Skip to main content
The Process API provides synchronous image generation for the Decart AI SDK. Unlike the Queue API which handles asynchronous video generation jobs, the Process API returns results immediately, making it ideal for real-time applications and interactive experiences.

​
Supported Models

The Process API supports the following image generation models:

lucy-pro-t2i

Text-to-image generation with professional quality output

lucy-pro-i2i

Image-to-image transformation and editing

​
When to Use Process vs Queue

​
Use the Process API when:

  • You need immediate results (synchronous)
  • Working with image generation (text-to-image or image-to-image)
  • Building real-time or interactive applications
  • You want a simpler API without polling or status checks

​
Use the Queue API when:

  • You need video generation (text-to-video, image-to-video, etc.)
  • Working with longer-running jobs
  • You need to track job status and handle asynchronous workflows

​
Quick Start Example

Here’s a basic example of generating an image using the Process API: 
import { createDecartClient, models } from '@decartai/sdk';

const client = createDecartClient({
  apiKey: process.env.DECART_API_KEY,
});

// Generate an image synchronously
const imageBlob = await client.process({
  model: models.image('lucy-pro-t2i'),
  prompt: 'A serene Japanese garden with cherry blossoms and a wooden bridge',
  seed: 42,
  resolution: '720p',
  orientation: 'landscape',
});

// The result is a Blob that you can save or display
const buffer = Buffer.from(await imageBlob.arrayBuffer());
fs.writeFileSync('output.png', buffer);

​
Key Features

The Process API returns the generated image immediately as a Blob. No polling or status checks required.
Use the seed parameter to generate the same image consistently with the same inputs.
Choose between 480p and 720p resolution based on your needs.
Optional prompt enhancement improves generation quality (enabled by default for i2i).

​
Return Type

The client.process() method returns a Promise<Blob> containing the generated image in PNG format. You can:
  • Save it to a file using Node.js filesystem APIs
  • Display it in a browser using URL.createObjectURL()
  • Send it via HTTP responses
  • Convert it to base64 for embedding

​
Next Steps

Synchronous Generation

Learn how to use the Process API with detailed examples

Queue API

Explore asynchronous video generation with the Queue API

Build docs developers (and LLMs) love

Get started for freeTalk to us