Create Stunning Custom Images with the Cognitive Actions from charlesmccarthy/cog-iniverse

24 Apr 2025
Create Stunning Custom Images with the Cognitive Actions from charlesmccarthy/cog-iniverse

In today's digital landscape, the ability to generate high-quality images from textual descriptions has become increasingly valuable. The Cognitive Actions from the charlesmccarthy/cog-iniverse spec allow developers to leverage advanced image generation capabilities to create customized images based on detailed prompts. With options to adjust various parameters, these actions offer flexibility and power for developers looking to enhance their applications with creative visual content.

Prerequisites

Before you start integrating the Cognitive Actions, ensure you have the following:

  • An API key for the Cognitive Actions platform.
  • Basic familiarity with JSON and API requests.
  • A configured environment to run Python code and make HTTP requests.

Authentication typically involves passing your API key in the request headers to authorize your actions.

Cognitive Actions Overview

Generate Customized Images

The Generate Customized Images action enables you to create images using a textual description. You can fine-tune various parameters to control the output, including dimensions, model type, and additional settings.

  • Category: Image Generation

Input

The input for this action is structured as follows:

{
  "seed": -1,
  "steps": 35,
  "width": 1184,
  "height": 864,
  "prompt": "1girl, cat girl, cat ears, cat tail, yellow eyes, white hair, bob cut, from side, scenery, sunset",
  "batchSize": 1,
  "modelType": "guofengv11.safetensors",
  "configScale": 7,
  "addPreprompt": true,
  "scheduleType": "DPM++ 2M SDE Karras",
  "negativePrompt": "unaestheticXL_Sky3.1, animal, cat, dog, big breasts",
  "guidanceRescale": 0.7,
  "variationalAutoEncoder": "sdxl-vae-fp16-fix"
}

Key Fields:

  • seed: Integer for random generation (-1 for random).
  • steps: Number of steps (1-100) to perform during generation.
  • width and height: Dimensions of the generated image (1-2048 pixels).
  • prompt: Descriptive text guiding the image generation.
  • batchSize: Number of images to generate (1-4).
  • modelType: Specifies the ML model to be used.
  • configScale: Determines adherence to the prompt (1-30).
  • addPreprompt: Boolean to prepend a predefined string to the prompt.
  • scheduleType: Algorithm for guiding image generation.
  • negativePrompt: Undesired elements to avoid in the output.
  • guidanceRescale: Degree of CFG noise rescaling (0-1).
  • variationalAutoEncoder: Specifies the VAE model.

Output

Upon successful execution, the action returns a URL pointing to the generated image. Here’s an example of the output:

[
  "https://assets.cognitiveactions.com/invocations/28631c62-6f32-4052-86d2-2c204a9172d8/d1c7db9e-2d53-4dc2-bd94-6c99cf1c040d.png"
]

Conceptual Usage Example (Python)

Here’s a conceptual Python snippet to demonstrate how to call the Generate Customized Images 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 = "d88a5714-9e43-433d-834c-fa7370a37434"  # Action ID for Generate Customized Images

# Construct the input payload based on the action's requirements
payload = {
    "seed": -1,
    "steps": 35,
    "width": 1184,
    "height": 864,
    "prompt": "1girl, cat girl, cat ears, cat tail, yellow eyes, white hair, bob cut, from side, scenery, sunset",
    "batchSize": 1,
    "modelType": "guofengv11.safetensors",
    "configScale": 7,
    "addPreprompt": true,
    "scheduleType": "DPM++ 2M SDE Karras",
    "negativePrompt": "unaestheticXL_Sky3.1, animal, cat, dog, big breasts",
    "guidanceRescale": 0.7,
    "variationalAutoEncoder": "sdxl-vae-fp16-fix"
}

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:

  • Replace "YOUR_COGNITIVE_ACTIONS_API_KEY" with your actual API key.
  • The action_id variable holds the ID for the "Generate Customized Images" action.
  • The payload dictionary is structured according to the required input schema.

Conclusion

The Generate Customized Images action from the charlesmccarthy/cog-iniverse spec empowers developers to create visually appealing images tailored to specific descriptions. By leveraging its customizable parameters, you can enhance user engagement and enrich your applications.

For further exploration, consider integrating other Cognitive Actions in your project to extend functionality and provide more interactive experiences!

← Back to All Articles