Skip to main content

​
Overview

The process() method generates images synchronously and returns the result as a Blob. This method is available for image models only (lucy-pro-t2i and lucy-pro-i2i).

​
Method Signature

client.process<T extends ImageModelDefinition>(
  options: ProcessOptions<T>
): Promise<Blob>

​
Parameters

​
model
ImageModelDefinition
required
The image model definition to use for generation.Available models:
  • models.image("lucy-pro-t2i") - Text-to-image generation
  • models.image("lucy-pro-i2i") - Image-to-image editing
​
prompt
string
required
Text description for the generation or editing.
  • Maximum length: 1000 characters
  • For text-to-image: Describe what you want to generate
  • For image-to-image: Describe the changes to apply
See the Prompt Engineering guide for best practices.
​
data
FileInput
Required for image-to-image (lucy-pro-i2i) only. The source image to edit.Accepted types:
  • File - Browser File object
  • Blob - Binary data
  • ReadableStream - Stream of data
  • URL - URL object
  • string - URL string
  • ReactNativeFile - React Native file format
​
seed
number
Random seed for reproducible results.Using the same seed with identical prompt and settings produces the same output every time. Useful for testing and debugging.
​
resolution
'480p' | '720p'
default:"720p"
Output resolution for the generated image.
​
orientation
'landscape' | 'portrait'
default:"landscape"
Output orientation for the generated image.
​
enhance_prompt
boolean
default:"true"
Whether to enhance the prompt automatically.For best results, keep this enabled to let Decart’s AI enhance your prompts. Only disable if you need exact prompt control.Available for lucy-pro-i2i only.
​
signal
AbortSignal
Optional AbortSignal for canceling the request.
const controller = new AbortController();
client.process({ model, prompt, signal: controller.signal });
// Later: controller.abort();

​
Return Value

​
result
Promise<Blob>
Returns a Promise that resolves to a Blob containing the generated image data.The Blob can be:
  • Converted to a URL using URL.createObjectURL(blob)
  • Downloaded as a file
  • Sent to a server
  • Displayed in an <img> element

​
Examples

​
Text-to-Image Generation

Generate an image from a text prompt: 
import { createDecartClient, models } from "@decart/sdk";

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

const blob = await client.process({
  model: models.image("lucy-pro-t2i"),
  prompt: "A serene mountain landscape at sunset with vibrant colors",
  resolution: "720p",
  orientation: "landscape",
  seed: 42, // Optional: for reproducible results
});

// Use the generated image
const imageUrl = URL.createObjectURL(blob);
document.getElementById("output").src = imageUrl;

​
Image-to-Image Editing

Edit an existing image using a text prompt: 
import { createDecartClient, models } from "@decart/sdk";

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

// Load an image file
const fileInput = document.getElementById("imageInput");
const sourceImage = fileInput.files[0];

const blob = await client.process({
  model: models.image("lucy-pro-i2i"),
  prompt: "Add autumn foliage and warm lighting",
  data: sourceImage,
  resolution: "720p",
  enhance_prompt: true,
});

// Display the edited image
const imageUrl = URL.createObjectURL(blob);
document.getElementById("output").src = imageUrl;

​
With Cancellation

Cancel a long-running generation: 
const controller = new AbortController();

try {
  const blob = await client.process({
    model: models.image("lucy-pro-t2i"),
    prompt: "Complex detailed cityscape",
    signal: controller.signal,
  });
  
  // Use the result
  const url = URL.createObjectURL(blob);
} catch (error) {
  if (error.name === "AbortError") {
    console.log("Generation cancelled");
  }
}

// Cancel from another function/event
button.onclick = () => controller.abort();

​
Using with URLs

Edit an image from a URL: 
const blob = await client.process({
  model: models.image("lucy-pro-i2i"),
  prompt: "Convert to black and white with high contrast",
  data: "https://example.com/image.jpg",
  resolution: "720p",
});

​
Error Handling

The method throws errors in the following cases:
  • Invalid inputs: When parameters don’t match the model’s input schema
  • Network errors: When the API request fails
  • Authentication errors: When the API key is invalid
  • Abort errors: When the request is cancelled via AbortSignal
try {
  const blob = await client.process({
    model: models.image("lucy-pro-t2i"),
    prompt: "Beautiful landscape",
  });
} catch (error) {
  if (error.code === "INVALID_INPUT") {
    console.error("Invalid parameters:", error.message);
  } else if (error.code === "AUTHENTICATION_ERROR") {
    console.error("Invalid API key");
  } else {
    console.error("Generation failed:", error);
  }
}

​
Notes

  • Only image models (lucy-pro-t2i and lucy-pro-i2i) support synchronous processing
  • For video generation, use the queue API instead
  • Maximum prompt length is 1000 characters
  • The method validates inputs against the model’s schema before sending the request
  • File inputs are automatically converted to the appropriate format

Build docs developers (and LLMs) love

Get started for freeTalk to us