Create Stunning Images with the siamakf/campfire-all-characters Cognitive Action

24 Apr 2025
Create Stunning Images with the siamakf/campfire-all-characters Cognitive Action

In the realm of artificial intelligence, image generation has become a fascinating frontier, allowing developers to create unique visuals based on textual prompts. The siamakf/campfire-all-characters spec introduces a powerful Cognitive Action that enables seamless image generation through specified inputs and customizations. This article will guide you through leveraging this action to generate captivating images tailored to your needs.

Prerequisites

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

  • API Key: You will need a valid API key from the Cognitive Actions platform to authenticate your requests.
  • Understanding of JSON: Familiarity with JSON format for constructing input payloads will be beneficial.

Authentication typically involves passing the API key in the headers of your HTTP requests, allowing secure access to the Cognitive Actions functionalities.

Cognitive Actions Overview

Generate Image Using Custom Mask and Prompt

Purpose:
This action creates an image based on a specified text prompt and input image while allowing for customization through options like inpainting, image dimensions, and refinement styles. You can generate up to four outputs, adjust the guidance scale, and even apply a watermark.

Category: Image Generation

Input

The action requires a structured input. Below is the schema and an example for clarifying the necessary fields:

{
  "mask": "http://example.com/mask.png",
  "seed": 12345,
  "image": "http://example.com/input.png",
  "width": 1024,
  "height": 1024,
  "prompt": "cute cartoon female mafioso cat smirking, wearing pink dress, animal crossing",
  "refine": "expert_ensemble_refiner",
  "loraScale": 0.6,
  "scheduler": "K_EULER",
  "guidanceScale": 7.5,
  "applyWatermark": true,
  "negativePrompt": "realistic, multiple characters",
  "promptStrength": 0.8,
  "numberOfOutputs": 4,
  "highNoiseFraction": 0.8,
  "numberOfInferenceSteps": 75
}

Example Input:

{
  "width": 1024,
  "height": 1024,
  "prompt": "cute cartoon female mafioso cat smirking, wearing pink dress, animal crossing",
  "refine": "expert_ensemble_refiner",
  "loraScale": 0.6,
  "scheduler": "K_EULER",
  "guidanceScale": 7.5,
  "applyWatermark": true,
  "negativePrompt": "realistic, multiple characters",
  "promptStrength": 0.8,
  "numberOfOutputs": 4,
  "highNoiseFraction": 0.8,
  "numberOfInferenceSteps": 75
}

Output

The action returns a list of URLs pointing to the generated images. Here’s an example of the output you may receive:

[
  "https://assets.cognitiveactions.com/invocations/6703917c-7bbd-4191-9983-0bae62870340/bd11fd93-a2a8-433d-94af-339b65ba3aac.png",
  "https://assets.cognitiveactions.com/invocations/6703917c-7bbd-4191-9983-0bae62870340/35057240-1585-4041-8d8a-81069fe8b834.png",
  "https://assets.cognitiveactions.com/invocations/6703917c-7bbd-4191-9983-0bae62870340/6915c985-ffbc-4bb6-bb68-5122606ab2f4.png",
  "https://assets.cognitiveactions.com/invocations/6703917c-7bbd-4191-9983-0bae62870340/54d604ab-9a82-49f0-9be7-4cf0d8f47ada.png"
]

Conceptual Usage Example (Python)

Here's how you might invoke this 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 = "9d8a369a-9af9-4c51-8b3d-f97fa132a9dc"  # Action ID for Generate Image Using Custom Mask and Prompt

# Construct the input payload based on the action's requirements
payload = {
    "width": 1024,
    "height": 1024,
    "prompt": "cute cartoon female mafioso cat smirking, wearing pink dress, animal crossing",
    "refine": "expert_ensemble_refiner",
    "loraScale": 0.6,
    "scheduler": "K_EULER",
    "guidanceScale": 7.5,
    "applyWatermark": True,
    "negativePrompt": "realistic, multiple characters",
    "promptStrength": 0.8,
    "numberOfOutputs": 4,
    "highNoiseFraction": 0.8,
    "numberOfInferenceSteps": 75
}

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 Python code snippet, replace "YOUR_COGNITIVE_ACTIONS_API_KEY" with your actual API key. The payload structure corresponds to the action's input schema, ensuring that all necessary parameters are included.

Conclusion

The siamakf/campfire-all-characters Cognitive Action empowers developers to create customized images effortlessly, enriching applications with unique visuals. Whether you are looking to generate artwork, illustrations, or any imaginative visuals, this action provides all the necessary tools to bring your concepts to life. Start integrating today and explore the endless possibilities of image generation!

← Back to All Articles