Create Stunning Videos in Cowboy Bebop Style with Hunyuan Actions

24 Apr 2025
Create Stunning Videos in Cowboy Bebop Style with Hunyuan Actions

In the realm of content creation, infusing creativity and nostalgia can lead to captivating results. The deepfates/hunyuan-cowboy-bebop API offers a powerful Cognitive Action that enables developers to generate videos in the iconic style of the beloved anime series Cowboy Bebop (1998). This pre-built action simplifies the video generation process, allowing you to focus on your creative vision while leveraging advanced AI capabilities.

Prerequisites

Before diving into the implementation, ensure you have the following:

  • An API key for the Cognitive Actions platform, which will be used to authenticate your requests.
  • Familiarity with JSON payload structures, as the API interactions involve sending and receiving JSON data.

To authenticate your requests, you will need to pass the API key in the headers of your HTTP requests.

Cognitive Actions Overview

Generate Video in Cowboy Bebop Style

Description: This action creates a video in the distinctive style of Cowboy Bebop using the Hunyuan-Video model. For optimal results, it is recommended to start your prompt with "A video in the style of CWBYB, CWBYB".

Category: Video Generation

Input:

The input schema for this action consists of several fields that define how the video should be generated:

  • seed (optional, integer): A specific seed value for reproducibility. If not set, a random seed will be used by default.
    Example: 12345
  • steps (optional, integer): The number of diffusion steps to use in generating the video, ranging from 1 to 150 (default is 50).
    Example: 50
  • width (optional, integer): The width (in pixels) for the generated video, between 64 and 1536 (default is 640).
    Example: 640
  • height (optional, integer): The height (in pixels) for the generated video, between 64 and 1024 (default is 360).
    Example: 360
  • prompt (required, string): A descriptive text prompt that specifies the scene to be generated in the video.
    Example: "A video in the style of CWBYB, CWBYB The video clip depicts a serene and picturesque snow-covered landscape..."
  • flowShift (optional, integer): Continuity factor for the video flow, from 0 to 20 (default is 9).
    Example: 9
  • frameRate (optional, integer): The frames displayed per second in the video, ranging from 1 to 60 (default is 16).
    Example: 16
  • scheduler (optional, string): The algorithm for generating the video frames. Default is DPMSolverMultistepScheduler.
    Example: "DPMSolverMultistepScheduler"
  • frameCount (optional, integer): Number of frames in the video, from 1 to 1440 (default is 33).
    Example: 66
  • loraFileUrl (optional, string): URL to a LoRA .safetensors file or a Hugging Face repository.
    Example: "" (empty string for no LoRA file)
  • forceOffload (optional, boolean): Indicates whether to force offload model layers to the CPU (default is true).
    Example: true
  • guidanceScale (optional, number): Balances the influence of the prompt and the model's tendencies, from 0 to 30 (default is 6).
    Example: 6
  • loraIntensity (optional, number): Adjusts the intensity of the LoRA effect, from -10 to 10 (default is 1).
    Example: 1
  • qualityFactor (optional, integer): Specifies the CRF for H264 video encoding, with lower values yielding higher quality (default is 19).
    Example: 19
  • enhancementEnd (optional, number): Ends video enhancement, as a proportion of total duration (default is 1).
    Example: 1
  • denoiseStrength (optional, number): Strength of noise reduction, from 0 to 2 (default is 1).
    Example: 1
  • enhancementStart (optional, number): Starts video enhancement, as a proportion of total duration (default is 0).
    Example: 0
  • enhancementStrength (optional, number): Degree of enhancement applied to the video, from 0 to 2 (default is 0.3).
    Example: 0.3
  • doubleFrameEnhancement (optional, boolean): Applies enhancement across pairs of frames (default is true).
    Example: true
  • singleFrameEnhancement (optional, boolean): Applies enhancement to individual frames (default is true).
    Example: true

Example Input:

{
    "seed": 12345,
    "steps": 50,
    "width": 640,
    "height": 360,
    "prompt": "A video in the style of CWBYB, CWBYB The video clip depicts a serene and picturesque snow-covered landscape...",
    "flowShift": 9,
    "frameRate": 16,
    "scheduler": "DPMSolverMultistepScheduler",
    "frameCount": 66,
    "loraFileUrl": "",
    "forceOffload": true,
    "guidanceScale": 6,
    "loraIntensity": 1,
    "qualityFactor": 19,
    "enhancementEnd": 1,
    "denoiseStrength": 1,
    "enhancementStart": 0,
    "enhancementStrength": 0.3,
    "doubleFrameEnhancement": true,
    "singleFrameEnhancement": true
}

Output:

The action typically returns a URL to the generated video.
Example Output: "https://assets.cognitiveactions.com/invocations/f2a7ef34-edc6-4576-b0e4-1f94e4d9eb02/c2ce7496-84cf-4753-bf7d-3324ef242867.mp4"

Conceptual Usage Example (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 = "85693810-089e-49e8-b9f1-20826998f245" # Action ID for Generate Video in Cowboy Bebop Style

# Construct the input payload based on the action's requirements
payload = {
    "seed": 12345,
    "steps": 50,
    "width": 640,
    "height": 360,
    "prompt": "A video in the style of CWBYB, CWBYB The video clip depicts a serene and picturesque snow-covered landscape...",
    "flowShift": 9,
    "frameRate": 16,
    "scheduler": "DPMSolverMultistepScheduler",
    "frameCount": 66,
    "loraFileUrl": "",
    "forceOffload": true,
    "guidanceScale": 6,
    "loraIntensity": 1,
    "qualityFactor": 19,
    "enhancementEnd": 1,
    "denoiseStrength": 1,
    "enhancementStart": 0,
    "enhancementStrength": 0.3,
    "doubleFrameEnhancement": true,
    "singleFrameEnhancement": 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 YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The action_id is set to the ID for generating a video in Cowboy Bebop style. The input payload is constructed based on the action's schema, and the request is sent to the hypothetical endpoint to generate the video.

Conclusion

The deepfates/hunyuan-cowboy-bebop API offers a unique way to generate videos in a style that resonates with fans of the Cowboy Bebop series. By utilizing the provided Cognitive Action, developers can easily create and customize video content that captures the essence of this iconic anime. Explore the possibilities, experiment with different prompts and settings, and let your creativity flow!

← Back to All Articles