Generate Stunning Images with Dvine-v3.4 Cognitive Actions

25 Apr 2025
Generate Stunning Images with Dvine-v3.4 Cognitive Actions

In today's digital world, the ability to generate high-quality images from textual descriptions has become increasingly valuable. The Dvine-v3.4 Cognitive Actions provide developers with a powerful API for generating images based on user-defined prompts. This integration allows for customization of various parameters, giving developers flexibility and control over the final output. By leveraging advanced features like Compel weighting syntax, users can fine-tune the image content to meet specific creative needs.

Prerequisites

Before diving into the integration of Dvine-v3.4 Cognitive Actions, ensure you have the following:

  • An API key for the Cognitive Actions platform.
  • Basic knowledge of JSON formatting.
  • A suitable development environment for making HTTP requests.

To authenticate your requests, you will typically pass your API key in the request headers. This allows you to securely access the Cognitive Actions services.

Cognitive Actions Overview

Generate Image with Dvine-v3.4

Description:
The "Generate Image with Dvine-v3.4" action uses the Dvine-v3.4 model to create images based on prompts defined by the user. This allows for extensive customization, including image dimensions, the number of generation steps, and various scheduling options. The incorporation of Compel weighting syntax enables users to specify both positive and negative prompts, enhancing the control over the image output.

Category: Image Generation

Input

The input schema for this action includes the following parameters:

  • seed (integer, optional): The seed value used for generating content. Set to -1 for a random seed.
    Example: -1
  • model (string, required): Specifies the model to be used, defaulting to "Dvine-v3.4".
    Example: "Dvine-v3.4"
  • steps (integer, optional): The number of steps for image generation, ranging from 1 to 100. Default is 40.
    Example: 40
  • width (integer, optional): The width of the generated image in pixels, between 1 and 4096. Default is 1024.
    Example: 1024
  • height (integer, optional): The height of the generated image in pixels, between 1 and 4096. Default is 1024.
    Example: 1024
  • prompt (string, required): The prompt for generating content, utilizing Compel weighting syntax for influence.
    Example: "street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V"
  • batchSize (integer, optional): The number of images to generate in a batch, valid between 1 to 4.
    Example: 1
  • scheduler (string, optional): Defines the scheduler to be used during generation. Default is "Euler a".
    Example: "Euler a"
  • clipLayerSkip (integer, optional): Specifies the number of CLIP layers to skip. Default is 2.
    Example: 2
  • pagScaleValue (number, optional): Adjusts the PAG scale, similar to CFG. Default is 0 (disabled).
    Example: 0
  • negativePrompt (string, optional): Specifies elements to be excluded from the generation, using Compel weighting syntax.
    Example: "nsfw, naked"
  • configurationScale (number, optional): Determines prompt adherence during generation. Default is 7.
    Example: 7
  • prependInitialPrompt (boolean, optional): Whether to prepend a predefined preprompt for enhanced quality. Default is true.
    Example: true
  • guidanceRescaleFactor (number, optional): Rescales CFG-generated noise to prevent overexposure. Default is 1.
    Example: 1
  • variationalAutoencoder (string, optional): Selects the VAE to utilize in the process. Default is "default".
    Example: "default"

Example Input:

{
  "seed": -1,
  "model": "Dvine-v3.4",
  "steps": 40,
  "width": 1024,
  "height": 1024,
  "prompt": "street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V",
  "batchSize": 1,
  "scheduler": "Euler a",
  "clipLayerSkip": 2,
  "pagScaleValue": 0,
  "negativePrompt": "nsfw, naked",
  "configurationScale": 7,
  "prependInitialPrompt": true,
  "guidanceRescaleFactor": 1,
  "variationalAutoencoder": "default"
}

Output

The action typically returns a URL to the generated image.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/70751f83-8866-4803-88c0-1a116fd6d04d/ca16708d-f6f8-4b54-9119-4f449cc314e4.png"
]

Conceptual Usage Example (Python)

Here’s how you can call the Dvine-v3.4 action using a conceptual Python code snippet:

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 = "44843f00-cd25-4652-888d-879ff96f44a2"  # Action ID for Generate Image with Dvine-v3.4

# Construct the input payload based on the action's requirements
payload = {
    "seed": -1,
    "model": "Dvine-v3.4",
    "steps": 40,
    "width": 1024,
    "height": 1024,
    "prompt": "street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V",
    "batchSize": 1,
    "scheduler": "Euler a",
    "clipLayerSkip": 2,
    "pagScaleValue": 0,
    "negativePrompt": "nsfw, naked",
    "configurationScale": 7,
    "prependInitialPrompt": True,
    "guidanceRescaleFactor": 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 code snippet, you replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The payload is structured according to the action's requirements, and the POST request is sent to the hypothetical endpoint.

Conclusion

The Dvine-v3.4 Cognitive Actions empower developers to generate customized images from textual prompts with ease. With various customizable parameters, you can fine-tune your image creation process to achieve stunning results. Start integrating these actions into your applications today, and explore the endless creative possibilities that await!

← Back to All Articles