Generate Stunning Images with DeepFates/Flux-BG3 Cognitive Actions

23 Apr 2025
Generate Stunning Images with DeepFates/Flux-BG3 Cognitive Actions

In the realm of game-inspired art, creating visually captivating images can be a daunting task. The DeepFates/Flux-BG3 API provides a powerful set of Cognitive Actions designed for developers looking to leverage advanced image generation capabilities specifically themed around Baldur's Gate 3. With these pre-built actions, developers can easily create rich and detailed images, enhancing their applications or personal projects with minimal effort.

Prerequisites

Before diving into the integration of the DeepFates/Flux-BG3 Cognitive Actions, ensure you have the following:

  • API Key: You will need an API key to authenticate your requests to the Cognitive Actions platform.
  • Basic Setup: Familiarity with making HTTP requests and handling JSON data in your development environment.

Conceptually, authentication typically involves passing your API key in the request headers, allowing you to access the various Cognitive Actions available.

Cognitive Actions Overview

Generate Baldur's Gate 3 Themed Image

The Generate Baldur's Gate 3 Themed Image action allows you to create images inspired by the Baldur's Gate 3 universe using the FLUX lora model. This action supports various options for aspect ratio, quality, and detailed customization, ensuring that the images generated are both thematic and high-quality.

Input

The input for this action requires a structured JSON object. Below are the key fields:

  • Required:
    • prompt: A text prompt guiding the image generation, for instance, "A BG3 portrait of a human male with blue skin, blond curly hair and a short beard".
  • Optional:
    • mask: URI of an image mask for inpainting.
    • seed: Random seed for consistent image generation.
    • image: URI of an input image for inpainting mode.
    • width and height: Dimensions for the generated image, applicable when using a custom aspect ratio.
    • goFast: Toggle for speed-optimized model.
    • numOutputs: Number of images to generate (1 to 4).
    • guidanceScale: Influences adherence to the prompt versus realism.
    • outputQuality: Image saving quality percentage (0 to 100).
    • outputImageFormat: File format for the output images (webp, jpg, png).
    • And more!

Here’s an example input JSON:

{
  "prompt": "A BG3 portrait of a human male with blue skin, blond curly hair and a short beard",
  "loraScale": 1,
  "numOutputs": 1,
  "guidanceScale": 2.5,
  "outputQuality": 90,
  "extraLoraScale": 1,
  "inferenceModel": "dev",
  "promptStrength": 0.8,
  "imageAspectRatio": "1:1",
  "numInferenceSteps": 28,
  "outputImageFormat": "webp"
}

Output

Upon successful execution, this action returns a list of generated image URLs. For example:

[
  "https://assets.cognitiveactions.com/invocations/ab7705dc-0d7e-49d9-99bb-a745fe11f513/32b9197b-7a79-439e-a7c1-c46e32c82561.webp"
]

The output consists of one or more links to the generated images based on your input specifications.

Conceptual Usage Example (Python)

Here’s how you might call this action using a hypothetical Cognitive Actions endpoint in 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 = "ac6a4665-b689-44d2-ac6a-2da86a2dd3c6" # Action ID for Generate Baldur's Gate 3 Themed Image

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "A BG3 portrait of a human male with blue skin, blond curly hair and a short beard",
    "loraScale": 1,
    "numOutputs": 1,
    "guidanceScale": 2.5,
    "outputQuality": 90,
    "extraLoraScale": 1,
    "inferenceModel": "dev",
    "promptStrength": 0.8,
    "imageAspectRatio": "1:1",
    "numInferenceSteps": 28,
    "outputImageFormat": "webp"
}

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 and endpoint. The action ID and input payload are structured based on the requirements of the Generate Baldur's Gate 3 Themed Image action. The example highlights how to send a POST request and handle the response effectively.

Conclusion

The DeepFates/Flux-BG3 Cognitive Actions provide a robust solution for developers looking to create stunning images inspired by the Baldur's Gate 3 universe. With customizable parameters and an easy-to-use interface, you can enhance your applications with unique visual content. Consider exploring different prompts and configurations to fully leverage the capabilities of this powerful API. Happy coding!

← Back to All Articles