Unlocking Creativity: Generate Images with the juddisjudd/barricadettv Cognitive Actions

21 Apr 2025
Unlocking Creativity: Generate Images with the juddisjudd/barricadettv Cognitive Actions

In today's digital landscape, the ability to generate and manipulate images programmatically can open up a myriad of possibilities for developers. The juddisjudd/barricadettv spec offers a powerful Cognitive Action that allows you to generate images using advanced techniques like inpainting and image-to-image transformations. This action provides customizable parameters to fit diverse use cases, enabling you to create visually stunning content with just a few API calls.

Prerequisites

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

  • An API key for the Cognitive Actions platform.
  • A basic understanding of JSON structures and API requests.

For authentication, you will typically pass your API key in the headers of your requests, ensuring secure access to the Cognitive Actions.

Cognitive Actions Overview

Generate Image with Inpainting and Image-to-Image

Description: This action allows you to generate images through inpainting and image-to-image conversion. You can customize various parameters such as aspect ratio, dimensions, and model selection to achieve the desired output. The action supports two models: 'dev' for optimal performance and 'schnell' for faster results.

Input

The input schema for this action requires a prompt and optionally includes various parameters for customization.

  • Required:
    • prompt: A string that describes the desired image content.
  • Optional:
    • mask: URI of the image mask for inpainting.
    • seed: Random seed for reproducibility.
    • image: URI of the input image for transformation.
    • width: Width of the generated image (in pixels).
    • height: Height of the generated image (in pixels).
    • fastMode: Boolean to enable faster image generation.
    • loraScale: Controls the intensity of the main LoRA application.
    • megapixels: Approximate number of megapixels for the generated image.
    • numOutputs: Number of images to generate.
    • aspectRatio: Specifies the aspect ratio for the generated image.
    • outputFormat: Format of the output images.
    • guidanceScale: Scale for the diffusion process.
    • outputQuality: Quality setting for the output images.
    • additionalLora: Specifies additional LoRA weights.
    • extraLoraScale: Adjusts the application intensity of extra LoRA weights.
    • inferenceModel: Selects the model for inference.
    • promptStrength: Strength of the prompt when using img2img.
    • trainingWeights: Loads additional LoRA weights from various sources.
    • numInferenceSteps: Number of denoising steps.
    • disableSafetyChecker: Disables the safety checker.

Example Input:

{
  "width": 742,
  "height": 906,
  "prompt": "a photo of barricadettv posing for the camera in an old magic shop, photorealistic, film, 35mm",
  "loraScale": 1,
  "numOutputs": 4,
  "aspectRatio": "1:1",
  "outputFormat": "png",
  "guidanceScale": 3.5,
  "outputQuality": 100,
  "extraLoraScale": 0.8,
  "inferenceModel": "dev",
  "promptStrength": 0.8,
  "numInferenceSteps": 28
}

Output

The action will return an array of image URLs corresponding to the generated outputs.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/0c3428cb-d941-434b-9638-76a5cda4c899/bbe223b9-ad2b-41a7-b581-e6e2e374544c.png",
  "https://assets.cognitiveactions.com/invocations/0c3428cb-d941-434b-9638-76a5cda4c899/b4403c9c-be5a-44d8-b223-f7e8234ee5a6.png",
  "https://assets.cognitiveactions.com/invocations/0c3428cb-d941-434b-9638-76a5cda4c899/fb15f17d-7879-448e-837f-9f12f9225a5d.png",
  "https://assets.cognitiveactions.com/invocations/0c3428cb-d941-434b-9638-76a5cda4c899/70f45b44-5c7a-431c-8ac2-a9d67a83f627.png"
]

Conceptual Usage Example (Python)

Here's a conceptual example of how to call the Cognitive Actions execution endpoint 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 = "c9f4d616-8db8-4813-97a9-5f4a75f92b61"  # Action ID for Generate Image with Inpainting and Image-to-Image

# Construct the input payload based on the action's requirements
payload = {
    "width": 742,
    "height": 906,
    "prompt": "a photo of barricadettv posing for the camera in an old magic shop, photorealistic, film, 35mm",
    "loraScale": 1,
    "numOutputs": 4,
    "aspectRatio": "1:1",
    "outputFormat": "png",
    "guidanceScale": 3.5,
    "outputQuality": 100,
    "extraLoraScale": 0.8,
    "inferenceModel": "dev",
    "promptStrength": 0.8,
    "numInferenceSteps": 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, remember to replace the COGNITIVE_ACTIONS_API_KEY and COGNITIVE_ACTIONS_EXECUTE_URL with your actual API key and endpoint. The action_id corresponds to the action you wish to execute. The payload is structured to match the required input for generating the image.

Conclusion

The Generate Image with Inpainting and Image-to-Image action in the juddisjudd/barricadettv spec offers developers a robust tool for image generation, allowing creativity to flourish through customizable options. By integrating these Cognitive Actions into your applications, you can elevate user experiences with unique visual content. Explore the possibilities and start creating today!

← Back to All Articles