Generate Stunning Images with the FLUX Cognitive Actions

24 Apr 2025
Generate Stunning Images with the FLUX Cognitive Actions

In today's world of artificial intelligence, generating images from text prompts has become increasingly powerful and accessible. The FLUX.1 model offers developers the ability to create custom images using a variety of parameters, making it a valuable tool in applications ranging from art generation to content creation. This blog post will guide you through the capabilities of the FLUX Cognitive Actions, showcasing how to leverage its image generation features effectively.

Prerequisites

Before you begin integrating the FLUX Cognitive Actions into your application, ensure you have the following:

  • An API key for the Cognitive Actions platform. This key will authenticate your requests.
  • A basic understanding of JSON and how to make HTTP requests using your preferred programming language.

Typically, authentication can be accomplished by passing your API key in the request headers.

Cognitive Actions Overview

Generate Image Using Fine-tuned FLUX.1

The Generate Image Using Fine-tuned FLUX.1 action allows you to produce high-quality images based on custom text prompts. With support for various parameters such as aspect ratio, resolution, and styles, this action enables flexible image generation tailored to your needs. You can also choose between a fast mode for quicker outputs and a standard detailed mode for enhanced quality.

Input

The action requires the following input parameters:

  • prompt (required): The text prompt to guide the image generation.
  • aspectRatio (optional): Specifies the aspect ratio (defaults to 1:1).
  • width (optional): Desired width of the generated image.
  • height (optional): Desired height of the generated image.
  • goFast (optional): Enable faster predictions (defaults to false).
  • model (optional): Choose the inference model (defaults to dev).
  • imageFormat (optional): Format of the output image (defaults to webp).
  • outputCount (optional): Number of images to generate (default is 1, max is 4).
  • imageQuality (optional): Quality of the output images (default is 80).
  • additionalLora (optional): Additional LoRA weights for enhanced customization.

Here’s an example of how the input JSON payload might look:

{
  "model": "dev",
  "goFast": false,
  "prompt": "a portrait of bharath-reddy-g98 resembling littlekrishna...",
  "aspectRatio": "1:1",
  "imageFormat": "webp",
  "outputCount": 1,
  "imageQuality": 80,
  "promptImpact": 0.8,
  "guidanceScale": 3,
  "loraIntensity": 1.08,
  "additionalLora": "https://replicate.delivery/xezq/AAAoHMzMLrpoB9oKt92NEew3a8skeBnZvmQkvK7f33qBkYgoA/trained_model.tar",
  "imageResolution": "1",
  "inferenceStepCount": 28,
  "additionalLoraIntensity": 0.66
}

Output

Upon successful execution, the action will return a URL pointing to the generated image. Here’s an example of what the output might look like:

[
  "https://assets.cognitiveactions.com/invocations/c58b6bb4-991a-42dd-8f76-febb84890c39/75fce12e-d830-4e4c-ac01-094a86a81091.webp"
]

Conceptual Usage Example (Python)

Here’s how you might call the Generate Image Using Fine-tuned FLUX.1 action using 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 = "3249a820-f9c9-4aa7-b1bd-3c993c2d7f85" # Action ID for Generate Image Using Fine-tuned FLUX.1

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "goFast": False,
    "prompt": "a portrait of bharath-reddy-g98 resembling littlekrishna...",
    "aspectRatio": "1:1",
    "imageFormat": "webp",
    "outputCount": 1,
    "imageQuality": 80,
    "promptImpact": 0.8,
    "guidanceScale": 3,
    "loraIntensity": 1.08,
    "additionalLora": "https://replicate.delivery/xezq/AAAoHMzMLrpoB9oKt92NEew3a8skeBnZvmQkvK7f33qBkYgoA/trained_model.tar",
    "imageResolution": "1",
    "inferenceStepCount": 28,
    "additionalLoraIntensity": 0.66
}

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 example, you replace the YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key and modify the payload as necessary. The endpoint URL and request structure are illustrative, focusing on the core elements needed to use the action.

Conclusion

The FLUX Cognitive Actions provide a robust framework for generating images tailored to your specifications. With customizable parameters, developers can create a variety of visuals to enhance their applications. Whether you're looking to create stunning artwork or generate images for content, these actions are a powerful addition to your toolkit. Start experimenting with the FLUX.1 model to unlock your creative potential today!

← Back to All Articles