Unleashing Creativity: Integrate Image Generation with astelvida/pacb Cognitive Actions

22 Apr 2025
Unleashing Creativity: Integrate Image Generation with astelvida/pacb Cognitive Actions

In the digital age, the ability to create and manipulate images on demand can significantly enhance user engagement and application functionality. The astelvida/pacb specification offers a powerful Cognitive Action designed for developers looking to leverage advanced image generation capabilities. The action, "Generate Image with Inpainting," allows for dynamic image creation through sophisticated techniques like image-to-image transformation and inpainting, offering a framework for crafting unique visual content.

Prerequisites

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

  • API Key: You will need a valid API key to authenticate your requests to the Cognitive Actions platform.
  • Setup: Familiarity with making HTTP requests in your programming environment of choice, particularly in Python for the examples provided.

Authentication is typically handled by including the API key in the request headers.

Cognitive Actions Overview

Generate Image with Inpainting

The "Generate Image with Inpainting" action empowers users to create images based on textual prompts, while also allowing for inpainting modifications to existing images. This action supports various models for balanced or optimized outputs and accommodates diverse image formats and quality settings.

Input

The input_schema for this action is as follows:

  • prompt (required): Describes the desired characteristics of the generated image.
  • mask (optional): URI of an image mask for inpainting, overriding size specifications.
  • seed (optional): Integer for random number generation to ensure consistent results.
  • image (optional): URI pointing to an input image for modifications.
  • width (optional): Custom width for the generated image (only applicable if aspect_ratio is 'custom').
  • height (optional): Custom height for the generated image (only applicable if aspect_ratio is 'custom').
  • modelType (optional): Specifies the model to use ('dev' or 'schnell').
  • outputFormat (optional): Format for the output image (webp, jpg, png).
  • guidanceScale (optional): Numerical value guiding the image generation process.
  • outputQuality (optional): Quality of the output on a scale from 0 to 100.
  • numberOfOutputs (optional): Specifies how many images to generate simultaneously (maximum of 4).
  • numInferenceSteps (optional): Number of denoising steps for enhanced detail.
  • additional options: Several other parameters allow fine-tuning of the image generation process, including additional LoRA weights and scaling factors.

Here’s a practical example of the input JSON payload:

{
  "prompt": "PACB pop art comic book image of a triumphant woman with bold, exaggerated features strides confidently away from a crumbling corporate skyscraper, pieces of glass depicted with sparkling Ben-Day dots falling behind her. She wears a power suit in vibrant purplish-blue, accented with acid yellow. The background bursts with dynamic lines and vibrant hues of dull green and Life Magazine red. A speech bubble with assertive, clear text declares: \"Glass ceilings? I prefer skylights!\" The image conveys empowerment and the breaking of societal barriers with high-brow humor.",
  "modelType": "dev",
  "outputFormat": "webp",
  "guidanceScale": 3.5,
  "outputQuality": 90,
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "imageAspectRatio": "1:1",
  "numInferenceSteps": 28,
  "mainLoraScalingFactor": 1,
  "additionalLoraScalingFactor": 1
}

Output

Upon successful execution, the action typically returns a URL to the generated image, which can then be utilized or displayed as needed. Here’s an example of the output:

[
  "https://assets.cognitiveactions.com/invocations/9a5bd226-826b-4d15-96f8-e7b83a394454/62cc5ee9-d9ab-4883-97b8-8a7671978bc9.webp"
]

Conceptual Usage Example (Python)

Below is a conceptual Python code snippet to illustrate how to call the Cognitive Actions execution endpoint:

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 = "a660bca4-3d76-49f5-863e-2de6c63c2393" # Action ID for Generate Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
  "prompt": "PACB pop art comic book image of a triumphant woman with bold, exaggerated features strides confidently away from a crumbling corporate skyscraper, pieces of glass depicted with sparkling Ben-Day dots falling behind her. She wears a power suit in vibrant purplish-blue, accented with acid yellow. The background bursts with dynamic lines and vibrant hues of dull green and Life Magazine red. A speech bubble with assertive, clear text declares: \"Glass ceilings? I prefer skylights!\" The image conveys empowerment and the breaking of societal barriers with high-brow humor.",
  "modelType": "dev",
  "outputFormat": "webp",
  "guidanceScale": 3.5,
  "outputQuality": 90,
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "imageAspectRatio": "1:1",
  "numInferenceSteps": 28,
  "mainLoraScalingFactor": 1,
  "additionalLoraScalingFactor": 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} # Hypothetical structure
    )
    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 snippet, the action ID and input payload are structured appropriately for the request. The endpoint URL and request structure are illustrative, focusing on how to format the necessary input.

Conclusion

The "Generate Image with Inpainting" action from the astelvida/pacb specification provides developers with a robust tool for creating engaging and customized images. By leveraging the power of AI-driven image generation, you can enhance your applications and captivate your users with unique visual content. Explore the possibilities and consider integrating this action into your next project to elevate your user experience!

← Back to All Articles