Unleashing Creativity: Generate Images with Custom Inpainting Using qsmarc/df209 Actions

24 Apr 2025
Unleashing Creativity: Generate Images with Custom Inpainting Using qsmarc/df209 Actions

In the world of digital content creation, the ability to generate stunning images based on custom prompts enhances creativity and streamlines workflows. The qsmarc/df209 specification offers a powerful set of Cognitive Actions designed for image generation, specifically leveraging custom inpainting techniques. These pre-built actions enable developers to seamlessly integrate image generation capabilities into their applications with adjustable parameters like aspect ratio, image quality, and output formats.

Prerequisites

Before diving into the integration of Cognitive Actions, ensure you have the following:

  • An API key for the Cognitive Actions platform.
  • Basic familiarity with making HTTP requests in your preferred programming language.
  • Understanding of JSON format for constructing input payloads.

Typically, authentication involves passing your API key in the headers of your requests to authenticate and authorize your access to the Cognitive Actions services.

Cognitive Actions Overview

Generate Images with Custom Inpainting

The Generate Images with Custom Inpainting action allows you to create images by providing a descriptive prompt and various adjustable parameters. This action supports different inference models to optimize the balance between image quality and generation speed.

Input

The input schema for this action requires a JSON object with the following fields:

  • prompt (required): A descriptive prompt for generating the image.
  • mask (optional): URI of the image mask for inpainting mode.
  • seed (optional): Specifies the random seed for reproducible image generation.
  • image (optional): URI of the input image for image-to-image transformation.
  • width (optional): Specifies the width of the generated image.
  • height (optional): Specifies the height of the generated image.
  • imageQuality (optional): Image quality for output files, ranging from 0 to 100.
  • resultFormat (optional): Format of the output images (webp, jpg, png).
  • outputQuantity (optional): Number of images generated per request.
  • inferenceModel (optional): Select the model for inference (dev or schnell).
  • inferenceSteps (optional): Total denoising steps to perform.
  • imageAspectRatio (optional): Desired aspect ratio for the generated image.
  • additional parameters: Several additional fields to control various aspects of image generation.

Example Input Payload:

{
  "prompt": "A df-209 airsoft grenade in a comics book action scene with POW and BANG in pink",
  "imageQuality": 80,
  "resultFormat": "webp",
  "loraIntensity": 1,
  "inferenceModel": "dev",
  "inferenceSteps": 28,
  "outputQuantity": 1,
  "promptIntensity": 0.8,
  "imageAspectRatio": "1:1",
  "guidanceIntensity": 3,
  "accelerateProcessing": false,
  "approximateMegapixels": "1",
  "additionalLoraIntensity": 1
}

Output

Upon successful execution, the action typically returns a JSON array containing the URLs of the generated images.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/b8aaf015-4908-4c9d-8f6f-b03f96997ce1/c36dd517-fdaa-4fa4-a5f1-22ebacacc6c1.webp"
]

Conceptual Usage Example (Python)

Here’s how you might call the Generate Images with Custom Inpainting action using Python:

import requests
import json

# Replace with your Cognitive Actions API key and endpoint
COGNITIVE_ACTIONS_API_KEY = "YOUR_COGNITIVE_ACTIONS_API_KEY"
COGNITIVE_ACTIONS_EXECUTE_URL = "https://api.cognitiveactions.com/actions/execute" # Hypothetical endpoint

action_id = "ff6cf52c-1e07-48af-a132-2dc71bcf8706" # Action ID for Generate Images with Custom Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "A df-209 airsoft grenade in a comics book action scene with POW and BANG in pink",
    "imageQuality": 80,
    "resultFormat": "webp",
    "loraIntensity": 1,
    "inferenceModel": "dev",
    "inferenceSteps": 28,
    "outputQuantity": 1,
    "promptIntensity": 0.8,
    "imageAspectRatio": "1:1",
    "guidanceIntensity": 3,
    "accelerateProcessing": False,
    "approximateMegapixels": "1",
    "additionalLoraIntensity": 1
}

headers = {
    "Authorization": f"Bearer {COGNITIVE_ACTIONS_API_KEY}",
    "Content-Type": "application/json"
}

try:
    response = requests.post(
        COGNITIVE_ACTIONS_EXECUTE_URL,
        headers=headers,
        json={"action_id": action_id, "inputs": payload}
    )
    response.raise_for_status() # Raise an exception for bad status codes (4xx or 5xx)

    result = response.json()
    print("Action executed successfully:")
    print(json.dumps(result, indent=2))

except requests.exceptions.RequestException as e:
    print(f"Error executing action {action_id}: {e}")
    if e.response is not None:
        print(f"Response status: {e.response.status_code}")
        try:
            print(f"Response body: {e.response.json()}")
        except json.JSONDecodeError:
            print(f"Response body: {e.response.text}")

In this code snippet, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The input payload is structured according to the requirements of the action, and the action ID is specified to target the correct cognitive function.

Conclusion

The qsmarc/df209 Cognitive Actions provide developers with powerful tools for generating images through custom inpainting. With adjustable parameters, these actions can be tailored to meet specific needs, enabling diverse applications from creative design to automated content generation. By integrating these actions, you can enhance your applications and offer users innovative capabilities. Consider exploring additional use cases, such as integrating user-generated prompts or utilizing different inference models to optimize performance!

← Back to All Articles