Create Stunning Image Interpolations with the Ad Interpolation Cognitive Action

23 Apr 2025
Create Stunning Image Interpolations with the Ad Interpolation Cognitive Action

In today's digital landscape, the ability to manipulate and create images through artificial intelligence has become a game-changer for many developers. The Ad Interpolation Cognitive Action allows you to generate stunning interpolated images using various AI models. By providing a starting and ending image along with user-defined prompts, you can create realistic transitions that include style and motion-based effects. This guide will help you integrate this powerful action into your applications seamlessly.

Prerequisites

Before you start using the Ad Interpolation Cognitive Action, you will need to ensure you have the following:

  • API Key: Obtain an API key for the Cognitive Actions platform to authenticate your requests.
  • Basic Setup: Familiarity with making HTTP requests and handling JSON payloads in your preferred programming language.

To authenticate, you typically pass your API key in the headers of your requests.

Cognitive Actions Overview

Interpolate Images with AI

This action uses advanced AI models to interpolate between a starting and ending image, applying various effects based on user-defined prompts. It leverages models like Realistic Vision V5.0 and Counterfeit-V3.0 to enhance the quality of the output.

Input

The following fields are required to invoke this action:

  • startingImagePath: (string, URI) URL of the starting image.
  • endingImagePath: (string, URI) URL of the ending image.
  • positivePrompt: (string) Prompt describing desired elements in the output image.
  • negativePrompt: (string) Prompt describing elements to avoid in the output image.

Optional fields include:

  • seed: (integer) Random seed value for sampling (default: -1).
  • model: (string) Choose the model file (default: "Counterfeit-V3.0_fp32.safetensors").
  • motionModel: (string) Select the motion model (default: "mm_sd_v14.ckpt").
  • configuration: (number) Interpolation configuration value (default: 8).
  • samplingSteps: (integer) Number of sampling steps (default: 30).
  • imageDimensions: (string) Dimensions of the output image (default: "512x512").

Example Input:

{
  "seed": -1,
  "model": "epic_realism.safetensors",
  "motionModel": "mm_sd_v14.ckpt",
  "configuration": 8,
  "samplingSteps": 30,
  "negativePrompt": "bad image",
  "positivePrompt": "griffith from berserk",
  "endingImagePath": "https://replicate.delivery/pbxt/JahtwWIg1pSfCueWjRn8UQxuc6jS2gJB0Mkp801O2j1rSewh/22.jpg",
  "imageDimensions": "512x512",
  "startingImagePath": "https://replicate.delivery/pbxt/JahtwPCw6Yue2fWWSjjwyovgWnnJwQsOCWPJ0s1ggh1XtPsN/21.jpg"
}

Output

The action typically returns a URL pointing to the generated interpolated image or animation.

Example Output:

https://assets.cognitiveactions.com/invocations/ad76a39b-3a19-4366-8dc0-912bf69f2911/bffe29ae-e2f3-4e5f-aa1e-e10a849a2dc6.gif

Conceptual Usage Example (Python)

Here's how you might call this action using Python:

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 = "fb3827ba-8af4-45fc-b4ef-c721c3c9d5e6" # Action ID for Interpolate Images with AI

# Construct the input payload based on the action's requirements
payload = {
    "seed": -1,
    "model": "epic_realism.safetensors",
    "motionModel": "mm_sd_v14.ckpt",
    "configuration": 8,
    "samplingSteps": 30,
    "negativePrompt": "bad image",
    "positivePrompt": "griffith from berserk",
    "endingImagePath": "https://replicate.delivery/pbxt/JahtwWIg1pSfCueWjRn8UQxuc6jS2gJB0Mkp801O2j1rSewh/22.jpg",
    "imageDimensions": "512x512",
    "startingImagePath": "https://replicate.delivery/pbxt/JahtwPCw6Yue2fWWSjjwyovgWnnJwQsOCWPJ0s1ggh1XtPsN/21.jpg"
}

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, the action ID and input payload are structured according to the required format. The endpoint URL and request structure are illustrative, and you should adapt them to your specific implementation.

Conclusion

The Ad Interpolation Cognitive Action provides developers with the opportunity to create visually stunning interpolated images using AI. By leveraging detailed user prompts and advanced models, you can transform your applications with this powerful image-processing capability. Consider exploring various use cases for this action, such as animation, visual storytelling, or even game development, to truly harness its potential. Happy coding!

← Back to All Articles