image-generation

Create Stunning Images with Inpainting Using Toto

26 Apr 2025
Create Stunning Images with Inpainting Using Toto

In today's digital landscape, the ability to generate high-quality images quickly and efficiently is invaluable for developers. Toto offers a powerful Cognitive Action that allows you to generate images using inpainting techniques, giving you the flexibility to customize parameters such as model selection, aspect ratio, and image quality. This action streamlines the image generation process, making it faster and more efficient while supporting various output formats and enhanced results through additional LoRA weights.

Common use cases for this action include creating unique visual content for marketing, enhancing artwork, or developing custom graphics for applications and websites. Whether you're a game developer looking to create immersive environments or a content creator needing eye-catching visuals, Toto's image generation capabilities can significantly enhance your projects.

Prerequisites

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

Generate Image with Inpainting

The Generate Image with Inpainting action enables you to create images by filling in missing areas or modifying existing ones based on a descriptive prompt. This action is particularly useful for tasks that require customization of image content or style, allowing you to refine visuals according to specific requirements.

Input Requirements

The input for this action requires a structured object that includes essential parameters such as:

  • prompt: A descriptive text prompt for image generation (e.g., "a man named Toto posing on cruise ship with sidney opera house in the background, smiling and wearing boxed-strip shirt, overcast, 50mm").
  • mask: (Optional) A URI for the image mask used in inpainting mode.
  • image: (Optional) A URI for an input image used for transformation.
  • width and height: (Optional) Dimensions for the generated image, applicable when using custom aspect ratios.
  • modelType: Select between "dev" and "schnell" models for inference.
  • numOutputs: Specify the number of images to generate.
  • imageFormat: Choose the output file format (e.g., "png").
  • guidanceScale: Control the strength of the diffusion process for image realism.
  • Additional parameters like loraScale, promptStrength, and outputQuality allow for further customization.

Expected Output

The expected output is a generated image in the specified format. For example, a successful call might return:

  • ["https://assets.cognitiveactions.com/invocations/710cb961-0807-44c5-a9a5-4ea583902d17/09a932b3-e2d1-4941-9380-564b5ec0bdba.png"]

Use Cases for this Specific Action

  • Marketing Campaigns: Quickly generate tailored images that fit specific branding aesthetics or campaign themes.
  • Game Development: Create unique art assets for characters, environments, or promotional materials, enhancing the visual appeal of the game.
  • Artistic Expression: Artists can use this action to experiment with different styles and compositions, easily generating variations of their work.
  • Content Creation: Bloggers and social media managers can produce custom visuals that resonate with their audience, improving engagement.
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 = "1d7dd5b0-90e6-44d8-bde7-4d7983459f02" # 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 = {
  "prompt": "a man named Toto posing on cruise ship with sidney opera house in the background, smiling and wearing boxed-strip shirt, overcast, 50mm",
  "loraScale": 1,
  "modelType": "dev",
  "numOutputs": 1,
  "imageFormat": "png",
  "guidanceScale": 3.5,
  "outputQuality": 90,
  "extraLoraScale": 1,
  "promptStrength": 0.8,
  "imageAspectRatio": "3:4",
  "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

Toto's Generate Image with Inpainting action provides developers with a versatile tool to create stunning, customized images efficiently. By leveraging its various parameters, you can fine-tune the output to meet your specific needs, whether for marketing, gaming, or creative projects. To explore the full potential of image generation with Toto, start integrating this action into your applications today!

← Back to All Articles