Create Stunning AI Avatars with the Hunyuan Heygen Joshua Cognitive Actions

21 Apr 2025
Create Stunning AI Avatars with the Hunyuan Heygen Joshua Cognitive Actions

Introduction

The Hunyuan Heygen Joshua Cognitive Actions provide powerful tools for creating high-quality AI-generated videos. Specifically designed for developers, these pre-built actions allow for seamless integration of advanced video generation capabilities into applications. By leveraging these actions, developers can customize video attributes such as dimensions, frame rates, and scene details, resulting in tailored and engaging content.

Prerequisites

To get started with the Hunyuan Heygen Joshua Cognitive Actions, you will need an API key for the Cognitive Actions platform, which will allow you to authenticate your requests. Generally, authentication is handled by including the API key in the request headers. Ensure you have a working development environment with access to the internet for making API calls.

Cognitive Actions Overview

Generate HunyuanVideo AI Avatar

The Generate HunyuanVideo AI Avatar action allows you to create a finely-tuned video of the Heygen AI avatar using the HunyuanVideo model. This action offers extensive customization options, ensuring high-quality video synthesis with tailored scene details and continuity.

Input

The input for this action is structured as follows:

  • seed (integer): An optional seed for reproducibility. If not specified, a random seed is used.
  • steps (integer, default: 50): Number of diffusion steps (1 to 150).
  • width (integer, default: 640): Width of the generated video in pixels (64 to 1536).
  • height (integer, default: 360): Height of the generated video in pixels (64 to 1024).
  • prompt (string, default: “A modern lounge in lush greenery.”): Description of the desired video scene.
  • frameRate (integer, default: 24): Frames displayed per second (1 to 60).
  • frameCount (integer, default: 85): Total number of frames in the resulting video (1 to 300).
  • loraIntensity (number, default: 1): Scale of LoRA influence.
  • qualityFactor (integer, default: 19): CRF value for video encoding (0 to 51).
  • enforceOffload (boolean, default: true): Offload model layers to CPU.
  • weightsFileUri (string): Optional URI to a tar file containing LoRA weights.
  • loraResourceUrl (string): URL to a .safetensors file or Hugging Face repository.
  • noiseControlLevel (number, default: 1): Level of noise applied during diffusion steps.
  • textModelInfluence (number, default: 6): Influence of the textual prompt.
  • videoContinuityFactor (integer, default: 9): Adjusts video flow continuity.

Example Input:

{
  "steps": 30,
  "width": 960,
  "height": 544,
  "prompt": "HGM1 man standing indoors, likely in a modern, well-lit space. He is wearing a white, long-sleeved shirt. The background includes large windows or glass doors, through which greenery and possibly other buildings can be seen, suggesting an urban or semi-urban setting. The lighting is natural, with sunlight streaming in, creating a bright and airy atmosphere. The man appears to be walking while speaking, as he is looking directly at the camera.",
  "frameRate": 15,
  "frameCount": 33,
  "loraIntensity": 0.9,
  "qualityFactor": 19,
  "enforceOffload": true,
  "loraResourceUrl": "",
  "noiseControlLevel": 1,
  "textModelInfluence": 6,
  "videoContinuityFactor": 9
}

Output

The action typically returns a URL pointing to the generated video file.

Example Output:

https://assets.cognitiveactions.com/invocations/fc812341-fbdb-44b5-b517-ee588cc37775/001b91a5-8a47-425f-8846-fad95df20883.mp4

Conceptual Usage Example (Python)

Here’s how you might call the Generate HunyuanVideo AI Avatar 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 = "96d88bb8-d6bf-4c4a-8ac2-f19041737389" # Action ID for Generate HunyuanVideo AI Avatar

# Construct the input payload based on the action's requirements
payload = {
    "steps": 30,
    "width": 960,
    "height": 544,
    "prompt": "HGM1 man standing indoors, likely in a modern, well-lit space. He is wearing a white, long-sleeved shirt. The background includes large windows or glass doors, through which greenery and possibly other buildings can be seen, suggesting an urban or semi-urban setting. The lighting is natural, with sunlight streaming in, creating a bright and airy atmosphere. The man appears to be walking while speaking, as he is looking directly at the camera.",
    "frameRate": 15,
    "frameCount": 33,
    "loraIntensity": 0.9,
    "qualityFactor": 19,
    "enforceOffload": true,
    "loraResourceUrl": "",
    "noiseControlLevel": 1,
    "textModelInfluence": 6,
    "videoContinuityFactor": 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 the above snippet, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The action_id corresponds to the Generate HunyuanVideo AI Avatar action, and the payload is structured based on the required input fields.

Conclusion

The Hunyuan Heygen Joshua Cognitive Actions empower developers to create dynamic and engaging AI-generated videos effortlessly. By utilizing the capabilities of the Generate HunyuanVideo AI Avatar action, you can customize various video attributes to suit your specific needs. As you explore these actions, consider how they can enhance your applications and provide richer user experiences. Happy coding!

← Back to All Articles