Unleashing Creativity: Integrate Image Inpainting with kikonessssss/oso_ricitos Cognitive Actions

24 Apr 2025
Unleashing Creativity: Integrate Image Inpainting with kikonessssss/oso_ricitos Cognitive Actions

In the world of image generation, the ability to create stunning visuals based on textual descriptions is revolutionizing how developers approach design and creativity. The kikonessssss/oso_ricitos Cognitive Actions provide powerful tools for generating inpainted images, allowing developers to transform prompts into vivid imagery. This blog post will guide you through the capability of the "Generate Inpainted Image" action, its requirements, and how to seamlessly integrate it into your applications.

Prerequisites

Before diving into the Cognitive Actions, ensure you have the following:

  • An API key for the Cognitive Actions platform to authenticate your requests.
  • Basic understanding of JSON structure, as the input and output will be formatted in JSON.
  • Familiarity with making HTTP requests, especially using Python for practical examples.

For authentication, you will typically pass your API key in the headers of your requests.

Cognitive Actions Overview

Generate Inpainted Image

Description: This action generates inpainted images based on a specified prompt and image mask. It offers two model options, 'dev' and 'schnell', allowing for varied performance, including an enhanced speed mode for quicker results.

Category: Image Generation

Input

The input for this action requires a JSON object with specific fields. Here’s a breakdown:

  • prompt (required): A textual description for the image you want to generate.
  • mask (optional): URI of the image mask for inpainting.
  • image (optional): URI of the input image for image-to-image transformation.
  • width (optional): Width of the generated image.
  • height (optional): Height of the generated image.
  • goFast (optional): Boolean to enable faster model predictions.
  • seed (optional): Random seed for reproducible results.
  • numOutputs (optional): Number of output images to generate (1 to 4).
  • outputQuality (optional): Quality of the generated image (0 to 100).
  • selectedModel (optional): Choose between 'dev' and 'schnell' models.
  • aspectRatioSetting (optional): Aspect ratio for the output image.
  • imageOutputFormat (optional): Format of the output image (webp, jpg, png).
  • promptStrength (optional): Determines how much of the original image information is maintained in case of inpainting.

Example Input:

{
  "goFast": false,
  "prompt": "A hyper-realistic cinematic scene of a teddy bear oso_ricitos floating in space saying goodbye, surrounded by countless iridescent soap bubbles of various sizes. Some bubbles reflect distant stars, while others gently drift and pop, releasing tiny sparkling droplets. A soft trail of foam extends behind, dispersing in zero gravity. The International Space Station (ISS) looms in the background, partially illuminated by the glow of Earth below. Shooting stars and glowing particles move subtly, adding depth and motion to the surreal atmosphere.",
  "loraScale": 1,
  "numOutputs": 1,
  "outputQuality": 100,
  "selectedModel": "dev",
  "extraLoraScale": 1,
  "promptStrength": 0.8,
  "imageMegapixels": "1",
  "guidanceIntensity": 3,
  "imageOutputFormat": "jpg",
  "numInferenceSteps": 28,
  "aspectRatioSetting": "16:9"
}

Output

The action typically returns a list of generated image URLs based on the provided prompt.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/dafe4861-a82d-4002-9a38-a23758e11588/25ce1de8-ca91-44d9-9909-2a89058df7a8.jpg"
]

Conceptual Usage Example (Python)

Here’s a conceptual Python snippet that demonstrates how to call the "Generate Inpainted Image" action:

import requests
import json

# Replace with your Cognitive Actions API key and endpoint
COGNITIVE_ACTIONS_API_KEY = "YOUR_COGNITIVE_ACTIONS_API_KEY"
COGNITIVE_ACTIONS_EXECUTE_URL = "https://api.cognitiveactions.com/actions/execute"  # Hypothetical endpoint

action_id = "80ce9cc1-2e61-4801-87eb-45af131aedff"  # Action ID for Generate Inpainted Image

# Construct the input payload based on the action's requirements
payload = {
    "goFast": False,
    "prompt": "A hyper-realistic cinematic scene of a teddy bear oso_ricitos floating in space saying goodbye, surrounded by countless iridescent soap bubbles of various sizes. Some bubbles reflect distant stars, while others gently drift and pop, releasing tiny sparkling droplets. A soft trail of foam extends behind, dispersing in zero gravity. The International Space Station (ISS) looms in the background, partially illuminated by the glow of Earth below. Shooting stars and glowing particles move subtly, adding depth and motion to the surreal atmosphere.",
    "loraScale": 1,
    "numOutputs": 1,
    "outputQuality": 100,
    "selectedModel": "dev",
    "promptStrength": 0.8,
    "imageOutputFormat": "jpg",
    "numInferenceSteps": 28,
    "aspectRatioSetting": "16:9"
}

headers = {
    "Authorization": f"Bearer {COGNITIVE_ACTIONS_API_KEY}",
    "Content-Type": "application/json"
}

try:
    response = requests.post(
        COGNITIVE_ACTIONS_EXECUTE_URL,
        headers=headers,
        json={"action_id": action_id, "inputs": payload}  # Hypothetical structure
    )
    response.raise_for_status()  # Raise an exception for bad status codes (4xx or 5xx)

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

In this code snippet, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key and ensure the endpoint URL is correct. The payload structure should align with the inputs outlined above.

Conclusion

The kikonessssss/oso_ricitos Cognitive Actions offer a powerful way to generate stunning images based on creative prompts. By integrating the "Generate Inpainted Image" action into your applications, you can provide users with the ability to visualize concepts beautifully and quickly. Consider exploring various prompts and configurations to fully leverage the capabilities of this action. Happy coding!

← Back to All Articles