Unleashing Creativity: Generating Images with Inpainting Using mofleck/teslasemishipped Cognitive Actions

21 Apr 2025
Unleashing Creativity: Generating Images with Inpainting Using mofleck/teslasemishipped Cognitive Actions

Cognitive Actions from the mofleck/teslasemishipped spec provide an exciting opportunity for developers to integrate advanced image generation capabilities into their applications. These actions leverage inpainting techniques to create stunning and customized images, offering various options for model selection, aspect ratios, and output formats. Whether you're looking to create artistic visuals or realistic images, these pre-built actions simplify the process, allowing you to focus on your application's core functionality.

Prerequisites

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

  • An API key for the Cognitive Actions platform, allowing you to authenticate requests.
  • A basic understanding of JSON and how to structure data for API calls.

In general, authentication can be handled by including the API key in the request headers, typically as a Bearer token.

Cognitive Actions Overview

Generate Image with Inpainting

The Generate Image with Inpainting action allows developers to create images using inpainting techniques. It enables customization through options like model selection, aspect ratios, and prompt strength. The 'schnell' model supports faster inference, making it ideal for quick image generation.

  • Category: image-generation

Input

The input for this action is structured as follows:

{
  "prompt": "Your descriptive prompt here",
  "mask": "http://example.com/mask.png", // Optional
  "image": "http://example.com/input.png", // Optional
  "width": 512, // Optional
  "height": 512, // Optional
  "fastMode": true, // Optional
  "loraScale": 1,
  "modelType": "dev",
  "randomSeed": 42, // Optional
  "imageFormat": "webp",
  "guidanceScale": 3.5,
  "outputQuality": 90,
  "inferenceSteps": 28,
  "outputQuantity": 1,
  "promptStrength": 0.8,
  "imageAspectRatio": "1:1",
  "additionalLoraScale": 1
}

Example Input:

{
  "prompt": "TOKTesla-Semi-shipped a colorful Tesla car parked in an empty parking lot at night. The car is covered in a colorful, abstract design with the word \"TESLA\" written in bold letters in the center.",
  "loraScale": 1,
  "modelType": "dev",
  "imageFormat": "webp",
  "guidanceScale": 3.5,
  "outputQuality": 90,
  "inferenceSteps": 28,
  "outputQuantity": 1,
  "promptStrength": 0.8,
  "imageAspectRatio": "1:1",
  "additionalLoraScale": 1
}

Output

The output of this action is a URL pointing to the generated image. The typical response is structured as follows:

[
  "https://assets.cognitiveactions.com/invocations/e371ef87-cbd2-4dce-8c32-847e0488c9a7/3043eccf-e33f-4213-83af-a4b9dfe6c76c.webp"
]

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/e371ef87-cbd2-4dce-8c32-847e0488c9a7/3043eccf-e33f-4213-83af-a4b9dfe6c76c.webp"
]

Conceptual Usage Example (Python)

Here’s how you could implement a call to the Generate Image with Inpainting 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 = "2ac8b3cd-d044-4100-aea4-2a71282d9f7a" # Action ID for Generate Image with Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "TOKTesla-Semi-shipped a colorful Tesla car parked in an empty parking lot at night. The car is covered in a colorful, abstract design.",
    "loraScale": 1,
    "modelType": "dev",
    "imageFormat": "webp",
    "guidanceScale": 3.5,
    "outputQuality": 90,
    "inferenceSteps": 28,
    "outputQuantity": 1,
    "promptStrength": 0.8,
    "imageAspectRatio": "1:1",
    "additionalLoraScale": 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 Python code snippet, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The action ID and input payload are structured to fit the requirements of the Generate Image with Inpainting action.

Conclusion

The mofleck/teslasemishipped Cognitive Actions provide developers with powerful tools to generate and manipulate images through inpainting techniques. From customizing image prompts to selecting models optimized for speed, these actions enhance the creative possibilities for application developers. Start integrating these capabilities into your projects and explore the potential of AI-driven image generation!

← Back to All Articles