Transforming Images with Text Prompts: A Guide to danielguedesb/pix2pix Cognitive Actions

21 Apr 2025
Transforming Images with Text Prompts: A Guide to danielguedesb/pix2pix Cognitive Actions

In the world of image generation, the ability to create visuals from textual descriptions opens up numerous possibilities for developers and artists alike. The danielguedesb/pix2pix API offers a powerful Cognitive Action that allows you to generate new images using a combination of a source image and a descriptive text prompt. This article will walk you through how to effectively use this action and its various parameters to achieve stunning results.

Prerequisites

Before diving into the implementation, ensure you have the following:

  • An API key for the Cognitive Actions platform to authenticate your requests.
  • Familiarity with making HTTP requests in your programming language of choice, particularly in Python.

Authentication typically involves passing your API key in the request headers, ensuring secure access to the Cognitive Actions services.

Cognitive Actions Overview

Generate Image with Text Guidance

The Generate Image with Text Guidance action enables you to create a new image by providing a URI of an existing image along with a descriptive text prompt. This action allows you to adjust various parameters such as the scheduler algorithm, guidance scale, and the number of inference steps to control the quality and relevance of the generated image.

  • Category: Image Generation

Input

The input for this action requires the following fields:

  • image (string, required): A valid URI of the image to be modified.
  • prompt (string, required): A descriptive text prompt guiding the image generation.
  • seed (integer, optional): A random seed for deterministic results (leave blank for random).
  • scheduler (string, optional): Scheduler algorithm to use (default: K_EULER_ANCESTRAL).
  • guidanceScale (number, optional): Scale for classifier-free guidance (default: 7.5, range: 1-20).
  • negativePrompt (string, optional): Elements to avoid in the generated image.
  • numberOfOutputs (integer, optional): Number of images to generate per request (default: 1, options: 1 or 4).
  • imageGuidanceScale (number, optional): Scale for matching the generated image to the source image (default: 1.5, minimum: 1).
  • numberOfInferenceSteps (integer, optional): Number of denoising steps during generation (default: 100, range: 1-500).

Example Input:

{
  "image": "https://replicate.delivery/pbxt/KaTzERm9BD8vG81jdtQ57gBKxwC5lGsSCMLMMzRjLfG0G9of/Screenshot%202024-03-16%20at%2019.48.23.png",
  "prompt": "make the fruit dark red",
  "scheduler": "K_EULER_ANCESTRAL",
  "guidanceScale": 7.5,
  "numberOfOutputs": 1,
  "imageGuidanceScale": 1.5,
  "numberOfInferenceSteps": 100
}

Output

Upon successful execution, this action returns an array of URIs pointing to the generated images based on the provided input.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/1602913f-92a7-46b3-a5dc-2937b3b97c4d/e03a2a73-8aba-4438-ac18-6649561cff94.png"
]

Conceptual Usage Example (Python)

Here is how you might structure your Python code to call this Cognitive Action:

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 = "3aa5baba-abe6-4e18-bbc8-b1a93246875b"  # Action ID for Generate Image with Text Guidance

# Construct the input payload based on the action's requirements
payload = {
    "image": "https://replicate.delivery/pbxt/KaTzERm9BD8vG81jdtQ57gBKxwC5lGsSCMLMMzRjLfG0G9of/Screenshot%202024-03-16%20at%2019.48.23.png",
    "prompt": "make the fruit dark red",
    "scheduler": "K_EULER_ANCESTRAL",
    "guidanceScale": 7.5,
    "numberOfOutputs": 1,
    "imageGuidanceScale": 1.5,
    "numberOfInferenceSteps": 100
}

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 YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The action_id is specific to the Generate Image with Text Guidance action, and the payload is structured according to the required input schema.

Conclusion

The danielguedesb/pix2pix Cognitive Action enables developers to harness the power of AI-driven image generation using text prompts and existing images. By adjusting parameters like guidance scale and inference steps, you can fine-tune the quality and relevance of the generated images. Whether you're building creative applications or enhancing existing workflows, these capabilities offer exciting opportunities for innovation. Start experimenting with this action today and unlock new creative potentials in your applications!

← Back to All Articles