Unlocking Creativity: Generate Images with Inpainting Using Cognitive Actions

24 Apr 2025
Unlocking Creativity: Generate Images with Inpainting Using Cognitive Actions

In today's digital landscape, the ability to generate and manipulate images through artificial intelligence is transforming how developers approach creative projects. The Cognitive Actions in the alexandercgo2/craisee5 spec offer an innovative solution for image generation, particularly through the action Generate Image with Inpainting. This action empowers developers to create images from text prompts while providing advanced options for customization, including inpainting capabilities. By leveraging these pre-built actions, you can enhance your applications with powerful image generation features without the need for extensive AI expertise.

Prerequisites

To start using the Cognitive Actions, you need to ensure that you have the following prerequisites:

  • An API key for the Cognitive Actions platform to authenticate your requests.
  • Basic knowledge of making API calls and handling JSON payloads.
  • A development environment set up with Python and the requests library for making HTTP requests.

Authentication typically involves including your API key in the headers of your requests, allowing you to securely access the Cognitive Actions functionalities.

Cognitive Actions Overview

Generate Image with Inpainting

The Generate Image with Inpainting action allows you to create images based on textual descriptions while supporting features like image-to-image transformations and inpainting. You can specify additional parameters such as mask input, model selection, and image dimensions to fine-tune the output.

Input

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

  • prompt (required): A text description guiding the image generation. Example: "a big bear in santa claus costume in a photostudio, in the style of CRAISEE".
  • Other optional fields include:
    • model: Select between "dev" and "schnell" (default: "dev").
    • width and height: Specify dimensions (only for custom aspect ratios).
    • outputCount: Number of variations to generate (1 to 4).
    • outputFormat: Format for the generated images (e.g., "webp", "jpg").
    • guidanceScale: Affects the image generation guidance (default: 3).
    • promptStrength: Determines how much to alter the original image in img2img processes.

Here’s an example of a JSON payload for this action:

{
  "model": "dev",
  "prompt": "a big bear in santa claus costume in a photostudio, in the style of CRAISEE",
  "loraScale": 1,
  "aspectRatio": "1:1",
  "outputCount": 1,
  "outputFormat": "webp",
  "guidanceScale": 3.5,
  "outputQuality": 90,
  "extraLoraScale": 1,
  "promptStrength": 0.8,
  "inferenceStepCount": 28
}

Output

The action typically returns a JSON array containing the URLs of the generated images. For example:

[
  "https://assets.cognitiveactions.com/invocations/7771e550-e89f-4bbc-a87a-843e1bf1dcfb/9d856bdf-853f-4819-b112-4900aacfe7ad.webp"
]

Conceptual Usage Example (Python)

Here’s a conceptual Python code snippet demonstrating how to use the Generate Image with Inpainting action:

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 = "d78b6593-4c94-4743-8a7f-1d035405e6bf"  # Action ID for Generate Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "prompt": "a big bear in santa claus costume in a photostudio, in the style of CRAISEE",
    "loraScale": 1,
    "aspectRatio": "1:1",
    "outputCount": 1,
    "outputFormat": "webp",
    "guidanceScale": 3.5,
    "outputQuality": 90,
    "extraLoraScale": 1,
    "promptStrength": 0.8,
    "inferenceStepCount": 28
}

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 code, you replace the API key and endpoint with your actual values. The payload is structured according to the action's requirements, and the response is printed out to show the generated image URLs.

Conclusion

The Generate Image with Inpainting action from the alexandercgo2/craisee5 spec provides a robust toolset for developers looking to incorporate advanced image generation capabilities into their applications. By utilizing the options for customization, you can create unique images tailored to your specific needs. As you explore further, consider integrating this action into various use cases, such as creative applications, marketing materials, or even enhancing user-generated content. Happy coding!

← Back to All Articles