Create Stunning Images with justingriffioen/justin_v2 Cognitive Actions

22 Apr 2025
Create Stunning Images with justingriffioen/justin_v2 Cognitive Actions

In today’s digital landscape, the ability to generate images from text prompts has become increasingly valuable for developers. The justingriffioen/justin_v2 API offers a powerful Cognitive Action that allows users to create images based on textual descriptions. This capability not only enhances creativity but can also be integrated into various applications ranging from art generation to content creation. In this post, we'll explore the Generate Image Based on Prompt action, its inputs, outputs, and how to seamlessly integrate it into your applications.

Prerequisites

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

  • An API key for the Cognitive Actions platform.
  • Familiarity with sending HTTP requests, particularly POST requests.
  • Basic knowledge of JSON formatting.

Authentication typically involves including your API key in the request headers. This allows you to securely access the Cognitive Actions endpoint.

Cognitive Actions Overview

Generate Image Based on Prompt

The Generate Image Based on Prompt action generates an image using a text prompt. It offers various options for inpainting, image size, and model selection, allowing developers to optimize for speed or quality. You can also customize output formats, integrate LoRA, and adjust prompt strength to refine the image generation process.

Input

The input schema for this action is a JSON object that requires the following fields:

  • prompt (required): The text prompt guiding the image generation.
  • Optional fields include mask, seed, image, model, width, height, fastMode, and more.

Example Input:

{
  "model": "dev",
  "prompt": "JUSTIN smiling with a white background",
  "fastMode": false,
  "megapixels": "1",
  "aspectRatio": "1:1",
  "outputCount": 1,
  "outputFormat": "webp",
  "guidanceScale": 3,
  "mainLoraScale": 1,
  "outputQuality": 80,
  "extraLoraScale": 1,
  "promptStrength": 0.8,
  "inferenceStepCount": 28
}

Output

The output of this action will typically return a URL pointing to the generated image.

Example Output:

[
  "https://assets.cognitiveactions.com/invocations/cdb09219-4dee-429a-affc-a534d105d670/03744b56-1f4f-49ba-8a46-bcb3a31474ae.webp"
]

Conceptual Usage Example (Python)

Here’s how you might call the Generate Image Based on Prompt 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 = "4d4499df-9f99-4e5e-87ee-710f91f6867e" # Action ID for Generate Image Based on Prompt

# Construct the input payload based on the action's requirements
payload = {
    "model": "dev",
    "prompt": "JUSTIN smiling with a white background",
    "fastMode": False,
    "megapixels": "1",
    "aspectRatio": "1:1",
    "outputCount": 1,
    "outputFormat": "webp",
    "guidanceScale": 3,
    "mainLoraScale": 1,
    "outputQuality": 80,
    "extraLoraScale": 1,
    "promptStrength": 0.8,
    "inferenceStepCount": 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}
    )
    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 code snippet, we replace the action ID and input payload with the appropriate values. The endpoint URL and request structure are illustrative, and you should adapt them based on your environment.

Conclusion

The Generate Image Based on Prompt action from the justingriffioen/justin_v2 API empowers developers to create captivating images from simple text prompts. With its flexible input parameters and high-quality output, you can easily incorporate this functionality into your applications. Whether you're building an art project, enhancing a game, or generating unique content, these capabilities can significantly elevate your offerings. Start experimenting with the Cognitive Actions today and unlock the creative potential of your applications!

← Back to All Articles