Unlock Creative Possibilities: Integrating Image Generation with Cognitive Actions

23 Apr 2025
Unlock Creative Possibilities: Integrating Image Generation with Cognitive Actions

Cognitive Actions provide developers with powerful tools to leverage advanced image processing capabilities easily. The "andrey-lepekhin/innop_25_no_captions_1500steps" spec offers a unique action called "Generate Inpainted Image," designed to create customized images based on user-defined parameters. By utilizing this action, developers can enhance their applications with sophisticated image generation features without needing extensive background knowledge in machine learning or image processing.

Prerequisites

Before diving into the specifics of the Cognitive Action, ensure that you have the following prerequisites:

  • API Key: You will need a valid API key to authenticate requests to the Cognitive Actions platform.
  • Basic Knowledge of JSON: Familiarity with JSON structure will help you construct the input payload effectively.

Authentication is typically handled by including the API key in the request headers, which will grant you access to the Cognitive Actions service.

Cognitive Actions Overview

Generate Inpainted Image

The "Generate Inpainted Image" action is designed to create photorealistic images based on a text prompt and optional parameters. This action allows users to specify various customizations, including masks, seed values, aspect ratios, resolution, and output formats, to optimize the image generation process.

Input

The input for this action is structured as a JSON object, where the only required field is the prompt. Below is the schema, along with an example input:

{
  "prompt": "innop A photorealistic portrait of a psychotherapist (early 30s) in an inviting office environment...",
  "model": "dev",
  "goFast": false,
  "loraIntensity": 1,
  "imageResolution": "1",
  "numberOfOutputs": 4,
  "promptIntensity": 0.8,
  "imageAspectRatio": "1:1",
  "guidanceIntensity": 3,
  "imageOutputFormat": "webp",
  "imageOutputQuality": 80,
  "numberOfInferenceSteps": 28,
  "additionalLoraIntensity": 1
}

Output

Upon successful execution, the action returns an array of URLs pointing to the generated images. Here’s an example of the output you can expect:

[
  "https://assets.cognitiveactions.com/invocations/e3e971ff-48e4-481e-afa4-94b463dddad9/98a335cc-1675-4ecd-b6f8-b618a3741de1.webp",
  "https://assets.cognitiveactions.com/invocations/e3e971ff-48e4-481e-afa4-94b463dddad9/276c2895-2000-4f95-9012-70c327a3228e.webp",
  "https://assets.cognitiveactions.com/invocations/e3e971ff-48e4-481e-afa4-94b463dddad9/d4aafd9c-5317-4da6-ab85-d77fa499c240.webp",
  "https://assets.cognitiveactions.com/invocations/e3e971ff-48e4-481e-afa4-94b463dddad9/72d5d692-2bda-4002-8d86-feecd842cb32.webp"
]

Conceptual Usage Example (Python)

To invoke the "Generate Inpainted Image" action, you can use the following conceptual Python code snippet. This example shows how to structure the input payload and send the request:

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 = "8376643e-1839-4116-adcd-678b60af0778"  # Action ID for Generate Inpainted Image

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "innop A photorealistic portrait of a psychotherapist (early 30s) in an inviting office environment...",
    "model": "dev",
    "goFast": False,
    "loraIntensity": 1,
    "imageResolution": "1",
    "numberOfOutputs": 4,
    "promptIntensity": 0.8,
    "imageAspectRatio": "1:1",
    "guidanceIntensity": 3,
    "imageOutputFormat": "webp",
    "imageOutputQuality": 80,
    "numberOfInferenceSteps": 28,
    "additionalLoraIntensity": 1
}

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 snippet, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The payload variable is populated with the necessary input data based on the action's schema. The response will provide you with URLs to the generated images.

Conclusion

The "Generate Inpainted Image" action within the "andrey-lepekhin/innop_25_no_captions_1500steps" spec opens up creative avenues for developers looking to enhance their applications with advanced image generation capabilities. By leveraging the power of pre-built Cognitive Actions, you can quickly integrate sophisticated features without needing in-depth expertise in image processing. Explore the potential of this action and consider how it can elevate your projects!

← Back to All Articles