video-generation

Create Stunning Videos from Text with Hunyuan Video

25 Apr 2025
Create Stunning Videos from Text with Hunyuan Video

In the ever-evolving landscape of content creation, video has emerged as a powerful medium for storytelling and engagement. The Hunyuan Video service offers developers a groundbreaking way to generate high-quality videos directly from text descriptions. By leveraging advanced AI capabilities, this service allows for the creation of videos with realistic motion, making it easier than ever to turn creative ideas into visual content.

Imagine the possibilities: a simple text prompt can transform into a dynamic video, enabling creators, marketers, and educators to produce engaging content rapidly and efficiently. Whether you are looking to enhance presentations, create promotional materials, or generate unique visual stories, Hunyuan Video simplifies the video creation process while maintaining high-quality output.

Prerequisites

To get started with Hunyuan Video, you'll need a Cognitive Actions API key and a basic understanding of how to make API calls. This will allow you to integrate the video generation capabilities into your applications seamlessly.

Generate Text-to-Video with Hunyuan Video

The primary action available in Hunyuan Video is the ability to generate videos from text descriptions.

This action serves to bridge the gap between text and visual content, allowing developers to create videos that reflect the nuances of their written prompts. With Hunyuan Video, you can produce compelling video content without the need for extensive video editing skills.

Input Requirements

To use this action, you will need to provide the following input parameters:

  • Prompt: A descriptive text that guides the video generation (e.g., "A cat walks on the grass, realistic style").
  • Width: The width of the video in pixels (default is 864).
  • Height: The height of the video in pixels (default is 480).
  • Guidance Scale: A value from 1 to 10 that directs the generation process (default is 6).
  • Inference Steps: The total number of denoising steps during video creation (default is 50).
  • Frames Per Second: The frame rate of the output video (default is 24).
  • Total Frame Count: The total number of frames in the video, which must be in the form of 4k+1 (default is 129).
  • Seed: An optional random seed for video generation.

Expected Output

Upon successful processing, the action will return a video file, which can be accessed via a URL, allowing you to view or embed the created video easily.

For example, a successful output might look like this:

https://assets.cognitiveactions.com/invocations/81790680-35b2-40cd-bfd7-065dd2cc5fe7/7aad748f-312c-46c9-ae9a-bdc16073596f.mp4

Use Cases for this Action

  1. Content Creation: Quickly generate promotional videos or social media content from marketing copy or blog posts, enhancing engagement and reach.
  2. Education: Create educational videos that illustrate concepts or stories based on written materials, making learning more interactive and visually appealing.
  3. Entertainment: Develop unique animated stories or short films from original scripts or narratives, opening up new avenues for creative expression.
  4. Product Demonstrations: Generate video demonstrations of products based on descriptions, offering potential customers a clearer understanding of features and benefits.
import requests
import json

# Replace with your actual Cognitive Actions API key and endpoint
# Ensure your environment securely handles the API key
COGNITIVE_ACTIONS_API_KEY = "YOUR_COGNITIVE_ACTIONS_API_KEY"
# This endpoint URL is hypothetical and should be documented for users
COGNITIVE_ACTIONS_EXECUTE_URL = "https://api.cognitiveactions.com/actions/execute"

action_id = "5c918ed4-0524-4d48-95c1-9e31fd9c270c" # Action ID for: Generate Text-to-Video with HunyuanVideo

# Construct the exact input payload based on the action's requirements
# This example uses the predefined example_input for this action:
payload = {
  "width": 864,
  "height": 480,
  "prompt": "A cat walks on the grass, realistic style",
  "guidanceScale": 6,
  "inferenceSteps": 50,
  "framesPerSecond": 24,
  "videoFrameCount": 129
}

headers = {
    "Authorization": f"Bearer {COGNITIVE_ACTIONS_API_KEY}",
    "Content-Type": "application/json",
    # Add any other required headers for the Cognitive Actions API
}

# Prepare the request body for the hypothetical execution endpoint
request_body = {
    "action_id": action_id,
    "inputs": payload
}

print(f"--- Calling Cognitive Action: {action.name or action_id} ---")
print(f"Endpoint: {COGNITIVE_ACTIONS_EXECUTE_URL}")
print(f"Action ID: {action_id}")
print("Payload being sent:")
print(json.dumps(request_body, indent=2))
print("------------------------------------------------")

try:
    response = requests.post(
        COGNITIVE_ACTIONS_EXECUTE_URL,
        headers=headers,
        json=request_body
    )
    response.raise_for_status() # Raise an exception for bad status codes (4xx or 5xx)

    result = response.json()
    print("Action executed successfully. Result:")
    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 (non-JSON): {e.response.text}")
    print("------------------------------------------------")

Conclusion

Hunyuan Video empowers developers to harness the power of AI-driven video generation, transforming simple text prompts into stunning, high-quality videos. This innovative approach not only saves time but also enhances creativity in content creation. As you explore the capabilities of Hunyuan Video, consider how it can fit into your projects, whether for marketing, education, or entertainment. Start integrating this technology today and revolutionize the way you create and share video content.

← Back to All Articles