Transforming Text Into Video: A Guide to the Hunyuan LoRA Cognitive Action

23 Apr 2025
Transforming Text Into Video: A Guide to the Hunyuan LoRA Cognitive Action

In the rapidly evolving landscape of multimedia content creation, the ability to generate videos from text descriptions is a game changer. The Hunyuan Video LoRA API offers a powerful Cognitive Action that allows developers to transform textual prompts into visually engaging videos. By leveraging the capabilities of the HunyuanVideo model with LoRA support, you can customize video styles without altering the main model. This article will guide you through integrating this innovative action into your applications.

Prerequisites

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

  • API Key: You will need a valid API key for the Cognitive Actions platform to authenticate your requests.
  • Setup: Familiarize yourself with the basic setup for making HTTP requests in your chosen programming language.

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

Cognitive Actions Overview

Generate Text-To-Video with Hunyuan LoRA

The Generate Text-To-Video with Hunyuan LoRA action allows you to create videos based on textual descriptions. This action is categorized under video-generation and is designed to enable customization using LoRA (Low-Rank Adaptation) files, which fine-tune the video generation process without modifying the core model.

Input

The input for this action requires a structured JSON object with specific properties:

  • loraUrl (string, required): URL pointing to the LoRA .safetensors file for model fine-tuning.
  • prompt (string, required): Text description of the scene to be generated.
  • width (integer, optional): Width of the video in pixels (default: 640, range: 64-1536).
  • height (integer, optional): Height of the video in pixels (default: 360, range: 64-1024).
  • steps (integer, optional): Number of diffusion steps (default: 50, range: 1-150).
  • frameRate (integer, optional): Video frame rate (default: 24 fps, range: 1-60).
  • loraStrength (number, optional): Strength of the LoRA model (default: 1).
  • videoQuality (integer, optional): Video quality (default: 19, range: 0-51).
  • guidanceScale (number, optional): Influence of the text prompt (default: 6).
  • flowContinuity (integer, optional): Continuity of video content (default: 9, range: 0-20).
  • numberOfFrames (integer, optional): Total number of frames (default: 85, range: 1-300).
  • denoiseStrength (number, optional): Level of noise during each step (default: 1).
  • forceModelOffload (boolean, optional): Force model layers to CPU (default: true).

Example Input:

{
  "steps": 30,
  "width": 512,
  "height": 512,
  "prompt": "In the style of RSNG. A woman with blonde hair stands on a balcony at night, framed against a backdrop of city lights. She wears a white crop top and a dark jacket, exuding a confident presence as she gazes directly at the camera",
  "loraUrl": "lucataco/hunyuan-musubi-rose-6",
  "frameRate": 15,
  "loraStrength": 1,
  "videoQuality": 19,
  "guidanceScale": 6,
  "flowContinuity": 9,
  "numberOfFrames": 33,
  "denoiseStrength": 1,
  "forceModelOffload": true
}

Output

Upon successfully executing the action, the response will typically include a URL to the generated video.

Example Output:

https://assets.cognitiveactions.com/invocations/8e2b3bfa-a004-4ced-a03a-ddb2923d38b3/a9da8762-5d2b-4d2c-83f6-8a35c195ad83.mp4

Conceptual Usage Example (Python)

Below is a conceptual Python snippet demonstrating how you might call this action using the Cognitive Actions API:

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 = "360d1497-2ce4-4bbf-bf61-f4bf11529405"  # Action ID for Generate Text-To-Video with Hunyuan LoRA

# Construct the input payload based on the action's requirements
payload = {
    "steps": 30,
    "width": 512,
    "height": 512,
    "prompt": "In the style of RSNG. A woman with blonde hair stands on a balcony at night, framed against a backdrop of city lights. She wears a white crop top and a dark jacket, exuding a confident presence as she gazes directly at the camera",
    "loraUrl": "lucataco/hunyuan-musubi-rose-6",
    "frameRate": 15,
    "loraStrength": 1,
    "videoQuality": 19,
    "guidanceScale": 6,
    "flowContinuity": 9,
    "numberOfFrames": 33,
    "denoiseStrength": 1,
    "forceModelOffload": True
}

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 the placeholders with your actual API key. The action ID corresponds to the Generate Text-To-Video with Hunyuan LoRA action. The payload is structured according to the required input schema, and the request is sent to the hypothetical execution endpoint.

Conclusion

The Hunyuan Video LoRA Cognitive Action is an impressive tool for developers looking to integrate text-to-video generation into their applications. With customizable parameters and the ability to utilize fine-tuning through LoRA files, this action offers extensive possibilities for creative video production. To explore further, consider experimenting with different prompts and video settings to see what unique content you can create!

← Back to All Articles