image-generation

Create Stunning Visuals with Cody's Enhanced Image Generation

25 Apr 2025
Create Stunning Visuals with Cody's Enhanced Image Generation

In today's digital landscape, the ability to create high-quality images quickly and efficiently is a game-changer for developers and designers alike. Cody's Enhanced Image Generation action empowers you to leverage advanced AI models to generate custom images tailored to your specific needs. Whether you're working on a game, an advertisement, or any visual content, Cody simplifies the process of image creation, allowing for rapid prototyping and iteration.

With features like customizable prompts, image inpainting, and flexible output settings, developers can produce stunning visuals that meet unique project requirements. This capability not only saves time but also enhances creativity by allowing developers to explore various artistic directions without the constraints of traditional design tools.

Prerequisites

To get started with Cody’s Enhanced Image Generation, you'll need a Cognitive Actions API key and a basic understanding of how to make API calls.

Generate Enhanced Images

The Generate Enhanced Images action allows you to create high-quality images using either the 'dev' or 'schnell' model. This action is particularly useful for generating detailed images based on textual descriptions, providing a balance between speed and quality.

Purpose

This action solves the problem of image creation by enabling developers to generate custom visuals from detailed prompts. It supports various configurations, including image inpainting and fast generation modes, catering to both quality-focused and speed-oriented projects.

Input Requirements

The input for this action requires a structured JSON object, which must include:

  • prompt: A detailed textual description of the desired image.
  • mask: (optional) A URI for an image mask used in image inpainting.
  • seed: (optional) An integer to ensure reproducibility.
  • width: (optional) The desired width of the output image.
  • height: (optional) The desired height of the output image.
  • Additional parameters include output count, model weights, quality settings, and various scaling options.

Example Input:

{
  "prompt": "A rugged, battle-worn man stands on the arid sands of Tatooine...",
  "loraScale": 1,
  "outputCount": 1,
  "guidanceScale": 3,
  "numMegapixels": "1",
  "outputQuality": 80,
  "fastGeneration": false,
  "inferenceModel": "dev",
  "promptStrength": 0.8,
  "imageAspectRatio": "21:9",
  "imageOutputFormat": "jpg",
  "numInferenceSteps": 28,
  "additionalLoraScale": 1
}

Expected Output

The output will be a URI pointing to the generated image, which can be used directly in your applications or displayed on websites.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/55728d2b-74e8-4a09-b0a6-abae100a800f/84dbf59a-3cf2-4f81-87eb-507ee33b207b.jpg"
]

Use Cases for this Specific Action

  • Game Development: Create unique character designs or landscapes based on narrative prompts.
  • Marketing and Advertising: Generate eye-catching visuals for campaigns or social media posts that resonate with target audiences.
  • Content Creation: Quickly produce images for blogs, articles, or digital media that align with specific themes or topics.
  • Artistic Exploration: Experiment with various styles and concepts without the need for extensive graphic design skills.

```python
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 = "18c1df25-c41c-41cd-b127-5820b4124382" # Action ID for: Generate Enhanced Images

# Construct the exact input payload based on the action's requirements
# This example uses the predefined example_input for this action:
payload = {
  "prompt": "A rugged, battle-worn man stands on the arid sands of Tatooine, his sharp eyes scanning the endless desert horizon. He wears a tattered, sand-colored poncho draped over his broad shoulders, the fabric worn from years of travel beneath the twin suns. Beneath the poncho, he dons a simple yet practical outfit—dust-streaked trousers and a weathered tunic, built for endurance in the unforgiving heat. His short-cropped brown hair is tousled by the dry wind, and his face, marked by years of war and hardship, holds a quiet intensity. The distant silhouettes of moisture farms and jagged rock formations dot the landscape behind him, as he stands firm, gripping a blaster at his side, ever watchful in the vast and merciless expanse of the Outer Rim.",
  "loraScale": 1,
  "outputCount": 1,
  "guidanceScale": 3,
  "numMegapixels": "1",
  "outputQuality": 80,
  "fastGeneration": false,
  "inferenceModel": "dev",
  "promptStrength": 0.8,
  "imageAspectRatio": "21:9",
  "imageOutputFormat": "jpg",
  "numInferenceSteps": 28,
  "additionalLoraScale": 1
}

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
Cody's Enhanced Image Generation action provides developers with powerful tools to create high-quality, customized images efficiently. With its flexibility and advanced features, you can cater to various project needs, whether focusing on speed or detail. As you integrate this action into your workflow, you'll find that it not only saves time but also opens up new creative possibilities. 

To get started, explore the API documentation, experiment with different prompts, and see how Cody can transform your image generation process!
← Back to All Articles