Elevate Your Image Generation with mcai/deliberate-v2-img2img Cognitive Actions

24 Apr 2025
Elevate Your Image Generation with mcai/deliberate-v2-img2img Cognitive Actions

In the realm of AI-driven creativity, the mcai/deliberate-v2-img2img API offers powerful Cognitive Actions that enable developers to generate stunning images from existing ones. Leveraging the Deliberate v2 model, these actions provide options for upscaling, detailed prompts, and more, allowing for a high degree of customization and quality in image creation. This guide will walk you through the capabilities of the "Generate Image with Deliberate v2" action, illustrating how you can seamlessly integrate it into your applications.

Prerequisites

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

  • An API key for the Cognitive Actions platform to authenticate your requests.
  • Basic knowledge of JSON and Python for constructing your requests and handling responses.

Authentication typically involves passing your API key in the headers of your HTTP requests.

Cognitive Actions Overview

Generate Image with Deliberate v2

The Generate Image with Deliberate v2 action allows you to create a new image based on an input image, using the Deliberate v2 model. This action is categorized under image-generation and offers extensive customization options through various parameters.

Input

The input schema for this action is defined as follows:

  • image (required): A valid URI pointing to the initial image for generating variations.
  • prompt (optional): A descriptive phrase to guide the image generation, enhancing output quality.
  • negativePrompt (optional): Phrases that guide the model away from undesired traits.
  • upscale (optional): A scaling factor for the image, ranging from 1 to 4 (default is 1).
  • strength (optional): The strength of noise applied to the image, between 0 and 1 (default is 0.5).
  • scheduler (optional): The algorithm for processing, defaulting to 'EulerAncestralDiscrete'.
  • guidanceScale (optional): Influences the guidance on image generation, with a valid range from 1 to 20 (default is 7.5).
  • numberOfOutputs (optional): Number of output images to produce (default is 1, maximum 4).
  • numberOfInferenceSteps (optional): Steps for the denoising process, ranging from 1 to 500 (default is 30).
  • seed (optional): A random seed for generating variations.

Example Input:

{
  "image": "https://replicate.delivery/pbxt/IqK12GYGsUykFdVxDjLBuZ3C8llIS5fzs94eE8QaEyBZ7klD/out-0%20%281%29.png",
  "prompt": "highres, highest quality, illustration, ultra detailed...",
  "upscale": 2,
  "strength": 0.5,
  "scheduler": "EulerAncestralDiscrete",
  "guidanceScale": 7.5,
  "negativePrompt": "disfigured, kitsch, ugly, oversaturated...",
  "numberOfOutputs": 1,
  "numberOfInferenceSteps": 30
}

Output

The output typically returns an array of image URIs generated based on the input parameters.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/15889a88-765a-427c-9f9e-40361c0dda8e/a6711af2-0a92-4b9d-8e3d-0c07e3a4f691.png"
]

Conceptual Usage Example (Python)

Here's how you might invoke the Generate Image with Deliberate v2 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 = "1ed57f6f-0f32-41b6-9ccd-ec37f63afe94"  # Action ID for Generate Image with Deliberate v2

# Construct the input payload based on the action's requirements
payload = {
    "image": "https://replicate.delivery/pbxt/IqK12GYGsUykFdVxDjLBuZ3C8llIS5fzs94eE8QaEyBZ7klD/out-0%20%281%29.png",
    "prompt": "highres, highest quality, illustration, ultra detailed...",
    "upscale": 2,
    "strength": 0.5,
    "scheduler": "EulerAncestralDiscrete",
    "guidanceScale": 7.5,
    "negativePrompt": "disfigured, kitsch, ugly, oversaturated...",
    "numberOfOutputs": 1,
    "numberOfInferenceSteps": 30
}

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, you can see how to structure your input payload according to the action's requirements. The action ID and input parameters are clearly defined, and the endpoint URL is illustrative of a hypothetical Cognitive Actions execution endpoint.

Conclusion

The mcai/deliberate-v2-img2img Cognitive Actions provide developers with powerful tools to enhance their applications through sophisticated image generation capabilities. By integrating the Generate Image with Deliberate v2 action, you can easily create visually striking images tailored to your specifications. Whether for artistic endeavors, content creation, or innovative applications, the possibilities are endless. Consider exploring additional use cases and experimenting with various input parameters to fully leverage the potential of this cutting-edge API.

← Back to All Articles