Generate Stunning Images with PrometheusV1 Cognitive Actions

23 Apr 2025
Generate Stunning Images with PrometheusV1 Cognitive Actions

In today's digital landscape, the ability to create compelling visuals from text descriptions has become increasingly valuable. The PrometheusV1 cognitive actions provide developers with a powerful tool to generate images from text prompts. This model, a fine-tuned version of Playground v2.5, enhances accessibility for the open-source community and offers compatibility with various tools while delivering intricate and high-quality outputs. With PrometheusV1, you can transform your creative ideas into vibrant images effortlessly.

Prerequisites

Before you get started with PrometheusV1, ensure you have the following:

  • An API key from the Cognitive Actions platform to authenticate your requests.
  • A basic understanding of how to make API calls using JSON.
  • Familiarity with handling HTTP requests in your programming environment.

To authenticate, you'll typically pass your API key in the headers of your requests.

Cognitive Actions Overview

Generate Image with PrometheusV1

The Generate Image with PrometheusV1 action allows you to generate images based on textual descriptions. This action is particularly useful for applications requiring dynamic visual content creation.

Input

The input schema for this action is a JSON object that includes several properties:

  • prompt: (string) The text prompt guiding image generation.
    Example: "high quality pixel art, a pixel art silhouette of an anime space-themed girl in a space-punk steampunk style..."
  • width: (integer) The width of the output image in pixels.
    Default: 1024
  • height: (integer) The height of the output image in pixels.
    Default: 1024
  • scheduler: (string) The algorithm used to schedule denoising steps.
    Default: "DPM++2MSDE"
  • guidanceScale: (number) A scaling factor for classifier-free guidance.
    Default: 7 (recommended range: 4-6)
  • negativePrompt: (string) Optional text to specify features to avoid in the image.
  • promptStrength: (number) The strength of the text prompt effect in img2img or inpaint modes.
    Default: 0.8 (range: 0-1)
  • numberOfOutputs: (integer) Number of images to generate.
    Default: 1 (max 4)
  • numberOfInferenceSteps: (integer) The number of denoising steps.
    Default: 50 (range: 1-100)
  • mask: (string) URI of the input mask for inpaint mode (optional).
  • image: (string) URI of the input image for img2img or inpaint mode (optional).
  • disableSafetyChecker: (boolean) Flag to disable the safety checker for generated images (available only via API).

Here’s how a sample input JSON looks:

{
  "width": 1024,
  "height": 1024,
  "prompt": "high quality pixel art, a pixel art silhouette of an anime space-themed girl in a space-punk steampunk style...",
  "scheduler": "DPM++2MSDE",
  "guidanceScale": 7,
  "negativePrompt": "",
  "promptStrength": 0.8,
  "numberOfOutputs": 1,
  "numberOfInferenceSteps": 50
}

Output

Upon successful execution, the action returns a list of URLs pointing to the generated images. Here’s an example of the output:

[
  "https://assets.cognitiveactions.com/invocations/33d28410-bf40-40f3-a8df-29d52f0e684f/0d461e19-b7bc-40f5-ac47-0df25bb066bd.png"
]

This URL can be used to display the generated image in your application.

Conceptual Usage Example (Python)

Here’s a conceptual example of how you might implement this action in 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 = "f7f23a13-b7cc-424f-9c13-4ffeb80e9b6b"  # Action ID for Generate Image with PrometheusV1

# Construct the input payload based on the action's requirements
payload = {
    "width": 1024,
    "height": 1024,
    "prompt": "high quality pixel art, a pixel art silhouette of an anime space-themed girl in a space-punk steampunk style...",
    "scheduler": "DPM++2MSDE",
    "guidanceScale": 7,
    "negativePrompt": "",
    "promptStrength": 0.8,
    "numberOfOutputs": 1,
    "numberOfInferenceSteps": 50
}

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 YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The payload contains the necessary parameters for image generation as specified in the input schema. The response will include the URL(s) of the generated images.

Conclusion

The PrometheusV1 Cognitive Actions provide an innovative way to generate images from text prompts, making it easier for developers to create rich visual content. With its flexible input options and robust output capabilities, this tool is an excellent addition to any application requiring dynamic imagery. Explore the possibilities and integrate PrometheusV1 into your projects to unlock your creative potential!

← Back to All Articles