Generate Stunning Images with MiaoMiao-Harem-v1.5b Cognitive Actions

22 Apr 2025
Generate Stunning Images with MiaoMiao-Harem-v1.5b Cognitive Actions

In the world of AI, the ability to generate images from text prompts is a revolutionary step that opens up countless creative possibilities. The MiaoMiao-Harem-v1.5b spec provides a powerful Cognitive Action that allows developers to create images tailored to specific descriptions. This action takes advantage of advanced AI models to produce high-quality graphics based on user-defined parameters, making it an excellent tool for applications in gaming, graphic design, and more.

Prerequisites

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

  • An API key from the Cognitive Actions platform, which will be used for authentication.
  • Basic knowledge of JSON and Python for constructing API requests.
  • Familiarity with the image generation process and how various parameters affect the output.

Authentication typically involves passing your API key in the headers of your requests.

Cognitive Actions Overview

Generate Images Using MiaoMiao-Harem-v1.5b

This action creates images based on text prompts using the MiaoMiao-Harem-v1.5b model. It allows for extensive customization of image dimensions, style adherence, and quality enhancement through various scaling options.

Category: Image Generation

Input:

The input to this action is a JSON object containing various fields that dictate how the image is generated. Below is the schema and an example of the input:

{
  "seed": -1,
  "model": "MiaoMiao-Harem-v1.5b",
  "steps": 30,
  "width": 1024,
  "height": 1024,
  "prompt": "street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V",
  "scheduler": "Euler a",
  "configScale": 6,
  "clipLayerSkip": 2,
  "imageBatchSize": 1,
  "negativePrompt": "nsfw, naked",
  "prependPrePrompt": true,
  "progressiveScale": 0,
  "guidanceRescaleAmount": 1,
  "variationalAutoencoder": "default"
}
  • seed: (integer) Initializes the random number generator. Use -1 for a random seed.
  • model: (string) The AI model used for generating images. Default is "MiaoMiao-Harem-v1.5b".
  • steps: (integer) The number of steps for image generation (1 to 100). Default is 30.
  • width: (integer) The image width in pixels (1 to 4096). Default is 1024.
  • height: (integer) The image height in pixels (1 to 4096). Default is 1024.
  • prompt: (string) The text guiding image generation using Compel weighting syntax.
  • scheduler: (string) The scheduler algorithm for image generation. Default is "Euler a".
  • configScale: (number) CFG scale for prompt adherence (1 to 50). Default is 5.
  • clipLayerSkip: (integer) Number of CLIP layers to skip. Default is 2.
  • imageBatchSize: (integer) Number of images to generate at once (1 to 4). Default is 1.
  • negativePrompt: (string) Specifies undesirable elements in generation. Defaults to "nsfw, naked".
  • prependPrePrompt: (boolean) Indicates if to prepend a predefined pre-prompt to the input. Default is true.
  • progressiveScale: (number) Enhances image quality progressively (0 to 50). Default is 3.
  • guidanceRescaleAmount: (number) Adjusts rescaling of noise for exposure control (0 to 5). Default is 0.5.
  • variationalAutoencoder: (string) The VAE to use. Default is "default".

Output:

The action typically returns a URL to the generated image. For example:

[
  "https://assets.cognitiveactions.com/invocations/7da267c3-718f-4e31-8dcf-584861e45da4/5484384f-c427-4635-8b0b-99d24b39d6bb.png"
]

This URL points to the created image, allowing you to display or download it as needed.

Conceptual Usage Example (Python):

Here's a conceptual code snippet demonstrating how to invoke the image generation 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 = "f0a3fb43-f8f2-499d-83e9-502de84265b7"  # Action ID for Generate Images Using MiaoMiao-Harem-v1.5b

# Construct the input payload based on the action's requirements
payload = {
    "seed": -1,
    "model": "MiaoMiao-Harem-v1.5b",
    "steps": 30,
    "width": 1024,
    "height": 1024,
    "prompt": "street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V",
    "scheduler": "Euler a",
    "configScale": 6,
    "clipLayerSkip": 2,
    "imageBatchSize": 1,
    "negativePrompt": "nsfw, naked",
    "prependPrePrompt": True,
    "progressiveScale": 0,
    "guidanceRescaleAmount": 1,
    "variationalAutoencoder": "default"
}

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 Python code snippet, replace the placeholder for your API key and endpoint. The action ID corresponds to the Generate Images Using MiaoMiao-Harem-v1.5b action. The payload is structured based on the input schema, and the response contains the URL to the generated image.

Conclusion

The MiaoMiao-Harem-v1.5b Cognitive Action for image generation provides developers with an efficient and powerful tool to create custom images from text prompts. By understanding the various input parameters and how to structure API requests, you can easily integrate this feature into your applications. Explore the capabilities of AI image generation and consider potential use cases such as game design, content creation, and more. Happy coding!

← Back to All Articles