image-generation

Create Stunning Custom Images with Doublesuzy's Inpainting Action

26 Apr 2025
Create Stunning Custom Images with Doublesuzy's Inpainting Action

In today's fast-paced digital landscape, the ability to generate high-quality, customizable images can significantly enhance your projects. Doublesuzy offers a powerful Cognitive Action designed specifically for image generation through advanced inpainting techniques. This service allows developers to create visually striking images tailored to their needs, whether for marketing materials, social media posts, or creative projects. With features that support various models and customization options, Doublesuzy simplifies the image creation process while boosting creativity and fidelity.

Imagine needing to create a unique image for a client or a campaign. With Doublesuzy's image generation capabilities, you can input specific prompts and parameters, resulting in images that align perfectly with your vision. This flexibility makes it ideal for use in industries like advertising, e-commerce, and content creation.

Prerequisites

To get started with Doublesuzy's image generation capabilities, you'll need a valid Cognitive Actions API key and a general understanding of making API calls.

Generate Image with Inpainting and Customization

Doublesuzy's primary action focuses on generating images with inpainting and extensive customization options. This action solves the problem of creating tailored visuals that meet specific criteria, from aspect ratios to unique styles. It supports two model variants: the 'dev' model for detailed generation and the 'schnell' model for faster results.

Input Requirements

The action requires a prompt, which serves as the foundation for the generated image. Additional parameters include:

  • mask: Optional image mask for inpainting mode.
  • seed: For reproducible generation.
  • image: Input image for image-to-image or inpainting mode.
  • model: Choose between 'dev' and 'schnell'.
  • width & height: Specify dimensions only if using a custom aspect ratio.
  • goFast: Enable faster predictions.
  • outputQuality: Set quality from 0 to 100.
  • numberOfOutputs: Specify how many images to generate.

Expected Output

The output will be a URL link to the generated image, formatted in your specified output format (like WebP, JPG, or PNG).

Use Cases for this Specific Action

  1. Marketing Campaigns: Quickly generate eye-catching visuals that align with campaign themes.
  2. Social Media Content: Create tailored images for posts that resonate with your audience.
  3. E-Commerce: Develop product images that showcase items in unique settings or styles.
  4. Creative Projects: Provide artists and designers with a tool for generating inspiration and ideas.
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 = "308277d9-6d74-4065-805e-0e76245649ee" # Action ID for: Generate Image with Inpainting and Customization

# Construct the exact input payload based on the action's requirements
# This example uses the predefined example_input for this action:
payload = {
  "model": "dev",
  "goFast": false,
  "prompt": "portrait of suzy as a realtor with long wavy hair, and a friendly confident expression. She has one hand on her hip, french nails, with an inviting smile, evoking a poised professional vibe. Render this in bright sunlight in front of san antonio, texas tower of americas landscape downtown vibe, a soft yet cinematic soft skin  glow on suzy's face",
  "loraScale": 1,
  "outputQuality": 80,
  "extraLoraScale": 1,
  "promptStrength": 0.8,
  "imageMegapixels": "1",
  "numberOfOutputs": 1,
  "imageAspectRatio": "16:9",
  "imageOutputFormat": "webp",
  "numInferenceSteps": 28,
  "diffusionGuidanceScale": 3
}

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

Doublesuzy's image generation action offers immense value for developers looking to integrate customizable image creation into their applications. With its advanced inpainting techniques and flexible parameters, you can produce high-quality visuals tailored to specific needs. Whether you're enhancing marketing efforts or creating unique content, this action streamlines the image generation process and unleashes your creative potential.

Now that you're familiar with the capabilities of Doublesuzy, consider how you can incorporate this powerful tool into your projects to elevate your visual content.

← Back to All Articles