image-generation

Create Stunning Images with Red Vase Cognitive Actions

27 Apr 2025
Create Stunning Images with Red Vase Cognitive Actions

In the realm of digital creativity, the ability to generate customized images can unlock a world of possibilities for developers. The "Red Vase" Cognitive Actions provide an intuitive way to create unique visuals through image-to-image generation and inpainting techniques. By leveraging powerful models and customizable parameters, developers can enhance their applications with tailored images that resonate with their audience.

Whether you're building a design tool, enhancing a creative project, or automating content generation, these actions streamline the process and save time. Imagine being able to create a specific image based on a prompt or modify existing images with precision. The Red Vase Cognitive Actions make this a reality, allowing for rapid prototyping and creative experimentation.

Prerequisites

To get started with the Red Vase Cognitive Actions, you'll need an API key and a basic understanding of how to make API calls.

Generate Image with Inpainting

The Generate Image with Inpainting action allows you to produce customized images by providing detailed prompts and manipulating existing images. This action is particularly useful for developers looking to create unique visuals tailored to specific needs, such as marketing materials, artwork, or product designs.

Input Requirements

To use this action, you must provide a prompt that describes the desired image. You can also customize various parameters, including the model selection (either "dev" or "schnell"), output dimensions, aspect ratio, and more. If you're looking to modify an existing image, you can include a mask and an input image, which will override certain dimensions.

Example Input:

{
  "model": "dev",
  "prompt": "RDVSE33 red and grey vase with thin neck on a shelf",
  "megapixels": "1",
  "aspectRatio": "1:1",
  "loraIntensity": 1,
  "enableFastMode": false,
  "numberOfOutputs": 1,
  "promptIntensity": 0.8,
  "guidanceIntensity": 3,
  "imageOutputFormat": "webp",
  "imageOutputQuality": 80,
  "numberOfInferenceSteps": 28,
  "additionalLoraIntensity": 1
}

Expected Output

The output will be a generated image based on the provided prompt and parameters, returned in the specified format (e.g., webp, jpg, png). The images created can vary significantly based on the input parameters and the model used.

Example Output:

"https://assets.cognitiveactions.com/invocations/916e1561-f027-4f9e-957a-8f5493de697c/e812f85f-1be8-49d8-85bc-b1fbe7028038.webp"

Use Cases for this Action

  • Marketing and Advertising: Generate unique visuals for campaigns that stand out and capture attention.
  • Art and Design: Create custom artwork or modify existing pieces, allowing for artistic flexibility and innovation.
  • Content Creation: Automate the generation of images for blogs, social media, or websites, enhancing user engagement with rich visuals.
  • Prototyping: Quickly generate concept images for product designs or app interfaces to visualize ideas before final implementation.
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 = "0b130587-49eb-4b51-8a3d-042365fe9425" # Action ID for: Generate Image with Inpainting

# Construct the exact input payload based on the action's requirements
# This example uses the predefined example_input for this action:
payload = {
  "model": "dev",
  "prompt": "RDVSE33 red and grey vase with thin neck on a shelf",
  "megapixels": "1",
  "aspectRatio": "1:1",
  "loraIntensity": 1,
  "enableFastMode": false,
  "numberOfOutputs": 1,
  "promptIntensity": 0.8,
  "guidanceIntensity": 3,
  "imageOutputFormat": "webp",
  "imageOutputQuality": 80,
  "numberOfInferenceSteps": 28,
  "additionalLoraIntensity": 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

The Red Vase Cognitive Actions offer developers a powerful toolset for generating and customizing images. By harnessing the capabilities of image-to-image generation and inpainting, you can bring your creative visions to life effectively and efficiently. Whether you're enhancing an existing project or exploring new creative avenues, these actions provide the speed and flexibility needed to succeed.

As you integrate these actions into your applications, consider the numerous ways they can enhance user experience and engagement. Start exploring today and see how the Red Vase can transform your approach to digital imagery!

← Back to All Articles