image-generation

Create Stunning Images with Fcm2's Image Generation Action

26 Apr 2025
Create Stunning Images with Fcm2's Image Generation Action

In the age of digital content, visual appeal is paramount. Fcm2 offers a powerful set of Cognitive Actions designed to streamline the process of generating and refining images directly from textual descriptions. With the ability to create custom visuals that can be tailored to specific needs, this service not only enhances creativity but also significantly reduces the time and effort required to produce high-quality images.

Imagine crafting unique illustrations for your blog, generating artwork for marketing campaigns, or even producing concept visuals for presentations—all with just a few lines of code. Fcm2's image generation capabilities provide developers with versatile tools to automate image creation, making it an ideal solution for designers, content creators, and businesses looking to elevate their visual content.

Prerequisites

Before you dive into integrating Fcm2's Cognitive Actions, ensure you have a valid API key and a basic understanding of making API calls.

Generate And Refine Images

The "Generate And Refine Images" action within Fcm2 allows you to create images from textual prompts, offering a variety of options for inpainting and refining techniques. This action includes features such as customizable output size, randomization through seed settings, and watermark application, making it a comprehensive tool for image generation.

Purpose

This action solves the problem of generating high-quality images based on user-defined text descriptions. By allowing for inpainting and various refinement techniques, it provides developers with a flexible solution for creating visually engaging content tailored to their specific requirements.

Input Requirements

The input for this action is structured as an object that includes parameters such as:

  • prompt: A textual description guiding the image generation.
  • width and height: Dimensions of the output image.
  • seed: For random number generation.
  • mask: URI for inpainting mode.
  • loraScale: Scale factor for LoRA-trained features.
  • outputImageCount: Number of images to generate (1-4).
  • applyWatermark: Option to add a watermark to the generated images.

Expected Output

The output will be a URL to the generated image, which can be accessed and utilized as needed. The generated images will align with the specifications set in the input.

Use Cases for This Specific Action

  • Content Creation: Quickly generate unique images for articles, social media posts, or marketing materials based on specific themes or ideas.
  • Product Visualization: Create product mockups or concept images from descriptions to visualize designs before development.
  • Art and Design: Explore new artistic styles or concepts by generating images that can be refined further based on feedback or additional prompts.
  • Game Development: Produce concept art or assets for games based on narrative descriptions to aid in visual storytelling.
import requests
import json

# Replace with your actual Cognitive Actions API key and endpoint
# Ensure your environment securely handles the API key
COGNITIVE_ACTIONS_API_KEY = "YOUR_COGNITIVE_ACTIONS_API_KEY"
# This endpoint URL is hypothetical and should be documented for users
COGNITIVE_ACTIONS_EXECUTE_URL = "https://api.cognitiveactions.com/actions/execute"

action_id = "3b3a6c02-a9d7-4393-acc8-0df0d0aa7447" # Action ID for: Generate And Refine Images

# Construct the exact input payload based on the action's requirements
# This example uses the predefined example_input for this action:
payload = {
  "width": 1024,
  "height": 1024,
  "prompt": "soccer player in style of TOK",
  "loraScale": 0.6,
  "guidanceScale": 7.5,
  "highNoiseFrac": 0.8,
  "applyWatermark": true,
  "negativePrompt": "",
  "promptStrength": 0.8,
  "refinementStyle": "no_refiner",
  "outputImageCount": 1,
  "numInferenceSteps": 50,
  "executionScheduler": "K_EULER"
}

headers = {
    "Authorization": f"Bearer {COGNITIVE_ACTIONS_API_KEY}",
    "Content-Type": "application/json",
    # Add any other required headers for the Cognitive Actions API
}

# Prepare the request body for the hypothetical execution endpoint
request_body = {
    "action_id": action_id,
    "inputs": payload
}

print(f"--- Calling Cognitive Action: {action.name or action_id} ---")
print(f"Endpoint: {COGNITIVE_ACTIONS_EXECUTE_URL}")
print(f"Action ID: {action_id}")
print("Payload being sent:")
print(json.dumps(request_body, indent=2))
print("------------------------------------------------")

try:
    response = requests.post(
        COGNITIVE_ACTIONS_EXECUTE_URL,
        headers=headers,
        json=request_body
    )
    response.raise_for_status() # Raise an exception for bad status codes (4xx or 5xx)

    result = response.json()
    print("Action executed successfully. Result:")
    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 (non-JSON): {e.response.text}")
    print("------------------------------------------------")

Conclusion

Fcm2's image generation capabilities empower developers to create stunning visuals quickly and efficiently, enhancing the overall quality of digital content. By leveraging the flexibility of the "Generate And Refine Images" action, you can cater to a variety of use cases, from content creation to product visualization. The next step is to explore how you can integrate this action into your projects and unleash your creativity with AI-generated imagery.

← Back to All Articles