image-generation

Create Stunning Images with Sgntre's Inpainting Action

26 Apr 2025
Create Stunning Images with Sgntre's Inpainting Action

In the ever-evolving world of digital content creation, the need for high-quality images is paramount. Sgntre offers a powerful suite of Cognitive Actions designed to streamline the image generation process, particularly through its innovative inpainting capabilities. This action allows developers to create images using customizable settings, enabling quick and efficient generation of visual content tailored to specific needs.

With Sgntre's inpainting action, users can enhance existing images or create entirely new ones based on descriptive prompts. This flexibility opens up a multitude of use cases, from graphic design and marketing to game development and social media content creation. Whether you're looking to fill in missing parts of an image or generate completely new visuals from scratch, Sgntre's inpainting action provides the tools necessary to elevate your projects.

Prerequisites

To get started with Sgntre's Cognitive Actions, you will need an API key and a basic understanding of making API calls.

Generate Image with Inpainting

The Generate Image with Inpainting action is designed to create images using specified models while offering extensive customization options. This action solves the challenge of generating high-quality images that meet specific artistic or design requirements.

Input Requirements

To utilize this action, you will need to provide a structured input that includes:

  • prompt: A descriptive string indicating what the image should depict (required).
  • mask: An optional image mask for inpainting.
  • image: An optional input image for image-to-image generation.
  • model: Choice of model for inference (options include "dev" for quality and "schnell" for speed).
  • width and height: Dimensions of the generated image (if aspect ratio is custom).
  • goFast: A boolean to enable faster predictions.
  • additional parameters: Such as guidanceScale, outputQuality, and numInferenceSteps to control the image generation process.

Expected Output

The action will return one or more URLs pointing to the generated images in the specified format (e.g., webp, jpg, png).

Use Cases for this specific action

  • Graphic Design: Quickly generate images based on client specifications, allowing for rapid iterations and creative experimentation.
  • Marketing: Create tailored visuals for campaigns that resonate with target audiences by using specific prompts and styles.
  • Game Development: Develop unique assets by inpainting existing images or generating new ones that fit the game’s aesthetic.
  • Social Media: Produce eye-catching images that enhance posts and attract engagement through visually appealing content.
import requests
import json

# Replace with your actual Cognitive Actions API key and endpoint
# Ensure your environment securely handles the API key
COGNITIVE_ACTIONS_API_KEY = "YOUR_COGNITIVE_ACTIONS_API_KEY"
# This endpoint URL is hypothetical and should be documented for users
COGNITIVE_ACTIONS_EXECUTE_URL = "https://api.cognitiveactions.com/actions/execute"

action_id = "5a0165c4-eaf8-481c-9095-76bf3161b08b" # Action ID for: Generate Image with Inpainting

# Construct the exact input payload based on the action's requirements
# This example uses the predefined example_input for this action:
payload = {
  "model": "dev",
  "prompt": "film photograph of SGNTRE",
  "loraScale": 1,
  "aspectRatio": "1:1",
  "outputFormat": "webp",
  "guidanceScale": 3.5,
  "outputQuality": 90,
  "extraLoraScale": 1,
  "promptStrength": 0.8,
  "numberOfOutputs": 2,
  "numInferenceSteps": 28
}

headers = {
    "Authorization": f"Bearer {COGNITIVE_ACTIONS_API_KEY}",
    "Content-Type": "application/json",
    # Add any other required headers for the Cognitive Actions API
}

# Prepare the request body for the hypothetical execution endpoint
request_body = {
    "action_id": action_id,
    "inputs": payload
}

print(f"--- Calling Cognitive Action: {action.name or action_id} ---")
print(f"Endpoint: {COGNITIVE_ACTIONS_EXECUTE_URL}")
print(f"Action ID: {action_id}")
print("Payload being sent:")
print(json.dumps(request_body, indent=2))
print("------------------------------------------------")

try:
    response = requests.post(
        COGNITIVE_ACTIONS_EXECUTE_URL,
        headers=headers,
        json=request_body
    )
    response.raise_for_status() # Raise an exception for bad status codes (4xx or 5xx)

    result = response.json()
    print("Action executed successfully. Result:")
    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 (non-JSON): {e.response.text}")
    print("------------------------------------------------")

Conclusion

Sgntre's Generate Image with Inpainting action is a powerful tool for developers seeking to create high-quality, customized images efficiently. With its versatile input options and ability to generate images based on specific prompts, this action caters to a wide range of applications in various industries.

To harness the full potential of Sgntre, explore its other Cognitive Actions and integrate them into your projects for enhanced creativity and productivity. Start generating stunning visuals today!

← Back to All Articles