image-generation

Create Stunning Images with Inpainting using Steph's Cognitive Actions

25 Apr 2025
Create Stunning Images with Inpainting using Steph's Cognitive Actions

In the world of digital content creation, the ability to generate and manipulate images efficiently can significantly enhance your projects. Steph offers an innovative Cognitive Action called "Generate Image with Inpainting," which empowers developers to generate images with precise control over various attributes. With this functionality, you can create stunning visuals tailored to your specific needs, whether it's for marketing materials, social media posts, or artistic projects. This action simplifies the image generation process while maintaining high quality and flexibility, making it an essential tool for developers looking to enhance their applications.

Imagine the possibilities: creating unique artwork, adjusting existing images, or even generating visuals that align perfectly with your brand identity. The inpainting capabilities allow for targeted modifications, enabling developers to refine images by specifying masks and prompts. This opens up a realm of creative opportunities, whether you're looking to replace elements in an image or generate entirely new scenes based on textual descriptions.

Prerequisites

To get started with the "Generate Image with Inpainting" action, you'll need a Cognitive Actions API key and a basic understanding of API calls. This will allow you to integrate the functionality seamlessly into your applications.

Generate Image with Inpainting

The "Generate Image with Inpainting" action provides a powerful way to create images that meet your specific requirements through inpainting techniques. This capability allows for adjustments based on provided masks, making it easier to manipulate images without needing advanced graphic design skills.

Purpose

This action solves the problem of generating customized images quickly and efficiently. It provides flexibility in terms of image dimensions, styles, and qualities, making it suitable for various applications—from artistic renderings to practical marketing visuals.

Input Requirements

To utilize this action, you need to provide a structured input that includes:

  • prompt: A text description guiding the image generation (e.g., "steph is wearing all black and sitting at a cafe in Scotland sipping a cup of tea").
  • mask (optional): A URI pointing to an image mask for inpainting.
  • aspectRatio: The desired aspect ratio for the generated image (e.g., "4:5").
  • guidanceScale: A scale factor influencing the image generation process (default is 3).
  • numberOfOutputs: How many images you want to generate (default is 1).
  • Additional parameters like width, height, imageOutputFormat, and others to fine-tune the output.

Expected Output

The action will return a URI link to the generated image, ensuring that you have direct access to the visual content created based on your specifications. For example, a successful output might look like this:

  • https://assets.cognitiveactions.com/invocations/f61a4244-ea1f-4994-80c3-e31a7509ecaf/f72655cc-03ed-48b2-8b74-2d5320c67e2a.webp

Use Cases for this Specific Action

  • Content Creation: Quickly generate images for blog posts, articles, or social media content that align with specific themes or topics.
  • Marketing Materials: Create tailored visuals for advertising campaigns, ensuring that images resonate with your target audience.
  • Artistic Projects: Use inpainting to modify existing images or create entirely new scenes based on imaginative prompts.
  • Prototyping: Develop mock-ups for applications or websites that require unique visuals without relying on stock images.
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 = "30b369ef-94cb-43dc-85d1-296a64eaa4f0" # 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 = {
  "prompt": "steph is wearing all black and sitting at a cafe in Scotland sipping a cup of tea",
  "aspectRatio": "4:5",
  "guidanceScale": 3,
  "enableFastMode": false,
  "inferenceModel": "dev",
  "promptStrength": 0.8,
  "imageMegapixels": "1",
  "numberOfOutputs": 1,
  "imageOutputFormat": "webp",
  "imageOutputQuality": 80,
  "additionalLoraScale": 1,
  "loraApplicationScale": 1,
  "numberOfInferenceSteps": 28
}

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 "Generate Image with Inpainting" action from Steph is a game-changer for developers looking to enhance their applications with high-quality image generation capabilities. By enabling fine-tuned control over the image creation process, this action opens the door to a multitude of creative possibilities. Whether you're building marketing content, artistic projects, or simply experimenting with visuals, this tool offers the speed and flexibility necessary to bring your ideas to life.

Take the next step in your development journey by integrating this powerful Cognitive Action into your projects and experience the benefits of seamless image generation today!

← Back to All Articles