Create Stunning Animated Videos with ToonCrafter Cognitive Actions

24 Apr 2025
Create Stunning Animated Videos with ToonCrafter Cognitive Actions

In today's digital landscape, the ability to generate engaging multimedia content is paramount for developers looking to enhance their applications. The ToonCrafter Cognitive Actions provide a powerful API for transforming illustrated images into captivating animated videos. Utilizing pre-trained image-to-video diffusion models, these actions support functionalities such as interpolation and color correction, ensuring smooth and visually consistent outputs. In this article, we will dive into the specific actions available in the ToonCrafter API and how to integrate them into your applications.

Prerequisites

Before you start using the ToonCrafter Cognitive Actions, ensure you have the following:

  • An API key for the Cognitive Actions platform to authenticate your requests.
  • Basic familiarity with making HTTP requests and handling JSON payloads.

Authentication typically involves passing your API key in the request headers, allowing secure access to the Cognitive Actions features.

Cognitive Actions Overview

Generate Animated Video from Images

The Generate Animated Video from Images action allows you to create a coherent animated video by providing a series of illustrated input images. This action utilizes ToonCrafter's advanced image-to-video diffusion priors, enabling features such as interpolation and color correction for optimal visual output.

Input

The input for this action requires two mandatory images and several optional parameters. Here’s the schema for the input:

{
  "firstImage": "https://example.com/image1.webp",  // required
  "secondImage": "https://example.com/image2.webp", // required
  "loop": false,               // optional, defaults to false
  "seed": 12345,              // optional, a seed for reproducibility
  "prompt": "",                // optional, guides visual style
  "colorCorrection": true,     // optional, defaults to true
  "maximumWidth": 512,        // optional, defaults to 512 (256-768)
  "maximumHeight": 512,       // optional, defaults to 512 (256-768)
  "interpolate": false,       // optional, defaults to false
  // additional optional images...
}

Example Input:

{
  "loop": false,
  "prompt": "",
  "firstImage": "https://replicate.delivery/pbxt/L1pQdyf4fPVRzU5WxhhHAdH2Eo05X3zhirvNzwAKJ80lA7Qh/replicate-prediction-5cvynz9d91rgg0cfsvqschdpww-0.webp",
  "secondImage": "https://replicate.delivery/pbxt/L1pQeBF582rKH3FFAYJCxdFUurBZ1axNFVwKxEd1wIALydhh/replicate-prediction-5cvynz9d91rgg0cfsvqschdpww-1.webp",
  "maximumWidth": 512,
  "maximumHeight": 512,
  "colorCorrection": true,
  "interpolate": false
}

Output

Upon successful execution, this action returns a URL pointing to the generated animated video. For instance:

[
  "https://assets.cognitiveactions.com/invocations/8a3c3254-adb3-4e2a-b7e1-26f457ea38bb/b71db700-2dd5-410f-a653-35e4b71141cf.mp4"
]

Conceptual Usage Example (Python)

Here’s a conceptual Python snippet demonstrating how to invoke the Generate Animated Video from Images 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 = "4a46a824-fac7-4e6d-8c1a-a559b4263539" # Action ID for Generate Animated Video from Images

# Construct the input payload based on the action's requirements
payload = {
    "loop": false,
    "firstImage": "https://replicate.delivery/pbxt/L1pQdyf4fPVRzU5WxhhHAdH2Eo05X3zhirvNzwAKJ80lA7Qh/replicate-prediction-5cvynz9d91rgg0cfsvqschdpww-0.webp",
    "secondImage": "https://replicate.delivery/pbxt/L1pQeBF582rKH3FFAYJCxdFUurBZ1axNFVwKxEd1wIALydhh/replicate-prediction-5cvynz9d91rgg0cfsvqschdpww-1.webp",
    "maximumWidth": 512,
    "maximumHeight": 512,
    "colorCorrection": true,
    "interpolate": false
}

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}")

This code snippet shows how to set up the request to the Cognitive Actions API, including how to structure the input payload correctly. Remember, the endpoint URL and request structure are illustrative.

Conclusion

With the ToonCrafter Cognitive Actions, developers can seamlessly integrate animated video generation into their applications, enhancing user engagement and content richness. By leveraging the capabilities of the API, such as color correction and interpolation, you can create visually stunning animations that captivate your audience. Explore further use cases, experiment with different input parameters, and unleash your creativity with animated video content!

← Back to All Articles