Unlocking Creative Possibilities: Integrate Image Generation with blackytom/cybotom Cognitive Actions

22 Apr 2025
Unlocking Creative Possibilities: Integrate Image Generation with blackytom/cybotom Cognitive Actions

In today's digital landscape, the ability to generate and manipulate images on-the-fly can unlock a myriad of creative applications. The blackytom/cybotom spec provides developers with powerful Cognitive Actions to generate images with enhanced capabilities, including inpainting and custom aspect ratios. By leveraging these pre-built actions, you can integrate advanced image generation functionalities into your applications seamlessly.

Prerequisites

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

  • An API key for the Cognitive Actions platform.
  • Basic knowledge of JSON and how to make HTTP requests.
  • Familiarity with Python for conceptual code examples.

For authentication, you'll typically pass your API key in the headers of your requests.

Cognitive Actions Overview

Generate Image with Inpainting

Description: This operation generates images with inpainting support using an input image or specific parameters like width, height, and custom aspect ratios. It employs a fast mode with an FP8 quantized model for optimized performance, allowing you to tweak various parameters such as quality, prompt strength, and guidance scale.

Category: Image Generation

Input

The input for this action is structured as follows:

  • prompt (required): The text prompt guiding the image generation.
  • mask (optional): URI of the image mask used in inpainting mode.
  • seed (optional): Integer seed for reproducible outputs.
  • image (optional): URI of the input image for image-to-image or inpainting.
  • width (optional): Width of the generated image in pixels (256 to 1440).
  • height (optional): Height of the generated image in pixels (256 to 1440).
  • goFast (optional): Activate fast mode for optimized performance.
  • imageAspectRatio (optional): Aspect ratio for the generated image.
  • imageOutputFormat (optional): Format of the output images (webp, jpg, png).
  • imageOutputQuality (optional): Output image quality from 0 to 100.
  • numberOfOutputs (optional): Number of outputs to generate (1 to 4).
  • promptStrength (optional): Strength of the prompt in img2img mode.
  • diffusionGuidanceScale (optional): Scale of guidance during the diffusion process.
  • numberOfInferenceSteps (optional): Number of denoising steps (1 to 50).

Example Input:

{
  "goFast": false,
  "prompt": "A tight closeup of TOM clad in sleek, futuristic armor, grips the iconic MA5B Assault Rifle from *Halo*...",
  "loraScale": 1,
  "inferenceModel": "dev",
  "promptStrength": 0.8,
  "imageMegapixels": "1",
  "numberOfOutputs": 1,
  "imageAspectRatio": "9:16",
  "imageOutputFormat": "webp",
  "imageOutputQuality": 80,
  "additionalLoraScale": 1,
  "diffusionGuidanceScale": 3,
  "numberOfInferenceSteps": 28
}

Output

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

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/0ed80045-cd38-460f-b240-72a9157ce607/7d6d45e7-c435-44eb-9888-b96f27ccfabc.webp"
]

Conceptual Usage Example (Python)

Here’s a conceptual Python code snippet showing how to invoke 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 = "dace3554-5a78-4242-a0ea-d8fe461fda99"  # Action ID for Generate Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "goFast": False,
    "prompt": "A tight closeup of TOM clad in sleek, futuristic armor, grips the iconic MA5B Assault Rifle from *Halo*...",
    "loraScale": 1,
    "inferenceModel": "dev",
    "promptStrength": 0.8,
    "imageMegapixels": "1",
    "numberOfOutputs": 1,
    "imageAspectRatio": "9:16",
    "imageOutputFormat": "webp",
    "imageOutputQuality": 80,
    "additionalLoraScale": 1,
    "diffusionGuidanceScale": 3,
    "numberOfInferenceSteps": 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 snippet, we define the action ID and input payload as per the action's schema. The request is sent to a hypothetical endpoint, and we handle potential exceptions gracefully.

Conclusion

The blackytom/cybotom Cognitive Actions provide a robust framework for developers looking to incorporate advanced image generation capabilities into their applications. By utilizing the Generate Image with Inpainting action, you can create intricate visual content tailored to your specific needs.

Consider experimenting with different parameters to explore the creative possibilities these actions can offer. Happy coding!

← Back to All Articles