Unlock Image Generation with the socialseo/michi8 Cognitive Actions

21 Apr 2025
Unlock Image Generation with the socialseo/michi8 Cognitive Actions

In the world of digital content creation, the ability to generate and modify images can be a game-changer. The socialseo/michi8 Cognitive Actions provide developers with powerful tools to perform image generation with advanced inpainting capabilities. These pre-built actions allow you to create stunning visuals based on textual prompts, adjust various parameters for quality and style, and output images in multiple formats. Let’s dive into how you can leverage these actions in your applications.

Prerequisites

Before you start using the Cognitive Actions, ensure you have the following in place:

  • An API key for the Cognitive Actions platform. This key will authenticate your requests.
  • Basic understanding of JSON and how to send HTTP requests.

Typically, authentication works by passing the API key in the headers of your HTTP requests.

Cognitive Actions Overview

Generate Inpainted Image

The Generate Inpainted Image action allows you to create images with inpainting capabilities using different models. You can modify images based on prompts, adjust parameters for quality, and choose output formats. This action is especially useful for generating unique visual content quickly.

Input

The input for this action consists of several fields. The only required field is prompt, while others are optional but can greatly influence the output.

Example Input JSON
{
  "model": "dev",
  "width": 1440,
  "height": 1440,
  "prompt": "michi8 embroidering on white fabric in a photorealistic image styled like vintage 1970s films, with a desaturated look. The girl is dressed casually in a yellow ochre sweater and jeans. The embroidery is simple, featuring designs like simple flowers. The background of the scene is a green meadow, and michi8 fills almost the entire frame, captured in a close-up shot of her upper body, as if taken with a 50mm lens.",
  "loraScale": 1,
  "megapixels": "1",
  "enableFastMode": false,
  "numberOfOutputs": 4,
  "imageAspectRatio": "3:4",
  "imageOutputFormat": "jpg",
  "numInferenceSteps": 28,
  "imageGuidanceScale": 2.05,
  "imageOutputQuality": 80,
  "imagePromptStrength": 0.8,
  "extraLoraScaleFactor": 1
}

Output

Upon successful execution, the action returns an array of image URLs corresponding to the generated images. Each URL points to a generated image based on the provided prompt and parameters.

Example Output
[
  "https://assets.cognitiveactions.com/invocations/25f23bce-5ffc-45f3-b316-6e24cf456470/a6249c35-f347-4c56-9dce-a3e52817d464.jpg",
  "https://assets.cognitiveactions.com/invocations/25f23bce-5ffc-45f3-b316-6e24cf456470/ce0fe1ce-f0b1-480a-aaff-18f507a49500.jpg",
  "https://assets.cognitiveactions.com/invocations/25f23bce-5ffc-45f3-b316-6e24cf456470/0d29ac92-1282-4d4e-bc38-8b783e1289a5.jpg",
  "https://assets.cognitiveactions.com/invocations/25f23bce-5ffc-45f3-b316-6e24cf456470/2cd46f9f-6805-437c-b8d2-571cb7effadf.jpg"
]

Conceptual Usage Example (Python)

Here is a conceptual Python code snippet to demonstrate how you might 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 = "9aa449b4-40c2-4906-8e8a-b439076b91db" # Action ID for Generate Inpainted Image

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "width": 1440,
    "height": 1440,
    "prompt": "michi8 embroidering on white fabric in a photorealistic image styled like vintage 1970s films, with a desaturated look. The girl is dressed casually in a yellow ochre sweater and jeans. The embroidery is simple, featuring designs like simple flowers. The background of the scene is a green meadow, and michi8 fills almost the entire frame, captured in a close-up shot of her upper body, as if taken with a 50mm lens.",
    "loraScale": 1,
    "megapixels": "1",
    "enableFastMode": False,
    "numberOfOutputs": 4,
    "imageAspectRatio": "3:4",
    "imageOutputFormat": "jpg",
    "numInferenceSteps": 28,
    "imageGuidanceScale": 2.05,
    "imageOutputQuality": 80,
    "imagePromptStrength": 0.8,
    "extraLoraScaleFactor": 1
}

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, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The payload is constructed based on the required input fields for the action, and the response will include the URLs to the generated images.

Conclusion

The socialseo/michi8 Cognitive Actions offer a powerful way to integrate image generation capabilities into your applications. By using the Generate Inpainted Image action, developers can create stunning, customized images based on written prompts. Whether for artistic projects, marketing materials, or content creation, these tools can enhance your workflow significantly.

Explore the possibilities, and consider experimenting with different parameters to see how you can find the best results for your specific use cases!

← Back to All Articles