();
  while (Date.now() - start < timeout) {
    const response = await fetch(
      `${BASE_URL}/model/getResult?predictionId=${predictionId}`,
      { headers: { Authorization: `Bearer ${API_KEY}` } }
    );
    const result = await response.json();

    if (result.status === "completed") return result.output;
    if (result.status === "failed") throw new Error(result.error);

    console.log(`  Status: ${result.status}`);
    await new Promise((r) => setTimeout(r, interval));
  }
  throw new Error("Timeout");
}

// Run
const prompt =
  "A majestic snow-capped mountain reflected in a crystal-clear lake at sunrise, photorealistic";
console.log(`Generating: ${prompt}`);

const predictionId = await generateImage(prompt);
console.log(`Task: ${predictionId}`);

const imageUrl = await waitForResult(predictionId);
console.log(`Image: ${imageUrl}`);

cURL Example

# Step 1: Submit generation task
PREDICTION_ID=$(curl -s -X POST https://api.atlascloud.ai/api/v1/model/generateImage \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedream-3.0",
    "prompt": "A majestic snow-capped mountain reflected in a crystal-clear lake"
  }' | jq -r '.predictionId')

echo "Prediction ID: $PREDICTION_ID"

# Step 2: Poll for result
while true; do
  RESULT=$(curl -s "https://api.atlascloud.ai/api/v1/model/getResult?predictionId=$PREDICTION_ID" \
    -H "Authorization: Bearer $ATLASCLOUD_API_KEY")
  STATUS=$(echo $RESULT | jq -r '.status')
  echo "Status: $STATUS"
  if [ "$STATUS" = "completed" ]; then
    echo $RESULT | jq -r '.output'
    break
  elif [ "$STATUS" = "failed" ]; then
    echo "Failed: $(echo $RESULT | jq -r '.error')"
    break
  fi
  sleep 2
done

Tips

  • Model selection: Try different models for different styles. Seedream excels at photorealistic images, FLUX is great for artistic styles
  • Prompt engineering: Be specific about style, composition, lighting, colors, and mood
  • Batch generation: Submit multiple requests in parallel for batch image generation
  • Error handling: Always check for failed status and handle timeouts gracefully

Next Steps