Generate Stunning Images with the anotherjesse/multi-control Cognitive Actions

22 Apr 2025
Generate Stunning Images with the anotherjesse/multi-control Cognitive Actions

In the realm of image generation, the anotherjesse/multi-control Cognitive Actions offer an exciting way to leverage multiple control images—such as QR codes, pose data, and edge detection—to create structured and guided images. These pre-built actions enable developers to enhance their applications with advanced image generation features, facilitating creative projects without the need for extensive machine learning expertise.

Prerequisites

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

  • An API key for the Cognitive Actions platform, which will be used to authenticate your requests.
  • Basic knowledge of JSON for constructing requests and handling responses.

Authentication typically involves passing the API key in the request headers.

Cognitive Actions Overview

Generate Image with Multi-Control

Description:
This action utilizes various control images to generate a structured image based on a provided prompt, enhancing the creative flexibility for developers in generating unique visuals.

Category: Image Generation

Input

The input for this action is defined by the following schema:

  • Required Fields:
    • prompt: A string guiding the model in generating output images.
  • Optional Fields:
    • seed: (integer) An integer seed for reproducible results.
    • qrScale: (number) Multiplier for QR controlnet influence.
    • hedScale: (number) Multiplier for HED controlnet influence.
    • segScale: (number) Multiplier for segmentation controlnet.
    • poseScale: (number) Multiplier for pose controlnet influence.
    • cannyScale: (number) Multiplier for canny controlnet.
    • depthScale: (number) Multiplier for depth controlnet influence.
    • houghScale: (number) Multiplier for Hough controlnet contribution.
    • normalScale: (number) Controls normal controlnet effect.
    • outputCount: (integer) Specifies the number of images to generate (1 to 10).
    • guidanceScale: (number) Determines the influence level for classifier-free guidance.
    • imageResolution: (integer) Specifies the smallest image dimension (256, 512, 768).
    • Various control images (e.g., qrControlImage, hedControlImage, etc.) which are URLs directing to the respective control images.

Example Input:

{
  "prompt": "whippet, flemish baroque, el yunque rainforest, 35mm film, quadtone color grading, chromakey\n",
  "qrScale": 1.47,
  "hedScale": 1,
  "segScale": 1,
  "poseScale": 1,
  "cannyScale": 1,
  "depthScale": 1,
  "houghScale": 1,
  "normalScale": 1,
  "outputCount": 1,
  "guidanceScale": 9,
  "imageResolution": 512,
  "qrControlImage": "https://replicate.delivery/pbxt/J0ZYvssNVIBI906LgbXe5kpjkMrugsb5gDklk6erALej1efO/replicate-qr.png"
}

Output

The action typically returns a URL link to the generated image.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/9f3a8adb-1a09-447f-9cf7-40eb82293002/5c1ff77f-75b0-4612-a25c-f8823512845e.png"
]

Conceptual Usage Example (Python)

Here's a conceptual Python code snippet illustrating how to call this 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 = "dae28c26-f9f0-4315-bc70-983b585849f4"  # Action ID for Generate Image with Multi-Control

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "whippet, flemish baroque, el yunque rainforest, 35mm film, quadtone color grading, chromakey\n",
    "qrScale": 1.47,
    "guidanceScale": 9,
    "imageResolution": 512,
    "qrControlImage": "https://replicate.delivery/pbxt/J0ZYvssNVIBI906LgbXe5kpjkMrugsb5gDklk6erALej1efO/replicate-qr.png"
}

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 snippet:

  • Replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key.
  • The action_id corresponds to the "Generate Image with Multi-Control" action.
  • The payload is structured based on the input schema, ensuring all required fields are filled appropriately.

Conclusion

The anotherjesse/multi-control Cognitive Actions provide a powerful toolset for developers looking to enhance their applications with advanced image generation capabilities. By utilizing a variety of control images, you can create stunning visuals tailored to your specific needs. Explore integrating these actions into your projects today, and unleash the potential of automated image creation!

← Back to All Articles