image-generation

Create Stunning Images Effortlessly with Advlook Inpainting

27 Apr 2025
Create Stunning Images Effortlessly with Advlook Inpainting

Advlook is an innovative service designed to empower developers with advanced image generation capabilities. Through its Cognitive Actions, particularly the Image Generation with Inpainting feature, you can create high-quality images tailored to your specific needs, whether for artistic projects, marketing materials, or web design. The ability to customize aspects like resolution, aspect ratios, and inpainting enhances both the speed and quality of your image creation process.

Imagine needing to generate unique visuals for a campaign or content that stands out. With Advlook, you can quickly produce images that not only meet your creative vision but also allow for rapid iterations and adjustments. This is particularly beneficial in scenarios such as creating social media graphics, designing promotional materials, or generating concept art for games and animations.

Prerequisites

To get started with Advlook, you'll need a valid Cognitive Actions API key and a basic understanding of making API calls.

Generate Image with Inpainting

Purpose

The "Generate Image with Inpainting" action allows you to create high-quality images by providing a descriptive prompt and optional parameters. This action is particularly useful for filling in missing parts of images or creatively altering existing images, making it a versatile tool for developers working on various visual projects.

Input Requirements

To utilize this action, you must provide a prompt, which describes the desired image. Additionally, you can include parameters such as:

  • mask: A URI of the image mask for inpainting.
  • seed: An integer for reproducibility.
  • image: A URI of an existing image for modification.
  • Other customizable options like width, height, outputCount, and modelType.

Expected Output

The output will be a generated image based on your input parameters. For instance, an example output could look like:

  • https://assets.cognitiveactions.com/invocations/99a2c919-b702-417a-9967-004e554da4a3/025106ad-eebf-4efe-9383-0db568d2f07c.png

Use Cases for this Specific Action

  • Creative Projects: Generate unique artwork or illustrations based on specific themes or prompts, perfect for artists and designers.
  • Marketing Material: Quickly create visually appealing images for advertisements or social media posts that resonate with your target audience.
  • Game Development: Produce concept art or character designs that can be easily modified and refined during the development process.
  • Content Creation: Enhance blog posts or articles with custom images that capture the essence of the 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 = "9e8aec8f-67cd-43fc-9741-c2f714f705bf" # 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 = {
  "goFast": false,
  "prompt": "a, extreme close up man in balaclava and a black bomber doing a robbery in a bank, pointing a gun on the head, year 1970, in the style of CINELOOK ",
  "loraScale": 1,
  "modelType": "dev",
  "outputCount": 1,
  "guidanceScale": 3,
  "outputQuality": 100,
  "promptStrength": 0.8,
  "imageMegapixels": "1",
  "imageAspectRatio": "16:9",
  "imageOutputFormat": "png",
  "numInferenceSteps": 36,
  "additionalLoraStrength": 1
}

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

Advlook's Image Generation with Inpainting offers developers a powerful tool to create stunning visuals quickly and efficiently. With its customizable features and fast processing options, you can bring your creative ideas to life, whether for personal projects or professional applications.

Explore how you can integrate this action into your workflow, experiment with the various parameters, and unlock the potential of your visual content creation. The possibilities are endless with Advlook!

← Back to All Articles