Create Stunning Art with the Remedios Varo Style Image Action

24 Apr 2025
Create Stunning Art with the Remedios Varo Style Image Action

In the world of art and creativity, the ability to generate unique images using artificial intelligence has opened up exciting possibilities. The cyber42/remedios_varo API offers a powerful Cognitive Action that allows developers to create images inspired by the iconic style of Remedios Varo. This action leverages a fine-tuned model to produce visually captivating results based on customizable prompts. In this article, we will explore how to integrate the "Generate Remedios Varo Style Image" action into your applications and unlock its full potential.

Prerequisites

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

  • An API key for the Cognitive Actions platform. This key will be used for authentication.
  • Conceptual understanding of how to make API calls, where you will pass your API key in the request headers.

Cognitive Actions Overview

Generate Remedios Varo Style Image

Description: This action generates images in the style of the renowned artist Remedios Varo. With options for customizable prompts, negative prompts to exclude unwanted elements, and various enhancements like image size and watermarking, developers can create unique artistic outputs.

Category: Image Generation

Input

The input for this action requires a structured JSON object with several fields:

  • mask (optional): URI of the input mask for inpainting mode.
  • seed (optional): Random seed for generation; leave blank for a random seed.
  • image (optional): URI of the input image for img2img or inpainting mode.
  • width: Width (in pixels) of the output image. Default is 1024 pixels.
  • height: Height (in pixels) of the output image. Default is 1024 pixels.
  • prompt: Text prompt to guide the image generation.
  • inversePrompt (optional): Specifies undesirable elements to exclude.
  • applyWatermark: Determines if a watermark is applied; default is true.
  • promptIntensity: Strength of the prompt in img2img or inpainting modes, ranging from 0 to 1.
  • refinementSteps (optional): Number of refinement steps for the image.
  • refinementStyle: Choice of refinement style to apply.
  • outputImageCount: Number of images to generate, maximum is 4.
  • schedulingMethod: Scheduler algorithm for generation.
  • guidanceIntensity: Strength of guidance applied to the generation process.
  • highNoiseFraction (optional): Fraction of applied noise for refiners.
  • inferenceStepCount: Number of denoising steps during inference.
  • loraAdjustmentScale: Adjustment scale for LoRA weights.
  • safetyCheckerDisabled: Allows disabling the safety checker for generated images.

Example Input:

{
  "width": 1024,
  "height": 1024,
  "prompt": "In the style of RemediosVaro, a person looking at her image in a lake",
  "inversePrompt": "",
  "applyWatermark": true,
  "promptIntensity": 0.8,
  "refinementStyle": "no_refiner",
  "outputImageCount": 1,
  "schedulingMethod": "K_EULER",
  "guidanceIntensity": 7.5,
  "highNoiseFraction": 0.8,
  "inferenceStepCount": 50,
  "loraAdjustmentScale": 0.6
}

Output

The action typically returns a list of URIs pointing to the generated images.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/a2c85b7b-65a5-4aaa-9f01-b6cc2a6ccc53/3e322dd7-ec08-4e57-9f01-b6cc2a6ccc53.png"
]

Conceptual Usage Example (Python)

Here’s a conceptual example of how to call the "Generate Remedios Varo Style Image" 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 = "5581c35e-36d9-4470-871d-8616608f68e0"  # Action ID for Generate Remedios Varo Style Image

# Construct the input payload based on the action's requirements
payload = {
    "width": 1024,
    "height": 1024,
    "prompt": "In the style of RemediosVaro, a person looking at her image in a lake",
    "inversePrompt": "",
    "applyWatermark": True,
    "promptIntensity": 0.8,
    "refinementStyle": "no_refiner",
    "outputImageCount": 1,
    "schedulingMethod": "K_EULER",
    "guidanceIntensity": 7.5,
    "highNoiseFraction": 0.8,
    "inferenceStepCount": 50,
    "loraAdjustmentScale": 0.6
}

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}
    )
    response.raise_for_status()

    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 API key and endpoint with your own. The action_id corresponds to the "Generate Remedios Varo Style Image" action. The payload includes the necessary input fields formatted according to the action's schema.

Conclusion

The "Generate Remedios Varo Style Image" Cognitive Action offers a fantastic opportunity to infuse creativity into your applications. By leveraging customizable prompts and advanced options, you can create stunning images that resonate with the unique style of Remedios Varo. Start experimenting with this action today, and imagine the artistic possibilities that await!

← Back to All Articles