image-generation

Generate Stunning Images with Janelle's Inpainting Feature

26 Apr 2025
Generate Stunning Images with Janelle's Inpainting Feature

In the ever-evolving realm of image generation, Janelle stands out as a powerful tool for developers looking to create high-quality visuals quickly and efficiently. With its advanced inpainting capabilities, Janelle allows you to generate images that are not only visually appealing but also customizable to meet specific requirements. The optional fast mode ensures that you can optimize speed without sacrificing quality, making it an ideal choice for projects that demand rapid turnaround times.

Common use cases for Janelle's image generation capabilities include creating promotional materials, generating unique artwork for digital content, or even enhancing existing images with tailored modifications. Whether you're a developer working on a creative application or an artist seeking innovative ways to express your vision, Janelle offers the functionality to streamline your workflow and enhance your creative output.

Prerequisites

To get started with Janelle's Cognitive Actions, you will need a valid API key, along with a basic understanding of how to make API calls.

Generate Image with Inpainting and Fast Mode

This action allows you to generate images using cutting-edge inpainting techniques. You can choose to enable fast mode for quicker results, making it suitable for scenarios where time is of the essence. The action supports various customizations, including aspect ratios, LoRA intensity adjustments, and multiple output formats.

Input Requirements:

  • Prompt: A detailed text description of the desired image.
  • Mask/Image: Optionally provide a URI for an image mask or input image for inpainting.
  • Width/Height: Specify dimensions if using a custom aspect ratio.
  • Go Fast: Enable for faster image generation.
  • LoraScale: Adjust the influence of LoRA for your image.
  • OutputCount: Choose the number of images to generate (1-4).
  • GuidanceScale: Set the diffusion process's guidance level.
  • OutputQuality: Define the quality of the output images.
  • InferenceModel: Select between 'dev' or 'schnell' models for inference.

Expected Output: Upon successful execution, the action returns a URI link to the generated image(s), enabling you to access and utilize your new visual content effortlessly.

Use Cases for this specific action:

  • Marketing Campaigns: Quickly generate images for advertisements or social media posts, tailored to specific themes or branding.
  • Artistic Projects: Create unique pieces of art by combining different prompts and images, allowing for creative experimentation.
  • Content Creation: Enhance blog posts, articles, or websites with original visuals that resonate with the intended audience.
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 = "65452864-88de-4267-9db0-86f9fc9b7d48" # Action ID for: Generate Image with Inpainting and Fast Mode

# Construct the exact input payload based on the action's requirements
# This example uses the predefined example_input for this action:
payload = {
  "prompt": "Janelle in a professional photo, hair up, short hair. Dressed in white suit, thick body, with white background. Looking straight ahead. portrait. 4k",
  "loraScale": 1,
  "outputCount": 1,
  "guidanceScale": 3.5,
  "outputQuality": 90,
  "inferenceModel": "dev",
  "promptStrength": 0.8,
  "imageAspectRatio": "1:1",
  "imageOutputFormat": "webp",
  "additionalLoraScale": 1,
  "inferenceStepsCount": 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

Janelle's image generation capabilities, particularly with its inpainting feature and fast mode, provide developers with a versatile tool for creating stunning visuals tailored to their needs. Whether you are working on marketing materials, artistic projects, or enhancing digital content, Janelle simplifies the process and accelerates your workflow. As you explore these capabilities, consider how they can be integrated into your projects to elevate your creative output and engage your audience more effectively.

← Back to All Articles