image-generation

Create Stunning Images with Inpainting Using Kevine

25 Apr 2025
Create Stunning Images with Inpainting Using Kevine

In the world of digital content creation, the ability to generate high-quality images is essential. Enter Kevine, a powerful service that offers advanced cognitive actions for image generation, particularly focusing on inpainting capabilities. With Kevine, developers can easily create customized images that align with specific requirements, streamlining the creative process and enhancing productivity.

Imagine needing to fill in gaps in an image or creatively alter elements without starting from scratch; Kevine's inpainting action allows you to do just that. This action not only provides flexibility in terms of the images you can create but also enhances the overall quality and fidelity of the output. Whether you're working on a marketing campaign, an art project, or simply experimenting with visuals, Kevine's image generation capabilities can significantly speed up your workflow.

Prerequisites

To get started with Kevine's cognitive actions, you'll need an API key from the Cognitive Actions platform and a basic understanding of how to make API calls.

Generate Image with Inpainting

The "Generate Image with Inpainting" action provides developers with the tools to create images that can be tailored to their specific needs. By utilizing customizable parameters such as image mask, prompt strength, and aspect ratio, you can generate images that align precisely with your vision.

Purpose

This action solves the problem of needing to modify existing images or create new visuals from textual prompts. It offers two models: 'dev' for high fidelity and 'schnell' for speed, allowing users to choose based on their specific requirements.

Input Requirements

To use this action, you must provide a prompt, along with optional parameters such as:

  • mask: A URI of the image mask for inpainting mode.
  • image: A URI of the input image for modification.
  • width and height: Dimensions for the generated image when using a custom aspect ratio.
  • numOutputs: The number of images to generate, ranging from 1 to 4.

Expected Output

The output will be a set of generated images based on the provided prompt and parameters, which can include various formats like webp, jpg, or png.

Use Cases for this Specific Action

  1. Content Creation: Perfect for marketers and content creators who need to generate unique visuals for campaigns or social media.
  2. Artistic Projects: Artists can leverage the inpainting feature to create variations of their work or to fill in details that enhance the overall composition.
  3. Prototyping: Designers can quickly generate and iterate on visual concepts without needing to start from scratch each time.

```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 = "2eb33e0c-9e25-41f3-a80f-f1ec910faa94" # 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 = {
  "width": 1080,
  "height": 1350,
  "prompt": "a photo of Etchandy wearing a black sweater in an old record store, canon eos 7d, realistic photograph",
  "loraScale": 1,
  "numOutputs": 2,
  "aspectRatio": "1:1",
  "outputFormat": "png",
  "guidanceScale": 3.5,
  "outputQuality": 100,
  "extraLoraScale": 0.8,
  "inferenceModel": "dev",
  "numInferenceSteps": 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
In summary, Kevine's image generation with inpainting capabilities empowers developers to create high-quality, customized images swiftly and efficiently. The flexibility in parameters and the choice between fidelity and speed make it a versatile tool for various applications, from marketing to art. As you explore the potential of Kevine, consider how these cognitive actions can enhance your projects and streamline your creative processes. Start integrating Kevine into your workflow today and experience the difference!
← Back to All Articles