Transform Your Imagery: Integrating Custom Inpainting with timo-xi/photo-kiko

22 Apr 2025
Transform Your Imagery: Integrating Custom Inpainting with timo-xi/photo-kiko

In the realm of image generation, the timo-xi/photo-kiko spec offers powerful Cognitive Actions that enable developers to create and manipulate images with remarkable precision. Among these capabilities, the Generate Image with Custom Inpainting action stands out, providing advanced features for generating visually stunning images tailored to specific prompts. This action not only enhances creativity but also streamlines the process of producing high-quality images for various applications.

Prerequisites

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

  • An API key for accessing the Cognitive Actions platform.
  • Familiarity with making HTTP requests and handling JSON payloads in your programming language of choice.

Authentication typically involves passing your API key in the request headers, allowing you to securely access the actions.

Cognitive Actions Overview

Generate Image with Custom Inpainting

The Generate Image with Custom Inpainting action uses an advanced model to generate images based on user-defined prompts. This action supports customizable parameters such as aspect ratio, image quality, and speed enhancements, making it versatile for various use cases in image generation.

Input

The input schema for this action requires a JSON object with the following fields:

  • prompt (required): A detailed text description of the image to be generated.
  • mask (optional): URI of the image mask for inpainting mode.
  • seed (optional): Random seed for consistent output across runs.
  • image (optional): URI of the input image for image-to-image or inpainting mode.
  • width (optional): Width of the generated image (256-1440 pixels).
  • height (optional): Height of the generated image (256-1440 pixels).
  • fastMode (optional): Boolean to enable faster predictions.
  • imageFormat (optional): Format of the output images (webp, jpg, png).
  • outputCount (optional): Number of outputs to generate (1-4).
  • imageQuality (optional): Quality level for saving output images (0-100).
  • weightsScale (optional): Determines the strength of the main LoRA application.
  • diffusionScale (optional): Guidance scale for the diffusion process.
  • inferenceModel (optional): Selects the model for running inference.
  • inferenceSteps (optional): Number of denoising steps (1-50).
  • approxMegapixels (optional): Approximate number of megapixels for the generated image.
  • imageAspectRatio (optional): Aspect ratio for the generated image.
  • inputPromptStrength (optional): Strength of the prompt when using image-to-image.
  • additionalWeightsScale (optional): Strength of the extra LoRA application.

Here’s an example input payload:

{
  "prompt": "Photo of a woman named Kiko, with facial features including [describe specific traits like face shape, eye shape, nose, lips, skin tone, hairstyle, etc.] and body proportions that closely resemble the reference photo. A professional portrait in the style of Forbes magazine, with a gentle, emotional demeanor, exuding confidence. The background is set on an Olympic track and field stadium during a 100-meter race, capturing the dynamic energy of the competition. She is dressed in an elegant, custom-tailored British suit, creating a striking contrast with the athletic environment, showcasing her inner strength, professional poise, and unique presence.",
  "fastMode": false,
  "imageFormat": "webp",
  "outputCount": 1,
  "imageQuality": 80,
  "weightsScale": 1,
  "diffusionScale": 3,
  "inferenceModel": "dev",
  "inferenceSteps": 50,
  "approxMegapixels": "1",
  "imageAspectRatio": "1:1",
  "inputPromptStrength": 0.8,
  "additionalWeightsScale": 1
}

Output

The action typically returns a list of generated image URLs based on the input parameters. Here’s an example of the expected output:

[
  "https://assets.cognitiveactions.com/invocations/117e3fb8-6dee-4fa9-8ea1-fb202bf57d3c/9d61a1a2-91ea-4001-8b89-f81085cb2b66.webp"
]

Conceptual Usage Example (Python)

To invoke the Generate Image with Custom Inpainting action, you can use the following Python code snippet:

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 = "c5ca2283-a09d-4dbc-b2b7-e33b4321f433"  # Action ID for Generate Image with Custom Inpainting

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "Photo of a woman named Kiko, with facial features including [describe specific traits like face shape, eye shape, nose, lips, skin tone, hairstyle, etc.] and body proportions that closely resemble the reference photo. A professional portrait in the style of Forbes magazine, with a gentle, emotional demeanor, exuding confidence. The background is set on an Olympic track and field stadium during a 100-meter race, capturing the dynamic energy of the competition. She is dressed in an elegant, custom-tailored British suit, creating a striking contrast with the athletic environment, showcasing her inner strength, professional poise, and unique presence.",
    "fastMode": False,
    "imageFormat": "webp",
    "outputCount": 1,
    "imageQuality": 80,
    "weightsScale": 1,
    "diffusionScale": 3,
    "inferenceModel": "dev",
    "inferenceSteps": 50,
    "approxMegapixels": "1",
    "imageAspectRatio": "1:1",
    "inputPromptStrength": 0.8,
    "additionalWeightsScale": 1
}

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 snippet, replace the placeholder for the API key and endpoint URL with your actual credentials. The payload variable contains the input JSON for the action, including the prompt and various options for image generation.

Conclusion

The timo-xi/photo-kiko Cognitive Action for generating images with custom inpainting opens up exciting possibilities for developers looking to enhance their applications with compelling visual content. By leveraging the advanced features offered by this action, you can create stunning images tailored to specific needs. Consider experimenting with different parameters to discover how they affect the output, and start integrating this powerful tool into your projects today!

← Back to All Articles