Generate Stunning Images with digitpixie/digitpixie-flux-lora Cognitive Actions

22 Apr 2025
Generate Stunning Images with digitpixie/digitpixie-flux-lora Cognitive Actions

In the world of artificial intelligence and machine learning, generating custom images has become a game-changer for developers and artists alike. The digitpixie/digitpixie-flux-lora API offers powerful Cognitive Actions that allow you to create highly detailed images tailored to your specific needs. With features like aspect ratio adjustments, resolution settings, and advanced options such as LoRA weights, these actions enable developers to enhance image quality while optimizing for speed. In this article, we’ll explore how to leverage the Generate Custom Images action to integrate stunning image generation capabilities into your applications.

Prerequisites

Before you start using the Cognitive Actions, ensure you have the following:

  • An API key for the digitpixie service.
  • Basic knowledge of making API calls and handling JSON data.

Authentication typically involves passing your API key in the headers of your requests, allowing you to securely access the image generation functionalities.

Cognitive Actions Overview

Generate Custom Images

The Generate Custom Images action allows you to create images based on specified parameters, including resolution, aspect ratio, and model selection. This action is particularly useful for applications that require unique imagery, such as marketing materials, gaming assets, or artistic projects.

Input

The input for this action is structured as follows:

  • prompt (required): A text prompt to guide the image generation. For example, "photo of dp, a woman, walking in a street in Toulouse, France, short bob hair cut".
  • mask (optional): A URL for an image mask used for inpainting.
  • seed (optional): An integer to ensure reproducibility of the output.
  • image (optional): A URL for an input image used for image-to-image generation.
  • width (optional): Width of the generated image in pixels (256 to 1440).
  • height (optional): Height of the generated image in pixels (256 to 1440).
  • goFast (optional): A boolean to enable faster generation.
  • aspectRatio (optional): Defines the aspect ratio (default is "1:1").
  • numOutputs (optional): Number of images to generate simultaneously (1 to 4).
  • outputFormat (optional): The output image format (default is "webp").
  • guidanceScale (optional): Scale for guidance during the generation process (0 to 10).
  • outputQuality (optional): Quality setting for saving output images (0 to 100, not applicable for png).
  • extraLora (optional): Load additional LoRA model weights.
  • loraScale (optional): Scale factor for primary LoRA strength (-1 to 3).
  • extraLoraScale (optional): Scale factor for secondary LoRA strength (-1 to 3).
  • inferenceModel (optional): Select the model for inference ("dev" or "schnell").
  • promptStrength (optional): Prompt strength when using image-to-image generation (0 to 1).
  • numInferenceSteps (optional): Number of denoising steps (1 to 50).
  • disableSafetyChecker (optional): Option to disable the safety checker.

Example Input:

{
  "prompt": "photo of dp, a woman, walking in a street in Toulouse, France, short bob hair cut",
  "loraScale": 1,
  "numOutputs": 3,
  "aspectRatio": "9:16",
  "outputFormat": "webp",
  "guidanceScale": 3.5,
  "outputQuality": 90,
  "extraLoraScale": 1,
  "inferenceModel": "dev",
  "promptStrength": 0.8,
  "numInferenceSteps": 28
}

Output

The output of this action consists of URLs pointing to the generated images. For instance, you might receive the following output:

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/1c7421cd-37cc-49da-be92-58b0b55ad950/a11c63dc-87dc-416c-828c-6bdf360ea240.webp",
  "https://assets.cognitiveactions.com/invocations/1c7421cd-37cc-49da-be92-58b0b55ad950/a065d258-9daf-42a3-8c0a-9b469236bf50.webp",
  "https://assets.cognitiveactions.com/invocations/1c7421cd-37cc-49da-be92-58b0b55ad950/c51f43fd-af3a-4140-9cc3-c4fd665be9d7.webp"
]

Conceptual Usage Example (Python)

Here is how you might call the Generate Custom Images 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 = "4245c610-d7f3-4b04-b7da-f4d8ae2e1534" # Action ID for Generate Custom Images

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "photo of dp, a woman, walking in a street in Toulouse, France, short bob hair cut",
    "loraScale": 1,
    "numOutputs": 3,
    "aspectRatio": "9:16",
    "outputFormat": "webp",
    "guidanceScale": 3.5,
    "outputQuality": 90,
    "extraLoraScale": 1,
    "inferenceModel": "dev",
    "promptStrength": 0.8,
    "numInferenceSteps": 28
}

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:

  • The action_id corresponds to the Generate Custom Images action.
  • The payload is structured based on the required and optional inputs.
  • The headers include your API key for authentication.
  • The response is handled gracefully, allowing you to see both the successful output and any errors.

Conclusion

By integrating the Generate Custom Images action from the digitpixie/digitpixie-flux-lora API, developers can easily create stunning, customized images that meet their specific requirements. This capability opens up a myriad of possibilities for enhancing applications in various domains, from creative arts to commercial products. Start experimenting with the action today, and unleash the power of AI-driven image generation in your projects!

← Back to All Articles